Professional Documents
Culture Documents
Document
Document
as parameter(s), a ply the study of a small Portion of| tally be a certain amount of) P‘ pai i in accuracy may be termed as| a z ‘er words, saj i s count of samp mpling errors are those errors Li Variations (in case of random sa arate Benerally happen to be random 7 mpling) i ‘ Population values Pling) in the sample estimates around the trueErrors in Survey Q.1. What are the different types of errors in surveys? Ans. In survey research, it is common to hav: pare from different source. Broadly, we can classif Types of error in survey research : i A. Random Sampling Error in : ‘ ised on sample. But isnot posible tha the sample wil ull pees of the population. As a result, error will occur such aes : is kn sie sampling error of random sampli: es Sena e e rt ampling error. In other words, using sample rather than population results in errors which is known as sampling error. This error is obvious & can’t be eliminated unit a large sample or the whole population is bein, studied. Different statistical techniques are used to determine the significance of the errors. B. Systematic error/Non-sampling error : The other major source of survey error, systematic error, results from some imperfect aspect of the research design or from a mistake in the execution of the research design or from a mistake in the execution of the research. The many source of error that in some way systematically influence answers can be divided into two general categories: e errors. Survey errors may arise these errors into two types. 1. Respondent error 2. Administrative error. 1. Respondent error : Surveys ask people for answers. If people co-operate and give truthful answers, a survey will likely accomplish its goal. If these conditions are not met, the two major categories of respondent error, may cause sample bias. * Non-response error in survey research © Response Bias Non response error in survey reezarch : Few surveys have 100 percent response rates. In fact, surveys with relatively low response rates many still accurately reflect the population of interest. The applied math variations between a survey that has solely people who responded and a survey that additionally enclosed people who didn’t respond area unit mentioned as non response error. Response Bias : A response bias occurs when respondents tend to answer questions with a certain slant people many consciously or unconsciously misrepresent that truth. When researchers identify response bias, they should include a corrective measure response bias may occur. in the following ways: Deliberate Falsification: Occasionally people deliberately give false answer. Itis difficult to assess why people knowingly misrepresent answers. A response (33)M AMAR : Research Methodology bias may occur when people misrepresent answer to appear intelligent, conce, personal information, avoid embarrassment, and so on. For example, Tespondeny may be able to remember the total amount of money spent on Brocery shoppin but they any forget the exact prices of individual items that they purchased Unconscious Misrepresentation ; Even when a respondent is conse trying to be truthful and cooperative, response bias can arise from the Weston, format the question content, or some other stimulus, For example, bias can be introduced by the situation in which the survey is administered, Types of Response Bias: Response bias falls into acquiescence bias, extremity bias interviewer bias, ‘These categori ously four specific categorie, and social desirability biag s overlap and are not mutually exclusive. * Acquiescence Bias: Some respondents are very agreeable. They seem tp agree to practically every statement they are asked about. A tendency to agree (or disagree) with all or most questions is known is acquiescence bias. This bias is particularly prominent in new product research, Extremity Bias:Some people tend to use extremes once responding to queries. for instance, they will opt for solely “1” or “10 on a ten-point scale. Others consistently refuse to use extreme Positions and tend to respond more neutrally “i never givea 10 because nothing is really perfect, Response styles vary from Person to person, and extreme responses may cause an extremity bias in the data. Interviewer Bias : Response bias might arise from the interaction between querier and respondent. If the interviewer's presence influences respondents to give untrue or modified answers, the survey will be marked by interviewer bias. Many homemakers and retired people welcome an interviewer's visit as a break in routine activities. Other respondents may give answers they believe will please the interviewer rather than the truthful response. Social Desirability Bias : Social desirability bias might occur either consciously or unconsciously as a result of the respondent desires to make @ good impression or save face within the presence of AN enquirer, Incomes may be inflated, education overstated, perceived respectable answers given to gain prestige. * Administrative error: The results of improper administration or execution of the analysis task is termed Associate in Nursing body error. Administrative errors are caused by carelessness, confusion, neglect, omission, or some other blunder. Four types of administrative errors are data-processing selection error, interviewer error, and interviewer cheating. Data processing error : Processing data by computer, like any arithmetic °F procedural proces is subject to error because data must be edited, coded, and entered into the computer by People. The accuracy of dat Processed by computer depends op correct data entry and programming. * Sample selection error : Many kinds of error involve failure to select @ representative sample. Sample choice error is systematic error that endsUnit-4 : Errors in Survey 35 up in Associate in Nursing untypical sample owing to a slip-up in either