Name Roll No.

Program Subject Code Learning Centre

Anil Sriram 520935193 MBA – SEM III Research Methodology MB 0034 [Set -1] [02815] Glace –Adyar, Chennai

Date of 06/12/2010 Submission

MB 0034

Page 1

Q 1. Give examples of specific situations that would call for the following types of research, explaining why – a) Exploratory research b) Descriptive research c) Diagnostic research d) Evaluation research. Ans.: Research may be classified crudely according to its major intent or the methods. According to the intent, research may be classified as: Basic (aka fundamental or pure) research is driven by a scientist's curiosity or interest in a scientific question. The main motivation is to expand man's knowledge, not to create or invent something. There is no obvious commercial value to the discoveries that result from basic research. For example, basic science investigations probe for answers to questions such as: • How did the universe begin? • • • What are protons, neutrons, and electrons composed of? How do slime molds reproduce? What is the specific genetic code of the fruit fly?

Most scientists believe that a basic, fundamental understanding of all branches of science is needed in order for progress to take place. In other words, basic research lays down the foundation for the applied science that follows. If basic work is done first, then applied spin-offs often eventually result from this research. As Dr. George Smoot of LBNL says, "People cannot foresee the future well enough to predict what's going to develop from basic research. If we only did applied research, we would still be making better spears." Applied research is designed to solve practical problems of the modern world, rather than to acquire knowledge for knowledge's sake. One might say that the goal of the applied scientist is to improve the human condition. For example, applied researchers may investigate ways to: • Improve agricultural crop production • • Treat or cure a specific disease Improve the energy efficiency of homes, offices, or modes of transportation

Some scientists feel that the time has come for a shift in emphasis away from purely basic research and toward applied science. This trend, they feel, is necessitated by the problems resulting from global overpopulation, pollution, and the overuse of the earth's natural resources. Exploratory research provides insights into and comprehension of an issue or situation. It should draw definitive conclusions only with extreme caution. Exploratory research is a type of research conducted because a problem has not been clearly defined. Exploratory research helps determine the best research design, data collection method and selection of subjects. Given its fundamental nature, exploratory research often concludes that a perceived problem does not actually exist. Exploratory research often relies on secondary research such as reviewing available literature and/or data, or qualitative approaches such as informal discussions with consumers, employees, management or competitors, and more formal approaches through in-depth interviews, focus groups, projective methods, case studies or pilot studies. The Internet allows for research methods that are more interactive in nature: E.g., RSS feeds efficiently supply researchers with up-to-date information; major search engine search results may be sent by email to researchers by services such as Google Alerts; comprehensive search results are tracked over lengthy

MB 0034

Page 2

periods of time by services such as Google Trends; and Web sites may be created to attract worldwide feedback on any subject. The results of exploratory research are not usually useful for decision-making by themselves, but they can provide significant insight into a given situation. Although the results of qualitative research can give some indication as to the "why", "how" and "when" something occurs, it cannot tell us "how often" or "how many." Exploratory research is not typically generalizable to the population at large. A defining characteristic of causal research is the random assignment of participants to the conditions of the experiment; e.g., an Experimental and a Control Condition... Such assignment results in the groups being comparable at the beginning of the experiment. Any difference between the groups at the end of the experiment is attributable to the manipulated variable. Observational research typically looks for difference among "in-tact" defined groups. A common example compares smokers and non-smokers with regard to health problems. Causal conclusions can't be drawn from such a study because of other possible differences between the groups; e.g., smokers may drink more alcohol than non-smokers. Other unknown differences could exist as well. Hence, we may see a relation between smoking and health but a conclusion that smoking is a cause would not be warranted in this situation. (Cp) Descriptive research, also known as statistical research, describes data and characteristics about the population or phenomenon being studied. Descriptive research answers the questions who, what, where, when and how. Although the data description is factual, accurate and systematic, the research cannot describe what caused a situation. Thus, descriptive research cannot be used to create a causal relationship, where one variable affects another. In other words, descriptive research can be said to have a low requirement for internal validity. The description is used for frequencies, averages and other statistical calculations. Often the best approach, prior to writing descriptive research, is to conduct a survey investigation. Qualitative research often has the aim of description and researchers may follow-up with examinations of why the observations exist and what the implications of the findings are. In short descriptive research deals with everything that can be counted and studied. But there are always restrictions to that. Your research must have an impact to the life of the people around you. For example, finding the most frequent disease that affects the children of a town. The reader of the research will know what to do to prevent that disease thus; more people will live a healthy life. Diagnostic study: it is similar to descriptive study but with different focus. It is directed towards discovering what is happening and what can be done about. It aims at identifying the causes of a problem and the possible solutions for it. It may also be concerned with discovering and testing whether certain variables are associated. This type of research requires prior knowledge of the problem, its thorough formulation, clear-cut definition of the given population, adequate methods for collecting accurate information, precise measurement of variables, statistical analysis and test of significance. Evaluation Studies: it is a type of applied research. It is made for assessing the effectiveness of social or economic programmes implemented or for assessing the impact of development of the project area. It is thus directed to assess or appraise the quality and quantity of an activity and its performance and to specify its attributes and conditions required for its success. It is concerned with causal relationships and is more actively guided by hypothesis. It is concerned also with change over time. Action research is a reflective process of progressive problem solving led by individuals working with others in teams or as part of a "community of practice" to improve the way they address issues and solve problems. Action research can also be undertaken by larger organizations or institutions, assisted or guided by professional researchers, with the aim of improving their strategies, practices, and knowledge of the environments within which they practice. As designers and stakeholders, researchers work with others to propose a new course of action to help their community improve its work practices (Center for Collaborative Action Research). Kurt Lewin, then a professor at MIT, first coined the term “action research” in about 1944, and it appears in his 1946 paper “Action Research and Minority Problems”. In that paper, he described action research as “a comparative research on the conditions and effects of various forms of social

MB 0034

Page 3

Action research is an interactive inquiry process that balances problem solving actions implemented in a collaborative context with data-driven collaborative analysis or research to understand underlying causes enabling future predictions about personal and organizational change (Reason & Bradbury. organizational. to 3rd-person research. On the other hand. What we conclude rejecting the null hypothesis is known as an alternative hypothesis. and inquiring occurring in the midst of emergent structure. then it is known as an alternative hypothesis. then we are accepting Ha. it may be more or less 100) MB 0034 Page 4 . From this starting point.. to 2nd-. For H0: µ= µ H0=100. we often talk about null and alternative hypotheses. briefly explain the difference between a) Null and alternative hypothesis b) Type 1 and type 2 error c) Two tailed and one tailed test d) Parametric and non-parametric tests. by moving beyond reflective knowledge created by outside experts sampling variables to an active moment-to-moment theorizing. After six decades of action research development. Then we would say that the null hypothesis is that the population mean is equal to the hypothesized mean 100 and symbolically we can express it as: H0: µ= µ H0=100 If our sample results do not support this null hypothesis. but how to develop genuinely well-informed action — how to conduct an action science” (Tolbert 2001). or societal transformation. This tension exists between ● those that are more driven by the researcher’s agenda to those more driven by participants. Those that are motivated primarily by instrumental goal attainment to those motivated primarily by the aim of personal. our research on our group (family/team). if we think that method A is superior. each of which is composed of a circle of planning. and • 1st-. “Knowledge is always gained through action and for action. then we are rejecting Ha and if we reject H0. and fact-finding about the result of the action”. aimed primarily at personal change.e. • Q 2. aimed primarily at improving the group. If we accept H0. not how to develop a reflective science about action. If we are to compare the superiority of method A with that of method B and we proceed on the assumption that both methods are equally good. Ans.: Some basic concepts in the context of testing of hypotheses are explained below 11) Null Hypotheses and Alternative Hypotheses: In the context of statistical analysis. many methodologies have evolved that adjust the balance to focus more on the actions taken or more on the research that results from the reflective understanding of the actions. data collecting. that is. to question the validity of social knowledge is to question. and ‘scholarly’ research aimed primarily at theoretical generalization and/or large scale change. These are symbolically represented as: Null hypothesis = H0 and Alternative hypothesis = Ha Suppose we want to test the hypothesis that the population mean is equal to the hypothesized mean (µ H0) = 100. we should conclude that something else is true.In the context of hypothesis testing. Action research challenges traditional social science. 2001).action and research leading to social action” that uses “a spiral of steps. then this assumption is termed as a null hypothesis. action. we may consider three possible alternative hypotheses as follows: Alternative Hypotheses Ha: µ≠µ H0 To be read as follows (The alternative hypothesis is that the population mean is not equal to 100 i. my research on my own action.

also called as level of significance of test. We may reject H0 when H0 is true and we may accept H0 when it is not true... because then the probability of rejecting it when it is true is α (the level of significance) which is chosen very small. while the alternative hypothesis represents all other possibilities. In case we take the significance level at 5%. and the null hypothesis is the one that is to be disproved. which is known as a decision rule. In other words. If the rejection of a certain hypothesis when it is actually true involves great risk. keeping the alternative hypothesis in view. it is taken as null hypothesis. and Type II error is denoted by β(beta).e.e.. if H0 is that a certain lot is good (there are very few defective items in it).Ha: µ>µ H0 Ha: µ< µ H0 (The alternative hypothesis is that the population mean is greater than 100) (The alternative hypothesis is that the population mean is less than 100) The null hypotheses and the alternative hypotheses are chosen before the sample is drawn (the researcher must avoid the error of deriving hypotheses from the data he collects and testing the hypotheses from the same data). according to which we accept H0 (i. then this implies that H0 will be rejected when the sampling result (i. It is always some percentage (usually 5%). then we must decide the number of items to be tested and the criterion for accepting or rejecting the hypothesis. one can assign the probabilities to different possible sample results. Generally.05 probability of occurring if H0 is true.e. we make a rule. For instance. 34) Type I & II Errors: In the context of testing of hypotheses. otherwise we will reject H0 (or accept Ha). which should have been accepted. reject Ha) or reject H0 (i. which is to be proved. the 5% level of significance means that the researcher is willing to take as much as 5% risk rejecting the null hypothesis when it (H0) happens to be true. but this cannot be done if we proceed with alternative hypotheses. Thus a null hypothesis represents the hypothesis we are trying to reject. which should have been rejected. the following considerations are usually kept in view: 1a. We might test 10 items in the lot and plan our decision saying that if there are none or only 1 defective item among the 10. MB 0034 Page 5 . we will accept H0.. observed evidence) has a less than 0. The alternative hypothesis is usually the one. Hence the use of null hypotheses (at times also known as statistical hypotheses) is quite frequent. Type I error is denoted by α (alpha). it should not state an approximate value. Type I error means rejection of hypotheses. against Ha. thought and reason. 12) The Level of Significance: This is a very important concept in the context of hypothesis testing. In other words. in hypothesis testing. we proceed on the basis of the null hypothesis. This sort of basis is known as a decision rule. 3c. and Type II error means accepting of hypotheses. In the choice of null hypothesis. there are basically two types of errors that we can make. accept Ha). 23) Decision Rule or Test of Hypotheses: Given a hypothesis Ha and an alternative hypothesis H0. which should be chosen with great care.e. Why so? The answer is that on the assumption that the null hypothesis is true. The former is known as Type I and the latter is known as Type II. The null hypothesis should always be a specific hypothesis i. 2b. that the lot is not good (there are many defective items in it). Thus the significance level is the maximum value of the probability of rejecting H0 when it is true and is usually determined in advance before testing the hypothesis.

these two terms are quite important and must be clearly understood. whereas type II error means taking a chance that an entire group of users of this chemicals compound will be poisoned.Decision Accept H0 H0 (true) Ho (false) Reject H0 Correct decision Type II error (β error) Type I error (α error) Correct decision The probability of Type I error is usually determined in advance and is understood as the level of significance of testing the hypotheses. In some. Generally speaking parametric methods make more assumptions than non-parametric methods. parametric formulae are often simpler to write down and faster to compute. But with a fixed sample size n.05 (equally split on both tails of the curve as 0. the probability of committing type II error increases. and wavelets. A one-tailed test would be used when we are to test. If those extra assumptions are correct. If significance level is 5 % and the two-tailed test is to be applied. parametric methods can be very misleading. it means there are about 5 chances in 100 that we will reject H0 when H0 is true. Data Envelopment Analysis provides efficiency coefficients similar to those obtained by Multivariate Analysis without any distributional assumption. the probability of the rejection area will be 0. splines. Parametric statistics is a branch of statistics that assumes data come from a type of probability distribution and makes inferences about the parameters of the distribution most well known elementary statistical methods are parametric. with an example of each. However. If we take µ = 100 and if our sample mean deviates significantly from µ. say. If type I error is fixed at 5%.01. parametric methods can produce more accurate and precise estimates. Kernel density estimation provides better estimates of the density than histograms. one must make all possible efforts to strike an adequate balance between Type I & Type II error. in that case we shall accept the null hypothesis.025) and that of the acceptance region will be 0. especially if care is taken to examine diagnostic statistics. their simplicity makes up for their non-robustness. They are said to have more statistical power. 15) Two Tailed Test & One Tailed Test: In the context of hypothesis testing. if we fix it at 1%. they are not distribution-free. then in such a situation one should prefer a type I error to a type II error. when we try to reduce type I error. if those assumptions are incorrect. Both types of errors cannot be reduced simultaneously. since there is a trade-off in business situations. Nonparametric regression and semi parametric regression methods have been developed based on kernels. On the other hand. We can control type I error just by fixing it at a lower level. The term nonparametric is not meant to imply that such models completely lack parameters but that the number and nature of the parameters are flexible and not fixed in advance. But there are situations when only a one-tailed test is considered appropriate. Q 3. If type I error involves time and trouble of reworking a batch of chemicals that should have been accepted. the sample mean is significantly higher or lower than the hypothesized value of the mean of the population. Explain the difference between a causal relationship and correlation. What are the possible reasons for a correlation between two variables? MB 0034 Page 6 .95. one must set a very high level for type I error in one’s testing techniques of a given hypothesis. whether the population mean is either lower or higher than some hypothesized value. Decision makers decide the appropriate level of type I error by examining the costs of penalties attached to both types of errors. Because parametric statistics require a probability distribution. Hence. As a result. but definitely not all cases. say. For that reason they are often not considered robust. Non-parametric models differ from parametric models in that the model structure is not specified a priori but is instead determined from data. in testing of hypotheses. For instance. we will say that the maximum probability of committing type I error would only be 0. Such a test is inappropriate when we have H0: µ= µ H0 and Ha: µ≠µ H0 which may µ>µ H0 or µ<µ H0. A two-tailed test rejects the null hypothesis if.

(the relationship is due to chance) or causative association (one variable causes the other). Social Media and Application Development. people. which emphasizes customer retention and satisfaction. automate those marketing and communication activities on concrete marketing sequences that could run in autopilot (also known as marketing sequences). and the best way to give the customer what he or she wants. Just like Customer relationship management(CRM). The correlation ratio is able to detect almost any functional dependency. i. it does not completely characterize the dependence structure (for example. The correlation coefficient completely defines the dependence structure only in very particular cases. it generally denotes a company-wide business strategy embracing all clientfacing departments and even beyond. organize. and reduce the costs of marketing and client service. processes. attract. and technology work in synergy to increase profitability. Relationship Marketing differs from other forms of marketing in that it recognizes the long term value of customer relationships and extends communication beyond intrusive advertising and sales promotional messages. and styles. synchronize business processes (principally sales and marketing activities) and most importantly. Distance correlation and Brownian covariance / Brownian correlation [8][9] were introduced to address the deficiency of Pearson's correlation that it can be zero for dependent random variables. Relationship Marketing is a broadly recognized. and win new clients. availability. nurture and retain those the company already has. Marketing research looks at trends in sales and studies all of the variables. and providing it. a multivariate t-distribution's degrees of freedom determine the level of tail dependence). This includes tools for managing relationships with customers that goes beyond simple demographic and customer service data. and let friends and family know where they got it. [1] Once simply a label for a category of software tools.: Correlation: The correlation is knowing what the consumer wants. Casual relationship Marketing was first defined as a form of marketing developed from direct response marketing campaigns. entice former clients back into the fold. If you can give the customer what they want. they will buy. With the growth of the internet and mobile platforms. widely-implemented strategy for managing and nurturing a company’s interactions with clients and sales prospects.) In the case of elliptic distributions it characterizes the (hyper-)ellipses of equal density. The information given by a correlation coefficient is not enough to define the dependence structure between random variables.e. Relationship Marketing extends to include Inbound Marketing efforts (a combination of search optimization and Strategic Content). for example when the distribution is a multivariate normal distribution. price. Relationship Marketing has continued to evolve and move forward as technology opens more collaborative and social communication channels. As a practice. and reduce operational costs Reasons for a correlation between two variables: Chance association. Making them happy makes the money. today. zero distance correlation and zero Brownian correlation imply independence. When an implementation is effective.Ans. (See diagram above. color. however. rather than a dominant focus on sales transactions. The overall goals are to find. or the entropy-based mutual information/total correlation which is capable of detecting even more general MB 0034 Page 7 . PR. It also involves using technology to.

The polychoric correlation is another correlation applied to ordinal data that aims to estimate the correlation between theorised latent variables. What are the characteristics of a good sample? Ans. One way to capture a more complete view of dependence structure is to consider a copula between them. we may or may not represent the population well. practical or theoretically sensible to do random sampling. In many research contexts. have you ever run into people in a mall or on the street who are carrying a clipboard and who are stopping various people and asking if they could interview them? Most likely they are conducting a purposive sample (and MB 0034 Page 8 . We usually would have one or more specific predefined groups we are seeking.: The difference between non-probability and probability sampling is that non-probability sampling does not involve random selection and probability sampling does. we sample with a purpose in mind. I would also argue that the typical use of college students in much psychological research is primarily a matter of convenience. Q 4. I would include in this category the traditional "man on the street" (of course. do you?). However. Briefly explain any two factors that affect the choice of a sampling technique. we know the odds or probability that we have represented the population well. the problem with all of these types of samples is that we have no evidence that they are representative of the populations we're interested in generalizing to -. we sample simply by asking for volunteers. in comparison to those that consider only 2nd moment (pairwise or quadratic) dependence. Most sampling methods are purposive in nature because we usually approach the sampling problem with a specific plan in mind. researchers prefer probabilistic or random sampling methods over non probabilistic ones. We are able to estimate confidence intervals for the statistic. and consider them to be more accurate and rigorous. In clinical practice. But it does mean that non-probability samples cannot depend upon the rationale of probability theory. now it's probably the "person on the street") interviews conducted frequently by television news programs to get a quick (although non representative) reading of public opinion. In general. Purposive Sampling In purposive sampling. Does that mean that non-probability samples aren't representative of the population? Not necessarily. At least with a probabilistic sample. Clearly. in applied social research there may be circumstances where it is not feasible.dependencies. Haphazard or Convenience Sampling One of the most common methods of sampling goes under the various titles listed here. The latter are sometimes referred to as multi-moment correlation measures. and it will often be hard for us to know how well we've done so. (You don't really believe that psychologists use college students because they believe they're representative of the population at large. With non-probability samples. For instance. we consider a wide range of non-probabilistic alternatives. Accidental. Here.and in many cases we would clearly suspect that they are not. We can divide non-probability sampling methods into two broad types: Accidental or purposive. The most important distinctions among these types of sampling methods are the ones between the different types of purposive sampling approaches. we might use clients who are available to us as our sample.