the sample style or the execution of the sampling procedure. Interviewer error : Interviewers’ abilities very considerably. Interviewer error is introduced when interviewers record answers but check the wrong response or are unable to write fast enough to record answers verbatim. Interviewer or cheating : Interviewer cheating occurs when an interviewer falsifies entire questionnaires or fills in answers to questions that have been intentionally skipped. If interviewers are suspected of faking questionnaires, they should be told total that a small percentage of respondents will be called back to confirm whether the initial interview was actually conducted. This practice should discourage interviewers from cheating. Q. 2. How we can, solve the problems of non-response in survey ? Ans .Here are six ways you can increase survey response by not annoying your respondents : Personalise Interactions : Don’t ask questions that you already know. By using information you already have (j.e., demographic information) you can improve survey experience and email communication. Target Intelligently : No one wants to be screened out in the middle of your survey. If someone doesn’t meet your criteria, screen them out before they begin. This way, you only send the right surveys to the right respondents. Automate Rewards : Send rewards as soon as your respondents complete the survey, not a month later. Automate this process so it's easy for your respondents and for you. Control Contact Frequency : This can get jumbled and chaotic in a hurry. Let Qualtrics Target Audience do it for you. Respect Global Opt-Outs : Continuing to send surveys when your Tespondents unsubscribe means you're spamming them with survey requests. Doing this not only results in less responses—it also harms your brand. Keep Your Promises :Avoid the temptation of asking too many questions in your surveys. If you tell a respondent that your survey takes 5 minutes but it teally takes 10, you lose trust and goodwill. Q. 3.What are the common Questionnaire making mistakes? Explain. Ans.Most experienced researchers and consultants can put together an effective Survey instrument, but even then, small issues can creep into the questionnaire that can compromise quality, introduce bias or lead to misleading results. While many of the common mistakes listed here may seem obvious, it is always good Practice to review a questionnaire with these potential issues in mind. Here are some of the common questionnaire mistakes market researchers should avoid: Mistake Leading the Respondent : This issue results when an adjective is Used that can cause bias. While often unintentional, itis sometimes seen in political Polling when trying to provoke a certain reaction to an issue. When it occurs in Bia= 36 AMAR : Research Methodology market research surveys, it tends to inflate ratings in aspects like custome; satisfaction or product research. Overlapping, Incomplete or Unclear Response Choices : Response option; should almost always be mutually exclusive and definitive. Any ambiguity wiq, confuse and/or frustrate respondents. Vague Questions : Having respondents guess what response the study jg looking for is a wasted opportunity. This most often occurs in open-ends when looking for something specific, but the respondent takes the question in a different direction. Also, be specific with timeframes. Ignoring Cultural Differences and Sensitivities : As mentioned in our post3 | Things to Consider When Asking Sensitive Questions respondents in different regions can be sensitive about certain topics related to income, sexual orientation, religion, personal care, and consumption/use of certain products and services, Combining Questions/Attributes : As mentioned previously, it is important that the respondent clearly understands the question they are answering or the attribute they are rating. Make sure each question focuses on one attribute/ behavior. Too many open-ended questions : Open ends can be revealing, but often they are used when response options have not been well-thought-out or as a substitute | for qualitative examination. Too many open-ends results in faster respondent | | fatigue, which means higher drop-out rates and/or less consideration when answering. Both issues compromise data quality. If real unstructured data is the goal, consider a different methodology such as in-person qualitative or an online community. Not Considering the Respondent Experience : As Jun Uematsu, Chief Operating Officer at dataSpring, mentions in the blog Understanding Questionnaire Design in Japan, market research participation rates are declining significantly, in part due to poor respondent experience: long surveys, confusing questions, multiple attribute matrix, and multiple open-ends try the patience of ‘even the most dedicated respondent. Q. 4. What are the Response Bias in reaserch & methodology? ‘Ans, Response Bias is a general term that describes the ways a respondent may be influenced when self-reporting their answers on a survey. Bias affects the accuracy and reliability of the results. There are several ways in which an individual's response may be inaccurate. The inaccuracy, or bias, may be deliberate ‘or subconscious on the part of the respondent; it is the result of a respondent being unduly influenced to respond a certain way, or a respondent's unwillingness to answer the questions honestly. Bias can be caused when items are unclear of poorly constructed but can also occur as a result of the response scale selected for participants to use when they provide their answers. Never underestimate the propensity of individuals to misunderstand what is being asked or otherwise provide information ee is tescrurete to some degree. ‘Gome common forms of Response Bias include : Soci its Conformity bias:-Itcan be hard for respondents to epealy ee deepen a IUnit-4 : Errors in Survey — when asked to self-report