you are likely to get the opinions of your target population. how do we know what the "typical" or "modal" case is? We could say that the modal voter is a person who is of average age. you're not concerned with having numbers that match the proportions in the population. educational level. • Quota Sampling In quota sampling. for instance. you specify the minimum number of sampled units you want in each category. For instance. In this case. And. how do you know that those three variables -. if you've already got the 40 women for your sample. In proportional quota sampling you want to represent the major characteristics of the population by sampling a proportional amount of each. In all of these methods we know what we want -.we are sampling with a purpose. Or.are the only or even the most relevant for classifying the typical voter? What if religion or ethnicity is an important discriminator? Clearly. They size up the people passing by and anyone who looks to be in that category they stop to ask if they will participate. Purposive sampling can be very useful for situations where you need to reach a targeted sample quickly and where sampling for proportionality is not the primary concern. First. they interview a "typical" voter. age. First. • Expert Sampling Expert sampling involves the assembling of a sample of persons with known or demonstrable experience and expertise in some area. if you know the population has 40% women and 60% men. and income in the population. you will continue sampling until you get those percentages and then you will stop. because it would be the best way to elicit the views of persons who have specific expertise. We might sample for diversity as in heterogeneity sampling.you have some acknowledged experts to back you.age. In sampling. and that you want a total sample size of 100. you simply want to have MB 0034 Page 9 .most likely they are engaged in market research). as in snowball sampling. or the "typical" case. But. In this method. you select people non-randomly according to some fixed quota. you will continue to sample men but even if legitimate women respondents come along. The advantage of doing this is that you aren't out on your own trying to defend your decisions -. but not the sixty men. The disadvantage is that even the experts can be. we might capitalize on informal social networks to identify specific respondents who are hard to locate otherwise." There are actually two reasons you might do expert sampling. • Modal Instance Sampling In statistics. So. and often are. With a purposive sample. we convene such a sample under the auspices of a "panel of experts. or quota sampling. We might sample for specific groups or types of people as in modal instance. One of the first things they're likely to do is verify that the respondent does in fact meet the criteria for being in the sample. it's not clear that using the averages of these is the fairest (consider the skewed distribution of income. wrong." The problem here (as in much purposive sampling) is that you have to decide the specific characteristics on which you will base the quota. Will it be by gender. Here. the mode is the most frequently occurring value in a distribution.? Non-proportional quota sampling is a bit less restrictive. we are sampling the most frequent case. expert sampling is essentially just a specific sub case of purposive sampling. In a lot of informal public opinion polls. you will not sample them because you have already "met your quota. but you are also likely to overweight subgroups in your population that are more readily accessible. You might convene an expert panel consisting of persons with acknowledged experience and insight into that field or topic and ask them to examine your modal definitions and comment on their appropriateness and validity. etc. But the other reason you might use expert sampling is to provide evidence for the validity of another sampling approach you've chosen. There are a number of problems with this sampling approach. let's say you do modal instance sampling and are concerned that the criteria you used for defining the modal instance are subject to criticism. There are two types of quota sampling: proportional and non proportional. education race. income -. They might be looking for Caucasian females between 30-40 years old. expert. Instead. religion. modal instance sampling is only sensible for informal sampling contexts. education. for instance). All of the methods that follow can be considered subcategories of purposive sampling methods. For instance. when we do a modal instance sample. Often.

not the population of people who have the ideas. Clearly. you are not likely to be able to find good lists of homeless people within a specific geographical area. there are times when it may be the best method available. However. After gaining sufficient knowledge about the population through the exploratory study. where the research objective requires statistical inference.enough to assure that you will be able to talk about even small groups in the population. it is difficult to apply a probability sampling method. probability sampling should be used. marketing surveys. not identifying the "average" or "modal instance" ones. then an appropriate probability sampling method must be selected. if you go to that area and identify one or two. Where even crude results would serve the purpose (E. The Nature of the Population: In terms of the variables to be studied. 22. • Snowball Sampling In snowball sampling. readership surveys etc). The researcher has to first identify the limiting factor or factors and must judiciously balance the conflicting factors.Measurability: The application of statistical inference theory requires computation of the sampling error from the sample itself. Hence. Although this method would hardly lead to representative samples.Degree of Precision: Should the results of the survey be very precise. stratified random sampling is appropriate. • Heterogeneity Sampling We sample for heterogeneity when we want to include all opinions or views. This method is the non-probabilistic analogue of stratified random sampling in that it is typically used to assure that smaller groups are adequately represented in your sample. Where a high degree of precision of results is desired.g.. what we would like to be sampling is not people. In effect. If the population is heterogeneous. we have to include a broad and diverse range of participants. even simple random sampling will give a representative sample. In many brainstorming or nominal group processes (including concept mapping). Purpose of the Survey: What does the researcher aim at? If he intends to generalize the findings based on the sample survey to the population. you begin by identifying someone who meets the criteria for inclusion in your study. if you are studying the homeless. or could even rough results serve the purpose? The desired level of precision is one of the criteria for sampling method selection. we would use some form of heterogeneity sampling because our primary interest is in getting broad spectrum of ideas. an appropriate probability sampling design may be adopted. 44. any convenient nonrandom sampling like quota sampling would be enough. Snowball sampling is especially useful when you are trying to reach populations that are inaccessible or hard to find. Characteristics of good Sample: The decision process is a complicated one. For instance. you may find that they know very well whom the other homeless people in their vicinity are and how you can find them. almost the opposite of modal instance sampling. but ideas. MB 0034 Page 10 . You then ask them to recommend others who they may know who also meet the criteria. The choice of a particular type of probability sampling depends on the geographical area of the survey and the size and the nature of the population under study. the sample should be drawn by applying simple random sampling method or stratified random sampling method. in order to get all of the ideas. depending on whether the population is homogenous or heterogeneous. Heterogeneity sampling is. The various criteria governing the choice of the sampling technique are: 11. 33. Information about Population: How much information is available about the population to be studied? Where no list of population and no information about its nature are available. We imagine that there is a universe of all possible ideas relevant to some topic and that we want to sample this population. Only probability samples allow such computation. and we aren't concerned about representing these views proportionately. is the population homogenous or heterogeneous? In the case of a homogenous population. and especially the "outlier" or unusual ones. Another term for this is sampling for diversity. in this sense. Then an exploratory study with non-probability sampling may be done to gain a better idea of the population. 55.

the precision has to be sacrificed to some extent. Q 5. The chosen plan thus represents an adaptation of the sampling theory to the available facilities and resources. They may also be external sources. e.. as a compromise. Secondary sources may be internal sources.: Primary Sources of Data Primary sources are original sources from which the researcher directly collects data that has not been previously collected. or even quota sampling as a compromise. 99. Where the finance is not a constraint. Economy: It should be another criterion in choosing the sampling method. Time Limitation: The time limit within which the research project should be completed restricts the choice of a sampling method. collection of data directly by the researcher on brand awareness. instead of stratified sampling/sampling with probability proportional to size. Financial Resources: If the available finance is limited. such as annual reports. financial statements. it represents a compromise between idealism and feasibility. sales reports. it may become necessary to choose a less costly sampling plan like multistage cluster sampling. which has been collected and compiled for another purpose. instead of single-stage sampling of elements. 77. minutes of meetings and other information that is available within the firm. 88. compared to gathering information from available sources 2 Data collection is a time consuming process 3 It requires trained interviewers and investigators 2 Secondary Sources of Data These are sources containing data. The above criteria frequently conflict with each other and the researcher must balance and blend them to obtain a good sampling plan. a researcher can choose the most appropriate method of sampling that fits the research objective and the nature of population. experiments and observation. One should use simple workable methods. A sample is economical if the precision per unit cost is high. multistage cluster sampling would be appropriate. Then. Select any topic for research and explain how you will use both secondary and primary sources to gather the required information. But if the area and the size of the population are small. unlike published information that is already available The disadvantages are – 1 It is expensive to collect. However. or multi-stage cluster sampling. single stage probability sampling methods could be used. That is. in the form of a marketing information system. for the purposes of the project immediately at hand. and brand loyalty and other aspects of consumer behavior. Of course. it may become necessary to choose less time consuming methods like simple random sampling. if the objectives of the study and the desired level of precision cannot be attained within the stipulated budget. Ans. It means achieving the desired level of precision at minimum cost. Primary data is first hand information collected through various methods such as surveys. Geographical Area of the Study and the Size of the Population: If the area covered by a survey is very large and the size of the population is quite large. The advantages of primary data are – 1 It is unique to a particular research study 2 It is recent information. brand preference. there is no alternative but to give up the proposed survey. instead of unduly elaborate and complicated techniques. or the cost per unit of variance is low. from a sample of consumers by interviewing them.66. such as MB 0034 Page 11 .g. inventory records.

audits and panels. census reports. It is a method of research involving collection of data directly from a population or a sample at a particular time.). trade associations (e. and his environment. which include: 1 Personal interview 2 Telephone interview 3 Mail survey and 4 Fax survey Personal Interview Personal interviewing is one of the prominent methods of data collection.g. trade and financial journals. Chambers of Commerce) and commercial services (outside suppliers of information). Interviewing may be used either as a main method or as a supplementary one in studies of persons. A survey has certain characteristics: 1 It is always conducted in a natural setting. radio listening and T. leadership studies. viewing surveys. knowledge-awareness practice (KAP) studies. sociological studies of social problems and social institutions. etc. It is useful for collecting a wide range of data. opinion polls. World Bank and International Monetary Fund. required data is not available from secondary sources and it has to be directly gathered from the primary sources. the researcher can collect the required data precisely according to his research needs and he can collect them when he wants and in the form that he needs it. Methods of Data Collection: The researcher directly collects primary data from its original sources. from factual demographic data to highly personal and intimate information relating to a person’s opinions. It may be defined as a two-way systematic conversation between an investigator and an informant. Yet. In this case. It involves not only conversation. Interviewing is appropriate when qualitative information is required. attitudes. Interviewing is the only suitable method for gathering information from illiterate or less educated respondents. initiated for obtaining information relevant to a specific study. or probing is necessary to draw out the respondent fully. for several types of social science research. published sources (annual reports of currency and finance published by the Reserve Bank of India. but also learning from the respondent’s gestures. 4 It may include an extensive study or an intensive study 5 It covers a definite geographical area. 1 Survey Research A survey is a fact-finding study. including surveys.g. publications of international organizations such as the UN. business management studies etc. observation and experiments. It is a field study. A survey involves the following steps 1 Selection of a problem and its formulation 2 Preparation of the research design 3 Operation concepts and construction of measuring indexes and scales 4 Sampling 5 Construction of tools for data collection 6 Field work and collection of data 7 Processing of data and tabulation 8 Analysis of data 9 Reporting There are four basic survey methods. beliefs. experiences and future intentions. social anthropological studies of rural communities and tribal communities.government agencies (e. marketing research.V. Primary data has to be gathered in cases where the available data is inappropriate. farm management studies. attitudinal surveys. values. But the collection of primary data is costly and time consuming. 3 It can cover a very large population. Where the area covered for MB 0034 Page 12 . It includes: socio economic surveys. reports of government departments). inadequate or obsolete. There are various methods of primary data collection. facial expressions and pauses. 2 It seeks responses directly from the respondents.

the investigator has to get himself/herself introduced to the respondent in an appropriate manner. It can also be conducted with a group of persons. personal interview is feasible. It will be useful in the following situations: 11. 3. Interview is often superior to other data-gathering methods. Although the interview is usually a conversation between two persons. a survey relating to trade conducted by a trade association or a chamber of commerce. The interview is not a mere casual conversational exchange. The respondent reacts to the interviewer’s appearance. 10. or when a sufficient number of qualified interviewers are available. momentary experience for them. The interview is an interactive process. It permits probing into the context and reasons for answers to questions. depending on the requirements of the study. Interviewing as a method of data collection has certain characteristics.g. This poses a problem of seeing that recording does not interfere with the tempo of conversation. It permits the investigator to seek clarifications and brings to the forefront those questions. The participants – the interviewer and the respondent – are strangers. It has a fixed beginning and termination points. 3 Telephone Interviewing Telephone interviewing is a non-personal method of data collection. which for some reason or the other the respondents do not want to answer. or a group of customers.g. 7.g. his perception of the thrust of the questions and his own personal needs. It enables the investigator to grasp the behavioral context of the data furnished by the respondents. Interview can add flesh to statistical information. 13. a survey relating to a profession conducted by the concerned professional association. e. hence. People are usually more willing to talk than to write. it need not be limited to a single respondent. psychological process. Interviewing is not a standardized process like that of a chemical technician. the interviewer should try to be closer to the social-economic level of the respondents. 5. 4. viz. MB 0034 Page 13 . When the survey must be conducted in a very short period of time. Once rapport is established. 6.. obtaining information relevant to a study. business executives. e. When the universe is composed of those persons whose names are listed in telephone directories. a radio or television program survey. The interview is a mode of obtaining verbal answers to questions put verbally.the survey is compact. facial expression and intonation. They are: 1. As far as possible. The investigator records information furnished by the respondent in the interview. gestures. 8. such as family members. 9. it is rather a flexible. When the subject is interesting or important to respondents. e. business houses. The interaction between the interviewer and the respondent depends upon how they perceive each other. The relationship between the participants is a transitory one. 14. When the study requires responses to five or six simple questions. provided the units of study are listed in the telephone directory. 12. because the interview can also be conducted over the telephone. or a group of children. even confidential information may be obtained. behavior. but a conversation with a specific purpose. It may be used as a major method or as a supplementary method. doctors and other professionals. The interaction between the interviewer and the respondent need not necessarily be on a face-to-face basis. 2. The interview proper is a fleeting.

beliefs. so that it could be completed within a few minutes. 44. 5 Mail Survey The mail survey is another method of collecting primary data. it is not desirable to reveal it. when such information may bias the result. It is desirable to address the respondent by name. It must anticipate objections and answer them briefly.15. or by a letter. so as to attract the attention of the respondent. The desired information may be obtained through self-administered questionnaire or interview. Free discussion is encouraged on some aspect of the subject under study. he must be aware that a single comment by a member can provide important insight. When the respondents are widely scattered and when there are many call backs to make. or advance notice in the newsletter of the concerned organization. Advance information: Advance information can be provided to potential respondents by a telephone call. Follow-up-contacts: In the case of respondents belonging to an organization. They are: 11. The distinctive feature of the mail survey is that the questionnaire is self-administered by the respondents themselves and the responses are recorded by them and not by the investigator. This method involves sending questionnaires to the respondents with a request to complete them and return them by post. In particular. as in the case of personal interview method. The progress in return may be watched and at the appropriate stage. However.  The sponsor’s identity may be revealed. intentions and opinions among individuals in the group. a disguised organization name may be used. In a personal interview. 1 After a few days from the date of mailing the questionnaires to the respondents.  A self-addressed stamped envelope should be enclosed in the covering letter. It must explain to the respondent the purpose of the study and the importance of his cooperation to the success of the project.  Anonymity must be assured. It does not involve face-to-face conversation between the investigator and the respondent. they may be approached through someone in that organization known as the researcher. the interviewers look for evidence of common elements of attitudes. The mail questionnaires should be simple so that the respondents can easily understand the questions and answer them. This can be used in the case of educated respondents only. so as to attract and hold the interest of the respondent. the flow of information is multi dimensional. stamps for collection and other incentives are also used to induce respondents to complete and return the mail questionnaire. Communication is carried out only in writing and this requires more cooperation from the respondents than verbal communication. clubs and other organized groups. the researcher can expect the return of completed ones from them. Quality printing: The questionnaire may be neatly printed on quality light colored paper. The response rate in mail surveys is generally very low in developing countries like India. with the discussion serving as a guide to ensure consideration of the areas of concern. follow-up efforts can be made. The discussion leader stimulates the group members to interact with each other. Certain techniques have to be adopted to increase the response rate. It should preferably contain mostly closed-ended and multiple choice questions. by collecting the addresses from the telephone directory of the association or organization to which they belong. Incentives: Money. 55. MB 0034 Page 14 . 22. In this case. Such preliminary contact with potential respondents is more successful than follow-up efforts. The interviewer acts as the discussion leader. a covering letter should accompany a copy of the questionnaire. Samples for group interviews can be obtained through schools. 4 Group Interviews A group interview may be defined as a method of collecting primary data in which a number of individuals with a common interest interact with each other. 33. At the same time. The group may consist of about six to eight individuals with a common interest. The researcher should prepare a mailing list of the selected respondents. Covering letter: The covering letter should be couched in a pleasant style. The following procedures should be followed .

66. weather. at clarifying contradictory findings. You may read about certain findings and notice that a certain field was not covered. 7 8Q 6.: Title: Newspaper reading choices Research problem: A research problem is the situation that causes the researcher to feel apprehensive. Long before any competition from cable television or Nintendo. Comparing reader content preferences over a 10-year period. Ans. editorials. at reconciling conflicting opinions. It is the demarcation of a problem area within a certain context involving the WHO or WHAT. For example. Larger sample size: A larger sample may be drawn than the estimated sample size.16 Younger readers showed increased interest in national news. A number of studies explored how young readers evaluate and use newspaper content. A second source could be scientific literature. at correcting a faulty methodology. the WHERE. Own experience or the experience of others may be a source of problem supply. Three sources usually contribute to problem identification. Gerald Stone and Timothy Boudreau found differences between readers ages 18-34 and those 35-plus. Shortcomings in theories could be researched. American newspaper publishers were worrying about declining readership among the young. the WHEN and the WHY of the problem situation. Even where circulation has grown or stayed stable. and food advertisements higher. Interest in international news and letters to the editor was less among MB 0034 Page 15 . As early as 1960. while older readers ranked weather. One of the underlying concerns behind the decline in youth newspaper reading is the question of how young people view the newspaper. at least 20 years prior to Music Television (MTV) or the Internet. confused and ill at ease. define the research problem and the objectives or questions to be answered by the study. media research scholars1 began to focus their studies on young adult readers' decreasing interest in newspaper content. This may help the researcher to secure an effective sample size closer to the required size. there is rising concern over penetration.2 Simply put. or at solving existing practical problems Types of questions to be asked :For more than 35 years. Case Study: You are engaged to carry out a market survey on behalf of a leading Newspaper that is keen to increase its circulation in Bangalore City. This could lead to a research problem. Develop a title for the study. a sample of 1500 may be drawn. This study looks at trends in newspaper readership among the 18-to-34 age group and examines some of the choices young adults make when reading newspapers. Research can thus be aimed at clarifying or substantiating an existing theory. the news about newspapers and young readers has been mostly bad for the newspaper industry. and classified advertisements over the decade between 1984 and 1994. sports. The concern over a declining youth market preceded and perhaps foreshadowed today's fretting over market penetration. defined as the percentage of occupied households in a geographic market that are served by a newspaper. population growth is occurring more rapidly than newspaper readership in most communities. in order to ascertain reader habits and interests. if the required sample size is 1000. There are many problem situations that may give rise to research. at correcting the inadequate or unsuitable use of statistical techniques. Theories could be a third source.

However. The researchers found no significant differences in readership among various academic majors. 133 (49. 53 majors were represented. Courses that comprise the framework for this sample were selected because they could fulfill basic studies requirements for all majors. In all. In each of the eight classes. Most (214) of the students were enrolled full time.3 percent) were male and 177 (66. The goal of this sampling procedure was to reach a cross-section of students representing various fields of study. 10 (3.8 percent).8 percent) Native American.8 percent) said they were of the Caucasian race. and books. school-age children.8 percent) Asian. In a study of younger. Procedure After two pre-tests and revisions. 59 (22.4 percent). magazines. A total of 25 participants chose not to divulge their genders. 65 (24. including electronic mail and computer networks. The study found that newspaper subscribers preferred print formats over electronic.younger readers. The researcher obtained permission from seven professors to distribute questionnaires in the eight classes during regularly scheduled class periods. whereas a few (28) were parttime students. were unrelated to newspaper readership. Of the 267 students who participated in the study. The class rank breakdown was: freshmen. The researcher provided pencils and was available to answer questions if anyone needed further assistance.9 percent) African/Native American. and phone number. two students declined.and 200-level English courses at a midwestern public university. with older readers more interested in news about public affairs. The study discovered that overall newspaper readership was positively related to students' focus on entertainment. Ages ranged from 17 to 56.4 percent) Arabic. obituaries. 15 (5. sophomores. five (1.8 percent) Hispanic.6 years. seniors.19 exploring the influence of media use. with MB 0034 Page 16 . 33 (12. but that young readers would choose an electronic newspaper over a printed one. Leo Jeffres and Atkin assessed dimensions of interest in newspapers. or by gender. while older readers showed less interest in reports of births.18 In an exploration of leisure reading among college students. though there was a slight correlation between age and the public affairs readership index. job / travel information.17 He reported that computer-related technologies.9 percent). and academic major on newspaper content preferences.1 percent) African American. and marriages. two (.6 percent). questionnaires were distributed and collected by the investigator. non-media leisure. the researcher introduced herself to the students as a journalism professor who was conducting a study on students' use of newspapers and other media. Each questionnaire included a cover letter with the researcher's name. The average time spent on the questionnaires was 20 minutes. and graduate students. Methodology Sample Participants in this study (N=267) were students enrolled in 100. This mean does not include the 32 respondents who declined to give their ages. 45 (16. the students' preference for reading as a leisure-time activity was related only to a public affairs focus. A total of 157 participants (58. Brian Brooks and James Kropp found that electronic newspapers could persuade children to become news consumers. juniors. address. with a mean age of 23. and public affairs. Content preferences for newspapers and other print media were related.3 percent) were female. and one (. 16 (6 percent). David Atkin explored the influence of telecommunication technology on newspaper readership among students in undergraduate media courses. The students' participation was voluntary. two (. A basic studies course is one that is listed within the core curriculum required for all students.