their behavior, beliefs and opinions; this is especially tue when the respondent believes they may be ridiculed or despised. In such cases, respondents will tend to provide a socially acceptable response (sometime subconsciously) over their true feelings. For example, a respondent may tend to agree with a statement more strongly than is factual when the item addresses something that is generally seen in society as desirable or expected. Prestige bias:-This bias is related to social desirability bias as it is based on an individual's personal desire to be seen in a positive light. However, with this bias it is personal, not based on a general instinct for conformity. For example, respondents may round up their income or report exaggerated amounts of time spent on worthy endeavors (noting, the reverse would be true for endeavors the individual feels may diminish how they are perceived). This may not involve outright lying, the individual may actually remember the facts inaccurately. Respondents often tend to view or recall their own situation in a more favorable light than is actually the case —subconsciously protecting their self-image or inflating their ego. It is often good practice to assume that, if a question has a potential prestige component, the responses are likely inflated to present the respondents in a more favorable light. Exactly how much they are inflated will depend on the question, context, and respondents. Acquiescence or Agreement bias : This bias is like conformity bias. However, unlike conformity bias, in this case the respondent will, in general and inadvertently, agree with statements. With this bias, participants tend to select a positive response option or disproportionately indicate a positive connotation. This bias will skew results towards the positive. Item and Option Order Effect bias : Order bias can be the result of both item order and response option order. The order in which survey items are presented can affect a respondent’s answers due to a priming effect. People tend to contextualize their responses. Because of this, survey questions that come just before a particular query may provide information that respondents will use as context in formulating their subsequent answers. If a different primer was presented, the responses may be significantly different. ‘Two common response biases associated with response option order are Primacy and Recency bias. Primacy bias is the tendency for respondents to pick one of the first options presented to them. This can happen when a respondent quickly reads through the survey and pick one of the first response options they agree with. Recency bias is the tendency to pick an answer option presented at the end of a list. For example, in a long list of options, the ones respondents read last are more memorable to the respondent as they select an answer. Mood bias and Emotional Mind Sets : One's mood or mind set will affect the way responses are provided. For example, if a participant is exceptionally happy or angry for some reason while taking a survey, their emotional state affects the general pattern of responses provided. Given time, the respondents current extreme emotions may subside which will modify the intensity of the responses provided. Emotional responses can be intense in either a positive or negative direction. You i,» a+ 38 AMAR: Research Methodology will also see this when the survey addresses an tha responce salle pots Responses may tend to be on the sarem ends of strong opinions; Kore because those who choose to complete the st 7 ted bw enc’ T, mood bias becomes a problem when opinions are exaggerated by one’s current emotional state. f Pere Central Tendency bias : This bias refers to the tendency of some individuals toavoid responding in extreme ways. For example, some people may never indicate they strongly agree or are extremely dissatisfied (i.e., nothing is perfect and nothing is completely without merit). This is the opposite of a mood bias in that reponses from those who have this bias will trend closer to the center of the response scale, | Demand Characteristic bias:- A demand characteristic is used to describe specific cues in research that may inadvertently influence a participant's response. | A demand characteristic can manifest in a number of different ways if the researcher is not careful when designing and proceeding with a study. In social science research, demand characteristics can create bias when the subject becomes aware of the purpose of the study. This may potentially bias or invalidate the ‘outcomes. When a respondent becomes aware of the reason or purpose of the | study they may intentionally provide answers they feel would influence the | results. For example, if a respondent figured out that the results of a survey will be used to set policy, the individual may attempt to answer in.a way that they feel | would be beneficial to them. Random Response bias : Random response bias can occur when a respondent honestly does not know the answer to the question but answers anyway. This can happen when you ask a respondent to answer a question for which they would not reasonably know the answer, Respondents resort to guessing or speculating rather reporting factual information. For example, asking someon to indicate the motive of another individual prompts a guessing bias. Another way this bias can manifest is when an individual has an opinion but hasn’t considered their true feeling carefully. Like a central tendency bias, these individuals also tend to choose options toward the middle of the response scale. At times, people with this bias will choose the exact middle point (on an odd numbered response scale) simply because they don't want to think about the issue or don’t really care. This bias can also manifest itself maliciously when an individual intentionally responds in a random fashion without actually reading the items. This