Roll No. Approximately six students asked to take the questionnaires home to finish.some individual students taking as long as an hour. Program Subject Code Learning Centre 520935193 MBA – SEM III Research Methodology MB 0034 [Set -2] [02815] Glace –Adyar. They returned the questionnaires to the researcher's mailbox within a couple of day. Chennai Date of 06/12/2010 Submission MB 0034 Page 17 .

Discuss the relative advantages and disadvantages of the different methods of distributing questionnaires to the respondents of a study. For example. This method may be useful for large-scale studies on topics of common interest. behavior or attitudes. because under this method.  the panel method offers a good way of studying trends in events. Newsstand inserts: This method involves inserting the covering letter. tears it out and mails it to the advertiser.: There are some alternative methods of distributing questionnaires to the respondents. it combines the advantages of the personal interview and the mail survey.Q 1.  A panel study also provides evidence on the causal relationship between variables. They are: 1) Personal delivery. questionnaire and self addressed reply-paid envelope into a random sample of newsstand copies of a newspaper or magazine. the questionnaires may be delivered in person and the respondents may return the completed questionnaires through mail. A gift or a discount coupon usually rewards the respondent. a political scientist can study the shifts in inclinations of voters and the causative influential factors during an election. the effect of public relations or advertising campaigns or welfare measures can be measured by collecting data before. the event or action is reported soon after its occurrence. it enables an economics researcher to study how employment. a panel enables a market researcher to study how brand preferences change from month to month. with a request to complete them at their convenience. Personal delivery: The researcher or his assistant may deliver the questionnaires to the potential respondents. 3) Advertising the questionnaire in a newspaper or magazine. the committee of Banks Customer Services used this method for collecting information from the customers of commercial banks in India.  this method makes it possible to have before and after designs made for field based studies. Advertising the questionnaire: The questionnaire with the instructions for completion may be advertised on a page of a magazine or in a section of newspapers. For example. income and expenditure of agricultural laborers change from month to month. Advantages and Disadvantages: The advantages of Questionnaire are:  this method facilitates collection of more accurate data for longitudinal studies than any other method. Ans. For example. the completed questionnaires can be collected from them. The potential respondent completes it. Attaching questionnaire to a product: A firm test marketing a product may attach a questionnaire to a product and request the buyer to complete it and mail it back to the firm. during and after the campaign. and 4) News-stand inserts. For example. After a day or two. Often referred to as the selfadministered questionnaire method. a cross sectional study of employees may show an association between their attitude to MB 0034 Page 18 . Alternatively. 2) Attaching the questionnaire to a product. It is also possible to find out how the constituency of the various economic and social strata of society changes through time and so on.

Persons with similar characteristics may replace the dropouts. Cheating by panel members or investigators may be a problem in some cases. Many persons may be unwilling to participate in a panel study. The formula for m is shown below: m= ΣX N Where ΣX is the sum of all the numbers in the numbers in the sample and N is the number of numbers in the sample.  the quality of reporting may tend to decline.4516 as shown below. there may be frequent dropouts. the mean of the numbers 1+2+3+6+8= 20 5 =4 regardless of whether the numbers constitute the entire population or just a sample from the population. However. One possible safeguard to panel conditioning is to give members of a panel only a limited panel life and then to replace them with persons taken randomly from a reserve list. and the costs involved in replacing dropouts. As an example.. In the course of the study. Q 2.: Measures of Central tendency: Arithmetic Mean The arithmetic mean is the most common measure of central tendency. after a panel has been in operation for some time. the members of a panel study of political opinions may try to appear consistent in the views they express on consecutive occasions. A panel study can provide data for finding an answer to this question. but it does not indicate as to which comes first favorable attitude or promotion.  A real danger with the panel method is “panel conditioning” i. all add to the expenditure. due to decreasing interest. m= ΣX N = 634 31 MB 0034 Page 19 .e. the payment of premiums. It simply the sum of the numbers divided by the number of numbers. Number of touchdown passes. For example.their jobs and their positions in the organization. periodic training of investigators and supervisors.  It facilities depth interviewing. In such cases. The symbol m is used for the mean of a population. The symbol M is used for the mean of a sample. shows the number of touchdown (TD) passes thrown by each of the 31 teams in the National Football League in the 2000 season. the risk that repeated interviews may sensitize the panel members and they become untypical. as a result of being on the panel. what is the difference between measures of central tendency and measures of dispersion? What is the most important measure of central tendency and dispersion? Ans. The table. The major limitations or problems of Questionnaire method are:  this method is very expensive. because panel members become well acquainted with the field workers and will be willing to allow probing interviews. The mean number of touchdown passes thrown is 20. The selection of panel members. the panel becomes untypical of the population it was selected to represent. In processing data. there is no guarantee that the emerging panel would be representative.  it is often difficult to set up a representative panel and to keep it representative.

Finally for Dataset 3. Student Dataset 1 Dataset 2 Dataset 3 You 3 3 3 John's 3 4 2 Maria's 3 4 2 Shareecia's 3 4 2 Luther's 3 5 1 Table 2: Three possible datasets for the 5-point make-up quiz For Dataset 1. there are 31 scores. When there is an even number of numbers. Median The median is also a frequently used measure of central tendency. the mode is 18 since more teams (4) had 18 touchdown passes than any other number of touchdown passes.4516 37 33 33 32 29 28 28 23 22 22 22 21 21 21 20 20 19 19 18 18 18 18 16 15 14 14 14 12 12 9 6 Table 1: Number of touchdown passes Although the arithmetic mean is not the only "mean" (there is also a geometric mean). Therefore. 7. the frequency of each value is one since no two scores will be exactly the same (see discussion of continuous variables). Number of touchdown passes.5. your score is above the median and therefore in the upper half of the distribution. 4. For this dataset. Therefore the mode of continuous data is normally computed from a grouped frequency distribution. The Grouped frequency distribution table shows a grouped frequency distribution for the target response time data. it is by far the most commonly used. 4. or some other mean. the median of the numbers 2. 12 is 4+7 2 =5. Let's return to the made up example of the quiz on which you made a three discussed previously in the module Introduction to Central Tendency and shown in Table 2. the median of 2. the median is 4. the median is 2. Range Frequency 500-600 3 600-700 6 700-800 5 800-900 5 900-1000 0 1000-1100 1 Table 3: Grouped frequency distribution MB 0034 Page 20 . if the term "mean" is used without specifying whether it is the arithmetic mean. The median is the midpoint of a distribution: the same number of scores is above the median as below it. it is assumed to refer to the arithmetic mean. the median is simply the middle number. For the data in the table. For example. The 16th highest score (which equals 20) is the median because there are 15 scores below the 16th score and 15 scores above the 16th score. Number of touchdown passes. Thus. the median is the mean of the two middle numbers. For Dataset 2. Since the interval with the highest frequency is 600-700. Mode The mode is the most frequently occurring value. With continuous data such as response time measured to many decimals. the median is three. For the data in the table. the geometric mean. your score is below the median. the mode is the middle of that interval (650). This means you are in the lower half of the class. and 7 is 4.=20. Computation of the Median: When there is an odd number of numbers. The median can also be thought of as the 50th percentile. Therefore. the same as your score.

Sources of statistical dispersion In the physical sciences. For categorical variables. MB 0034 Page 21 . In other words. it is less common to measure dispersion by a single number. One may assume that the quantity being measured is unchanging and stable. reproducible. and increases as the data becomes more diverse. So if a random variable X has a dispersion of SX then a linear transformation Y = aX + b for real a and b should have dispersion SY = |a|SX. In other words.e. they have no units even if the variable itself has units. It cannot be less than zero. such variability may result only from random measurement errors: instrument measurements are often not perfectly precise.. Other measures of dispersion are dimensionless (scale-free). if the measurements have units. Most measures of dispersion have the same scale as the quantity being measured. i. Variance-to-mean ratio — mostly used for count data when the term coefficient of dispersion is used and when this ratio is dimensionless. among them the Allan variance and the Hadamard variance. as count data are themselves dimensionless: otherwise this is not scale-free. One measure that does so is the discrete entropy. See qualitative variation. and that the variation between measurements is due to observational error. such as metres or seconds. equal to twice the Gini coefficient There are other measures of dispersion: • • Variance (the square of the standard deviation) — location-invariant but not linear in scale. Such measures of dispersion include: • • • • • • • Standard deviation Interquartile range Range Mean difference Median absolute deviation Average absolute deviation (or simply called average deviation) Distance standard deviation These are frequently used (together with scale factors) as estimators of scale parameters. the measure of dispersion has the same units. as well as linear in scale.Measures of Dispersion: A measure of statistical dispersion is a real number that is zero if all the data are identical. All the above measures of statistical dispersion have the useful property that they are locationinvariant. in which capacity they are called estimates of scale. Some measures of dispersion have specialized purposes. These include: • • • Coefficient of variation Quartile coefficient of dispersion Relative mean difference.

For example. Judd and Kenny. The presumed cause must occur prior to the presumed effect. For example. or. Changes in the presumed cause must be related to changes in the 2. or change the level of a treatment or program. if we introduce. whether a special work release program for prisoners causes lower recidivism rates.: Good research design:Much contemporary social research is devoted to examining whether a program. Each phenomenon must be examined to see if it warrants such a simplification. Cook and Campbell (1979) list a number of common plausible alternative explanations (or. we might wish to know whether a new educational program causes subsequent achievement score gains. an understanding of the logic of design construction in general will improve the comprehension of these standard approaches. whether a novel drug causes a reduction in symptoms. Temporal Precedence. While standard designs may sometimes fit real-life situations. even there. the meticulous scientist finds variation. it helps to clarify some of the basic principles of design logic. The reader is referred to standard research methods texts for more detailed discussions of threats to validity. While this is by no means the only strategy for constructing research designs. and so on.In the biological sciences. This tends to foster a "cookbook" approach to research design . Q 3. Cook and Campbell (1979) argue that three conditions must be met before we can infer that such a cause-effect relation exists: 1.The simple model of a stable quantity is preferred when it is tenable. which could be responsible for changes in the outcome measures. This paper takes a structural approach to research design. changes in record keeping or measurement systems which occur at the same time as the program might be falsely attributed to the program. But such explanations may be ruled out or minimized in a number of MB 0034 Page 22 . 1981) typically present an array of research designs and the alternative explanations. Thus. Minimizing Threats to Validity Good research designs minimize the plausible alternative explanations for the hypothesized cause-effect relationship. even if standard textbook designs are used. The presumed cause must be the only reasonable explanation for changes in the outcome measures. Furthermore. Any number of factors other than the treatment or program could cause changes in outcome measures. No Plausible Alternative Explanations. presumed effect. Standard social science methodology textbooks (Cook and Campbell 1979. This paper is primarily heuristic in purpose. this assumption is false: the variation observed might be intrinsic to the phenomenon: distinct members of a population differ greatly. In most social research the third condition is the most difficult to meet. 3. or manipulation causes some outcome or result. Ans. remove. What are the characteristics of a good research design? Explain how the research design for exploratory studies is different from the research design for descriptive and diagnostic studies. which these designs rule out or minimize. This is also seen in the arena of manufactured products. it will often be necessary to "tailor" a research design to minimize specific threats to validity. If there are other factors.an emphasis on the selection of an available design rather than on the construction of an appropriate research strategy. it may be that some historical event which occurs at the same time that the program or treatment is instituted was responsible for the change in the outcome measures. threats to internal validity). we cannot be confident that the presumed cause-effect relationship is correct. treatment. Covariation. Campbell and Stanley (1966) and later. we should observe some change in the outcome measures.

The dependent measure could be the pretest or other available pre-program measures. Consider. a change in the local economy. Nevertheless causal assertions are likely to be strengthened by demonstrating that treatment effects occur even after adjusting on a number of good covariates. There are a number of ways to rule out alternative explanations using statistical analysis. One factor in this study would be the original treatment group designations (i. for example. 4. comparison group). program vs. As a result. depending on the situation.e. ruling out a potential threat to validity by argument alone will be weaker than the other approaches listed below. The discussion.e. although the former will usually be more convincing than the latter. except in unusual cases. Where both effects occur. The plausibility of alternative explanations might also be minimized using covariance analysis. A main effect on the attrition factor would be indicative of a threat to external validity or generalizability. In some cases it will be possible to rule out a threat by measuring it and demonstrating that either it does not occur at all or occurs so minimally as to not be a strong alternative explanation for the cause-effect relationship. a study of the effects of an advertising campaign on subsequent sales of a particular product. The most straightforward way to rule out a potential threat to validity is to simply argue that the threat in question is not a reasonable one.e. By Argument. it might be possible to construct a measure of economic conditions and include that measure as a covariate in the statistical analysis. One interesting example is provided by Jurs and Glass (1971). the occurrence of other events which might lead to an increased desire to purchase the product) would be a plausible alternative explanation. be ruled out by argument only. For example. one might argue that an instrumentation threat is not likely because the same test is used for pre and post test measurements and did not involve observers who might improve. One might attempt to minimize such threats by measuring local economic indicators and the availability and sales of competing products. By Design. dropout vs. MB 0034 Page 23 . the most plausible threats in a study should not. one of which is by research design: 1. If there is no change in these measures coincident with the onset of the advertising campaign.. in a study of the effects of "workfare" programs on social welfare caseloads. waves of measurement."perfect" covariates do not exist in most social research and the use of imperfect covariates will not completely adjust for potential alternative explanations. or similar events could cause an increase in product sales. the removal of a competing product from the market. history (i. while an interaction between group and attrition factors would point to a possible threat to internal validity. In most cases. the major emphasis is on ruling out alternative explanations by adding treatment or control groups. For example.. By Measurement or Observation. By Analysis. This topic will be discussed in more detail below. In such a study. Similarly. Such an argument may be made either a priori or a posteriori. outlines five ways to minimize threats to validity. and the like. One must be careful when using covariance adjustments of this type -. it might be useful to observe everyday classroom behavior in order to verify that students were not receiving any additional math training to that provided in the study. 3. Here. it is reasonable to infer that there is a threat to both internal and external validity. They suggest that one could study the plausibility of an attrition or mortality threat by conducting a two-way analysis of variance. if one is studying the effects of special mathematics training on math achievement scores of children. For example. Here. while the other factor would be attrition (i. 2. which follows.. non-dropout group). these threats would be considerably minimized. one plausible alternative explanation might be the status of local economic conditions. or other such factors.ways other than by design.

A good research plan should. Measurements are typically depicted in design notation with the symbol "O". Time. each group is indicated on a separate line. In design notation we indicate this temporal element horizontally . In addition. The presumed cause may be a program or treatment under the explicit control of the researcher or the occurrence of some natural event or program not explicitly controlled. which was nonrandom assigned (i. Thus.e. "R" will represent a group. the "O" can be used to depict the entire set of measures. a nonequivalent group or cohort) and a "C" will indicate that the group was assigned using a cutoff score on a measurement.e. In design notation. In design notation we usually depict a presumed cause with the symbol "X". the manner in which groups are assigned to the conditions can be indicated by an appropriate symbol at the beginning of each line. While for some phenomena the elapsed time might be measured in microseconds and therefore might be unnoticeable to a casual observer. one which does not receive the program under study) no "X" is used. 2.whatever symbol is used to indicate the presumed cause would be placed to the left of the symbol indicating measurement of the effect. implies that some time has elapsed between the occurrence of the cause and the consequent effect. Here. When multiple programs or treatments are being studied using the same design. The choice of which strategy to use for any particular threat is complex and depends at least on the cost of the strategy and on the potential seriousness of the threat. we can keep the programs distinct by using subscripts such as "X1" or "X2". we normally assume that the cause and effect in social science arenas do not occur simultaneously. if the same set of measures is given at every point in time in this study. if the program is a desirable one. Furthermore. there will be one or more program and comparison groups. which was randomly assigned. Observation(s) or Measure(s). The final design element consists of the intact groups or the individuals who participate in various conditions. Similarly. Program(s) or Treatment(s).. then this "O" will be sufficient. If the same measurement or observation is taken at every point in time in a design. A causal relationship. where possible. In general. reducing a particular threat by design or preventive action will probably be stronger than by using one of the other three approaches. 4. 3. By Preventive Action. Groups or Individuals. For example. Design Construction Basic Design Elements. it is likely that the comparison group would feel jealous or demoralized. The inclusion of measurements designed to minimize threats to validity will obviously be related to the design structure and is likely to be a factor in the analysis. For a comparison group (i. The five categories listed above should not be considered mutually exclusive. as we read from left to right in design notation we are reading across time. MB 0034 Page 24 .5. Several actions can be taken to minimize the effects of these attitudes including offering the program to the comparison group upon completion of the study or using program and comparison groups which have little opportunity for contact and communication. by its very nature. "N" will depict a group. Complex designs might involve a lengthy sequence of observations and programs or treatments across time. When potential threats are anticipated some type of preventive action can often rule them out. auditing methods and quality control can be used to track potential experimental dropouts or to insure the standardization of measurement. make use of multiple methods for reducing threats.. Typically. However. if different measures are given at different times it is useful to subscript the "O" to indicate which measurement is being given at which point in time. Most research designs can be constructed from four basic elements: 1.

Include a short (less than 20-word) customer quote in larger text. writing case studies without careful planning usually results in sub optimal results? Savvy case study writers increase their chances of success by following these ten proven techniques for writing an effective case study: Involve the customer throughout the process. How is the Case Study method useful in Business Research? Give two specific examples of how the case study method can be applied to business research.: While case study writing may seem easy at first glance. and reads consistently. the template helps build the brand. • MB 0034 Page 25 . A template serves as a roadmap for the case study process. Ans. Involving the customer throughout the case study development process helps ensure customer cooperation and approval. What’s more.Q 4. learning how to write a case study takes time. formalize those elements. Start with a bang. developing an effective case study (also called a success story) is an art. Before beginning work. Rather than asking the customer to draft their quotes. Like other marketing communication skills. and results in an improved case study. and ensures that the document looks. Then. define 3-5 specific elements to include in every case study. Visually. Case Study Writing Ideas • Establish a document template. writing them for their review usually results in more compelling material. it simplifies the actual writing. solicit input during the development. Use action verbs and emphasize benefits in the case study title and subtitle. • Write all customer quotes for their review. feels. and stick to them. procedurally. and secure approval after drafting the document. Obtain customer permission before writing the document.