can happen when there is an incentive involved and people simply want to complete the survey for the promised reward, Ifyou suspect the possibility that a random response bias might occur, trigger items can be added to identify suspect response patterns. For example, adding an item that is the opposite of another item or reverse scoring an item can be used to identify Potential problems. Note however, the practice of reverse scoring some items but not allofthe legitimate | items is not advised as this can cause an response bias which can affect the analysis and interpretation of the results . | | | |Processing of Survey Data Q.1.What are the important steps of data processing? Ans. It is no secret that the results obtained from surveys, play a very crucial role in shaping any organization’s long term objectives. However, survey data entry and processing can be very time consuming and tedious for businesses. Hence, choosing an outsourcing service provider for survey data entry services requirements can help organizations to better focus on their core activities. Survey data processing consists of four important steps. Survey Designing : Devise suitable surveys/questionnaires to help organizations modify their products/services in order to gain higher profits in future. It involves working closely with client to understand and analyze their business needs as well as the target audience. Survey designing includes establishing obiective, determining sample, deciding upon the survey mode and finally creating questionnaire. A thoughtfully designed survey questionnaire can provide better insights on the research topic and prove very useful in improving business. Data Entry and Data Capture : Survey forms data entry basically means capturing data from paper/ web based questionnaires or survey forms and storing it in electronic format. This process requires a combination of professional skills and latest cutting edge technology to collate relevant information from all types of surveys. These days, OCR and other scanning techniques are being used for survey form scanning, which has been incremental in reducing data entry errors to a great extent. The data so collected is‘then stored in suitable digital formats including MS Excel, SAS, SPSS, MSWord, MySQL, etc. Data Quality Assurance and Analysis : One of the fundamental goals of survey data processing is to make quality data available to organizations for the purpose of analysis. Survey form data is always prone to errors, omissions and other inconsistencies. This data inconsistency and incompleteness, if not edited and corrected on time, ‘can complicate the analysis and may even result in wrong analysis. Hence, to avoid this problem, survey data entry service providers must have an effective quality assurance framework in place. Quality of data can be assured by following a proven methodology, such as:Survey forms are first categorized based on certain defined criteria. Forms are scrutinized for their code structure, and those with open ended responses are standardized and recoded at this stage. Check all questionnaires after data entry to make sure that all the data fields have been accurately filled in.Use double keying process to avoid any discrepancies in data.Check data for inconsistencies and resolve issues relating to missing, duplicate, incomplete data, etc. Reporting and Data Tabulation : Survey data in its raw form is not likely to make much sense to organizations, unless it is presented in a way that is easy to understand. Extensive reporting and statistics is required to help businesses (39) @e. fiSilda hp) Oe 0 ca ‘esearch Methodology ok 40 AMAR: s can be of various t gly. Reports can | i YPes cordingly. as presentation quality reports, ports are a great way to hayy, analyze situations and take actions accordingly. depending upon theneeds of an Sa Survey re cross tabulations, frequency analyst a bird’s eye view of survey responses. ta and it’s coding? Q. 2. What do you understand by Sa als particularly when yoy Ans, Data cleaning is a crucial part of data analysis, part you must enter jt Fee a aecraaanlliative data ie yee cali During tala process, whether into a computer program such as SAS, S "ies it there will be errors, No matter it is done by hand or a computer scanner does it, ¢ inevitable. This could mst how carefully the data has been entered, errors are orrect sensing of blacker) incorrect coding, incorrect reading of written codes, ee raceas*of detecting anq marks, missing data, and so on. Data cleaning is the p' J correcting these coding errors. . There are two types of data cleaning that needs to be penonned to aaa sets, They are possible code cleaning and contingency cleaning, Both are crucial to the data analysis process because if ignored, you will almost always produce misleading research finding, = Possible-Code Cleaning : Any given variable will have a specified set of answer choices and codes to match each answer choice. For example, the variable gender will have three answer choices and codes for each: 1 for male,? for female, and 0 for no answer. If you have a respondent coded as 6 for this variable, it is clear that an error has been made since that is not a possible anewer eocle, Possible- code cleaning is the process of checking to see that only the codes assigned to the answer choices for each question (possible codes) appear in the date file Some computer programs and statistical software packages available for data entry check for these types of errors as the data is being entered. Here, the user defines the possible codes for each question before the data is entered. Then, if a number outside pf the pre-defined possibilities is entered, an error message appears. For example, if the user tried to enter a 6 for gender, the computer might beep and Tefuse the code. Other computer programs are designed to test for illegitimate codes in completed data