use the opposite sequence. The MB 0034 Page 26 . First. Even with the best plan. the latter can be quite compelling to readers as well. • Reward the customer. offering a specific example demonstrates. • Use photos. in a concrete way. and concluding more generally allows the reader to understand how the solution can also address their problem. The prerequisites of observation consist of: • Observations must be done under conditions. After receiving final customer approval and finalizing the case study. “Using Solution X saved Customer Y over $ZZZ. describe the solution to this problem or resolution of this issue. describe how the solution solved this specific problem. If benefits cannot be quantified. The goal should be to tease the reader into wanting to read more. ZZZ after just 6 months of implementation.: Observation means viewing or seeing. technical savvy.summarize the key points of the case study in 2-3 succinct bullet points. then indicate how it can also help resolve this issue more broadly within the industry. Q 5. “Thanks to Solution X. The key is to present imaginative ideas to the customer for ways to quantify the benefits. describe how the customer benefited from the particular solution (more on this below). and remain flexible during this discussion. a case study is doomed to failure if the writer lacks the exceptional writing skills. Writing a case study is not easy.” Quantifying benefits can be challenging. solution. the time-tested. • Quantify benefits when possible. attempt to develop a range of qualitative benefits. Photos further personalize the story and help form a connection to readers. describe the specific problem or issue that the customer faced. next. finally. Ans. how the solution resolves a commonly faced issue. The shots need not be professionally done. What are the differences between observation and interviewing as methods of data collection? Give two specific examples of situations where either observation or interviewing would be more appropriate. as well as printed copies. most effective organization for a case study follows the problem-solutionbenefits flow. consider outsourcing the task to professionals who specialize in case study writing.” or. Another idea is to frame a copy of the completed case study and present it to the customer in appreciation for their efforts and cooperation. In the solution section. but not impossible. For example. begin with a general discussion of the issue that faces the relevant industry. Observation is classical method of scientific study. In the problem section. describe the business and/or technical problem or issue. employees at Customer Y have realized a ZZ% increase in productivity as measured by standard performance indicators. If a qualified internal writer is unavailable. in fact. This natural storytelling sequence resonates with readers. • Organize according to problem. Observation may be defined as a systematic viewing of a specific phenomenon on its proper setting for the specific purpose of gathering data for a particular study. In many cases. The observer must be in vantage point to see clearly the objects to be observed. “homegrown” digital photos sometimes lead to surprisingly good results and often appear more genuine. First. Regardless of length. No single element in a case study is more compelling than the ability to tie quantitative benefits to the solution. and benefits. to the customer. a talented writer can mean the difference between an ineffective case study and one that provides the greatest benefit. and marketing experience that these documents require. Then. provide a pdf. which will permit accurate results. • Use the general-to-specific-to-general approach. Beginning more generally draws the reader into the story. ideally using the solution. Ask the customer if they can provide shots of personnel.

The mechanical devices used must be in good working conditions and operated by skilled persons. For example only observation can be providing an insight into all the aspects of the process of negotiation between union and management representatives. It is easier to conduct disguised observation studies than disguised questioning. A certain number of cases can be observered again by another observer/another set of mechanical devices as the case may be. Observations make it possible to capture the whole event as it occurs.g. If it is feasible two separate observers and set of instruments may be used in all or some of the original observations. studies of children. Their purpose is to give the interviewer(s) a chance to assess your suitability for the role and for you to demonstrate your abilities and personality. it is also a good opportunity for you to ask questions and to make sure the organisation and position are right for you. Interview format Interviews take many different forms. • Observation must cover a sufficient number of representative samples of the cases. As this is a two-way process. It is a good idea to ask the organisation in advance what format the interview will take.distance and the light must be satisfactory. o o o o o o Interviews are a crucial part of the recruitment process for all Organisations. Observations improve the opportunities for analyzing the contextual back ground of behavior. The validity of what men of position and authority say can be verified by observing what they actually do. o Data collected by observation may describe the observed phenomena as they occur in their natural settings. The researcher needs to ask people about their behavior and interactions he can simply watch what they do and say. Observations in more suitable for studying subjects who are unable to articulate meaningfully e. There is no such artificiality in observational studies especially when the observed persons are not aware of their being observed. Furthermore verbal resorts can be validated and compared with behavior through observation. • The accuracy and completeness of recorded results must be checked. The results could then be compared to determine their accuracy and completeness. birds etc. • Recording should be accurate and complete. Observation is less demanding of the subjects and has less biasing effect on their conduct than questioning. Mechanical devices may be used for recording data in order to secure more accurate data and also of making continuous observations over longer periods. MB 0034 Page 27 . Advantages of observation o The main virtue of observation is its directness it makes it possible to study behavior as it occurs. tribal animals. Other methods introduce elements or artificiality into the researched situation for instance in interview the respondent may not behave in a natural way.

Screeners will hone in on gaps in your employment history or pieces of information that look inconsistent. which will usually have been detailed in the job specification or advert. (This is why you need a digital resume that is screening-friendly. examines whether or not you have evidence of possessing these. The Cooperative Group Technical interviews . but also to admit to what you do not know and stress that you are keen to learn. however informal the discussion may seem. Computer programs are among the tools used to weed out unqualified candidates. For this reason.These ranges from straightforward scenario questions (e.) Sometimes human professionals are the gatekeepers. Be aware that you are still being assessed. and to have an in-depth discussion about the pieces you have chosen to include. Save your winning personality for the person making hiring decisions! MB 0034 Page 28 . Senior/case study interviews . Recruitment Manager. Questions are likely to center on your academic history to date. Get into the straightforward groove.If you have applied for a job or course that requires technical knowledge. in an interview. Some tips for maintaining confidence during screening interviews: • • Highlight your accomplishments and qualifications.interviewers are interested in your thought process and logic.These are structured to reflect the competencies or qualities that an employer is seeking for a particular job. Screening interviewers often have honed skills to determine whether there is anything that might disqualify you for the position.Some interviews may be very formal. Academic interviews . Questions may focus on your final year project or on real or hypothetical technical problems. You will be evaluated on your analysis of the problem. Portfolio based interviews . Formal/informal interviews . You should be prepared to prove yourself. Answer questions directly and succinctly. and asks all the candidates the same questions. Do not worry if you do not know the exact answer . you may be asked to bring a portfolio of your work to the interview.’ The organisation determines the selection criteria based on the roles they are recruiting for and then.The interviewer has a set list of questions. only whether you are not a match. screeners tend to dig for dirt. Personality is not as important to the screener as verifying your qualifications. The interviewer is looking for evidence of your skills and may ask such things as: ‘Give an example of a time you worked as part of a team to achieve a common goal.If the role is within the arts.g. See our resume center for help. media or communications industries. ‘What would you do in a situation where…?’) to the detailed analysis of a hypothetical business problem. it is likely that you will be asked technical questions or has a separate technical interview.These are used for further study or research positions. Rememberthey does not need to know whether you are the best fit for the position. while others will feel more like an informal chat about you and your interests. They also will want to know from the outset whether you will be too expensive for the company. Structured interviews . • • • • • • Specific types of interview The Screening Interview Companies use screening tools to ensure that candidates meet minimum qualification requirements. how you pursue a particular line of thinking and whether you can develop and present an appropriate framework for organising your thoughts.• Competency/criteria based interviews . how you identify the key issues.

open-ended question before falling into silence. Either way. the interviewer has a clear agenda that he or she follows unflinchingly. The Informational Interview On the opposite end of the stress spectrum from screening interviews is the informational interview. The interviewer might ask you another broad. This takes off some of the performance pressure. You might feel like you are being steam-rolled. Directive interviewers rely upon their own questions and methods to tease from you what they wish to know. or esteem the mutual friend that connected you to them. when interviewers ask each candidate the same series of questions. That way. although you should keep an eye open for these if the interviewer would be your supervisor. feel flattered by your interest. especially if they like to share their knowledge. If the interviewer does not ask you for information that you think is important to proving your superiority as a candidate. Write a thank you note to the interviewer. Sometimes companies use this rigid format to ensure parity between interviews. whether the interviewer catches you sleeping or vacuuming the floor. Give a range. "I would be willing to consider your best offer. politely interject it. A meeting that you initiate. It might begin with a statement like "tell me about yourself. they can more readily compare the results. During an informational interview. following his or her lead. MB 0034 Page 29 . but be intentional nonetheless: • • • • Come prepared with thoughtful questions about the field and the company. The Directive Style In this style of interview." If the interview is conducted by phone. or you might find the conversation develops naturally. and try to avoid giving specifics by replying. the informational interview is underutilized by job-seekers who might otherwise consider themselves savvy to the merits of networking. are often open to informational interviews. usually used by inexperienced interviewers. remember: • • Flex with the interviewer.• • Be tactful about addressing income requirements. contact information and resume. Job seekers ostensibly secure informational meetings in order to seek the advice of someone in their current or desired field as well as to gain further references to people who can lend insight. you will be able to switch gears quickly. This interview style allows you tactfully to guide the discussion in a way that best serves you. Do not relinquish complete control of the interview. Their style does not necessarily mean that they have dominance issues. relies on you to lead the discussion. Employers that like to stay apprised of available talent even when they do not have current job openings. Give the interviewer your card." which you can use to your advantage. The Meandering Style This interview type. the jobseeker and employer exchange information and get to know one another better without reference to a specific job opening. it is helpful to have note cards with your vital information sitting next to the phone. Gain references to other people and make sure that the interviewer would be comfortable if you contact other people and use his or her name.

Case Study: You are engaged to carry out a market survey on behalf of a leading Newspaper that is keen to increase its circulation in Bangalore City.it is not simply a catalogue of what has been written. running with your own agenda and dominating the conversation means that you run the risk of missing important information about the company and its needs. In the early stages of your research you cannot be expected to have a fully developed appreciation of the implications of all findings. 2. Although the open format allows you significantly to shape the interview. take each group in turn and really think about what you want to achieve in presenting them this way. Ans. in order to ascertain reader habits and interests. Q 6. you will eventually reach a final decision as to your own topic and research design. Once you have established which authors and ideas are linked. but that you have the knowledge and skills to interpret the authors' meanings and intentions in relation to each other. What type of research report would be most appropriate? Develop an outline of the research report with the main sections. Even if you feel like you can take the driver's seat and go in any direction you wish. If he or she becomes more directive during the interview.: There are four major interlinking processes in the presentation of a literature review: 1. MB 0034 Page 30 . Rest assured that developing a sense of critical judgment in the literature surrounding a topic is a gradual process of gaining familiarity with the concepts. qualities and experiences.The following strategies. Ask well-placed questions. Remain alert to the interviewer. terminology and conventions in the field. Critiquing rather than merely listing each item a good literature review is led by your own critical thought processes . remain respectful of the interviewer's role. language. particularly if there are conflicting views or incompatible findings in a particular area. Do not rely on the interviewer to spark your memory-jot down some notes that you can reference throughout the interview. As you get used to reading at this level of intensity within your field you will find it easier and more purposeful to ask questions as you read: o What is this all about? o Who is saying it and what authorities do they have? o Why is it significant? o What is its context? o How was it reached? o How valid is it? o How reliable is the evidence? o What has been gained? o What do other authors say? o How does it contribute? o So what? Structuring the fragments into a coherent body through your reading and discussions with your supervisor during the searching and organising phases of the cycle. adjust. This is your opportunity for showing that you did not take all your reading at face value. are particularly important when interviewers use a non-directive approach: • • • Come to the interview prepared with highlights and anecdotes of your skills. which are helpful for any interview.

Knowing what you want to convey will help you decide the most appropriate structure. and how the debate informs your understanding of the topic.As you begin to group together the items you read. with your own intentions and conceptual framework in mind. This is a good time to finalise your concept map. Later. you should be able to relate your findings in one-to-one correspondence with many of the concepts or questions that were firmed up in the conclusion of your literature review. showing how each relates to the others. When you report on your own findings. The section then expands on these ideas and authors.' When using published data. Controlling the 'voice' of your citations in the text (by selective use of direct quoting. The final conclusion of the literature review ties together the main points from each of your sections and this is then used to build the framework for your own study. Now you can plan the structure of your written literature review. paraphrasing and summarizing) You can treat published literature like any other data. A review can take many forms. usually as a series of headed sections and subsections. a literature review needs: o o o An introduction A body A conclusion The introduction sets the scene and lays out the various elements that are to be explored. The body takes each element in turn. grouping linked items. for example: o o o An historical survey of theory and research in your field A synthesis of several paradigms A process of narrowing down to your own topic It is likely that your literature review will contain elements of all of these. the direction of your literature review will emerge with greater clarity. The first paragraph or two of each section mentions the major authors in association with their main ideas and areas of debate. for example: o 'Table 2 shows that sixteen of the twenty subjects responded positively. As with all academic writing. you would say: MB 0034 Page 31 . 3. but the difference is that it is not data you generated yourself. A short conclusion at the end of each section presents a synthesis of these linked ideas. when you come to write the discussion chapter of your thesis. you are likely to present the results with reference to their source. ideas and authors into firm categories as they relate more obviously to your own study.

and might be penalized. MB 0034 Page 32 . and it is your own voice that is predominant: o o Referring to the possible effects of cloudy weather. If you don't do this you would be in severe breach of academic convention. and it must be an identical copy of the original in every respect. which determines how strong the wall will be. Paraphrasing allows you to organize the ideas expressed by the authors without being rigidly constrained by the grammar. page 27). rain may well be indicated by the presence of cloud in the sky. you would naturally substitute the name. using an approved referencing system. Overuse or simple 'listing' of quotes can substantially weaken your own argument by silencing your critical view or voice. single quotation marks are used to enclose it. it appears that the majority of subjects responded positively.' 'From the results shown in table 2. with no loss of the author's intended meaning: o As Smith (1988) pointed out in the late eighties. Your field of study has its own referencing conventions you should investigate before writing up your results. In each case it would be your voice introducing a fact or statement that had been generated somewhere else. Paraphrasing is repeating an idea in your own words.o o 'Positive responses were recorded for 80 per cent of the subjects (see table 2). Smith (1988) claims that some degree of precipitation could be expected as the result of clouds in the sky: he has clearly discounted the findings of Jones (1986). Direct quoting repeats exact wording and thus directly represents the author: o 'Rain is likely when the sky becomes overcast' (Smith 1988. tense and vocabulary of the original. Had you found the same results on page 17 of a text by Smith published in 1988. The original writing is 'described' as if from the outside. You could see this process as building a wall: you select and place the 'bricks' and your 'voice' provides the ‘mortar’. Smith (1988) predicted the likelihood of rain. this is significant in the assessment of the merit and rigor of your work. You retain a degree of flexibility as to whose voice comes through most strongly. Summarizing means to shorten or crystallize a detailed piece of writing by restating the main points in your own words and in the order in which you found them. the author's name and publication details must be associated with the words in the text.' In these examples your source of information is table 2. There are three ways to combine an idea and its source with your own voice: o o o Direct quote Paraphrase Summary In each method. If the quotation is run in with your text. date and page number for 'table 2'. In turn.

. Using appropriate language Your writing style represents you as a researcher.. you should find that your writing becomes more lucid and fluent because you know what you want to say and how to say it. and on the context of the writing. Use past perfect tense for: o Events which occurred before a specified past time: MB 0034 Page 33 .. which can then be compared on equal terms with others:  Smith (1988) suggests that. especially theories. Use present perfect tense for: o Recent events or actions that are still linked in an unresolved way to the present:  Several studies have attempted to. You need to conform to discipline-specific requirements. there may still be some points of grammar and vocabulary you would like to improve. Which tense should I use? Use present tense: o o o o For generalizations and claims:  The sky is blue. Once you have established a good structure with appropriate headings for your literature review.4.. To convey ideas.practical and helpful The following guidance on tenses and other language tips may be useful. In referring to components of your own document:  Table 2 shows... If you have doubts about your confidence to use the English language well. The good use of language depends on the quality of the thinking behind the writing. However. you can help yourself in several ways: o o o Ask for feedback on your writing from friends. colleagues and academics Look for specific language information in reference materials Access programs or self-paced learning resources which may be available on your campus Grammar tips . and once you are confident in controlling the voice in your citations. Use simple past tense for: o Completed events or actions:  Smith (1988) discovered that. and reflects how you are dealing with the subtleties and complexities inherent in the literature. For authors' statements of a theoretical nature... which exist for the reader at the time of reading:  I think therefore I am.

critical/interpretive/ empiricist). could. The total process The story of a research study Introduction I looked at the situation and found that I had a question to ask about it. Avoid densely packed strings of words. Methodology I decided on the number and description of my subjects. and do not rely on your reader to read your mind! Keep sentences short and simple when you wish to emphasise a point. I established exactly where my investigation would fit into the big picture. verb and object in clear view. 'but'. I began with the broad decision about which research paradigm I would work within (that is. so I made sure that the instrument and my proposed method(s) of analysis were compatible right from the start. this would imply that. Use it to separate the elements of complex sentences in order to keep subject. Use modals (may. Findings/results What had I found? What did the tables/graphs/categories etc.. would.what was already known and said and what had previously been found. using certain known research methods (and perhaps some that are not so common). qualitative/quantitative. and with my research question clearly in mind. particularly nouns. Use compound (joined simple) sentences to write about two or more ideas which may be linked with 'and'. might.. Don't try to use an intellectual tone for the sake of it. I wanted to investigate something in particular. designed my own investigation process.. and began to realise at this stage how my study would be different from anything done previously. and nouns carry information more densely than verbs. Review of literature So I read everything I could find on the topic . should) to: o Convey degrees of doubt  This may indicate that . I knew I would have to analyse the raw data. Select active or passive verbs according to whether you are highlighting the 'doer' or the 'done to' of the action. categories. As part of the analysis. Then I carried out the research study and recorded all the data in a methodical way according to my intended methods of analysis. It was then that I began to realise what I had found. 'because'. have to say that could be pinned MB 0034 Page 34 . Verbs are more dynamic than nouns.. 'whereas' etc.. I reduced the data (by means of my preferred form of classification) to manageable thematic representation (tables. graphs. Keep punctuation to a minimum. etc). it had been thought that. Use complex sentences when you are dealing with embedded ideas or those that show the interaction of two or more complex elements. Then I devised my research instrument to get the best out of what I was investigating.. Other language tips o o o o o o o o Convey your meaning in the simplest possible way. Prior to these findings.

Establishing good practice 1. MB 0034 Page 35 . check. Research design and implementation 3. Conclusion We'll take a long hard look at this study from a broad perspective.just the facts. state of mind. Train yourself to select what you do need and reject what you don't need. 3. 8. Keep a research journal to reflect on your processes. so where do we all go from here? Three stages of research 1. succinct sentences. applying tests of significance where appropriate to ensure both reliability and validity. strength and thereby academic 'clout' if I took no shortcuts and remained both rigorous and scholarly. But I won't become over-apologetic about the things left undone. and whatever implications have arisen in my mind as a result of doing this thing at all. How does it rate? How did I end up answering the question I first thought of? The conclusion needs to be a few clear.. which may relate to your topic. decisions. even so. What did I find in the results that answered my original research question? Why was I so sure I had some answers? What about the unexplained or unexpected findings? Had I interpreted the results correctly? Could there have been any other factors involved? Were my findings supported or contested by the results of similar studies? Where did that leave mine in terms of contribution to my field? Can I actually generalise from my findings in a breakthrough of some kind. I was careful not to let my own interpretations intrude or voice my excitement just yet. Reading 2. Writing up the research report or thesis Use an active. I'll defend to the hilt. I'll wrap up with whatever generalizations I can make. redraft. How I wonder what you are .. the more questions arise. changes of mind. but in writing my report. Read widely to collect information. which. how I speculate. 2. 5. Keep your research question always in mind. I have my memories. after all? There were some obvious limitations to my study. Read widely to establish a context for your research. The more you find out.. For each display of results. note-taking and referencing records. or the abandoned analyses. I dealt correctly with all inferential statistical procedures. That way. 6. Be systematic with your reading. I wanted to state the facts . Keep a systematic log of technical records of your experimental and other research data. cyclical writing process: draft. 7. Discussion Now I was free to let the world know the significance of my findings. They would carry a great deal more credibility. OK. reflect. and noting any discrepancies or unexpected occurrences at the time you notice them. revise. 4. reactions to experimental outcomes etc. particularly to your hypothesis or research question. Discuss your ideas with your supervisor and interested others. or do I simply see myself as reinforcing existing knowledge? And so what. I also spelled out what I had found truly significant to make sure my readers did not miss it. I'll know that I know what I'm talking about. the fascinating byways sadly left behind. remembering to date each entry. I knew that I wanted my results to be as watertight and squeaky clean as possible.. I wrote a corresponding summary of important observations relating only elements within my own set of results and comparing only like with like.down? It was easy enough for me to see the salient points at a glance from these records.

Design your research approaches in detail in the early stages so that you have frameworks to fit findings into straightaway. Be thoughtful and think ahead about the way you will consider and store new information as it comes to light.9. MB 0034 Page 36 . Keep going back to the whole picture. Know how you will analyse data so that your formats correspond from the start. 10. 11.