files. That is, if they were not check! during the data check the files for coding errors 4 computer program that checks for coding errors during the data entry process, you can locate some errors simply by examining the distribution of repPonses to each item in the data set. For example, you could generate a frequency table for the variable gender and here you would See the number 6 that was mis-entered. You could then search for that entry in the data file and correct it. Contingency Cleaning : The second type of data cleaning is called contingency cleaning and is a little more complicated than Possible-code cleaning. The logical structure of the data may place certain limits on the responses of certain respondents or on certain variables. Contingency leaning is the process of checking that only those cases that should have data on a particular variable do in fact have such data. For example, let’s say that you have a questionnaire in which you ask respondents how many times they have been Pregnant. All female respondents should have a response coded in the data. Males, however should either be left blank or should have a special code for failing to answer. If any males in the data are coded as having 3 Pregnancies, for example, you know there is an error and it needs to be corrected.Ethics and Scientific Integrity Q. 1, What do you understand by scientific integrity? Ans. Research integrity may be defined as active adherence to the ethical principles and professional standards essential for the responsible practice of research. By active adherence we mean adoption of the principles and practices asa personal credo, not simply accepting them as impositions by rule makers. By ethical principles we mean honesty, the golden rule, trustworthiness, and high regard for the scientific record. NAS report definition: “For individuals research integrity is an aspect of moral character and experience. It involves above all a commitment to intellectual honesty and personal responsibility for ones actions and to a range of practices that characterize responsible research conduct.” These practices include: * Honesty and fairness in proposing, performing, and reporting research; Accuracy and fairness in representing contributions to research proposals and reports; Proficiency and fairness in peer review; Collegiality in scientific interactions, communications and sharing of resources; * Disclosure of conflicts of interest; © Protection of human subjects in the conduct of research; * Humane care of animals in the conduct of research; Adherence to the mutual responsibilities of mentors and trainees.” While science encourages (no, requires) vigorous defense of one’s ideas and work, ultimately research integrity means examining the data with objectivity and being guided by the results rather than by preconceived notions. We will return to the importance of preserving the integrity of the scientific record in the section on misconduct. Q. 2. What are protection issues for researchers to consider? Ans. Good data protection practice and ethics are essential in research in order to not only comply with the law but also the expectations of individuals that may be the subject of research. In developing a trusted relationship researchers need to follow ethical principles as well as expectations of confidentiality and privacy. In 2020 more data protection laws are being developed around the world and General Data Protection Regulation (GDPR) has focused many researchers’ minds on compliance there are more than 140 countries with data protection laws and many have similar approaches to the GDPR. Furthermore Regulators (41) Ls42 AMAR : Research Methodology around the world are enforcing the rights of individuals against organisation, that process personal data unlawfully or without transparency. The five important issues to consider are: . : : 1. Transparency and Accountability : Data Protection Principles require that when any personal data is being processed Researchers must provide transparent and plain language information to individuals whose data may be collected ang analysed. Researchers should ensure that they have available a Fair Processing Notice or Privacy Notice that informs individuals of who is processing the persona] data, with whom that personal data may be shared, the purposes for which the data will be used, for kow long it will be retained and what rights and privileges individuals have in terms of their personal data. In order to demonstrate accountability, the researcher as a controller must have appropriate policies and procedures in place such as not only the Privacy Notice but also a record of processing activities, a process for dealing with individuals rights requests, a process for using data protection impact assessments, a data retention and destruction policy and a policy for the control of sub contracted research organisations and any international transfers of personal data in the course of research. The above is not an exhaustive list of policies and procedures. 2. Understanding the nature of the personal data : It is essential to identify the nature of the personal data that is being collected during research as the more sensitive the nature of the data, the greater the obligations are for compliance. The GDPR defines personal data as, “any information relating to identified or identifiable natural persons who can be identified directly or indirectly, in particular by reference to an identification number or to one or more factors specific to their physical, psychological, genetic mental economic cultural or social identity”. The concept of personal data includes any sort of information about a person whether objective or subjective. The GDPR lays out more stringent obligations for researchers to consider where the personal data consist of “special categoriés of data” or “information relating to suspected criminal activities”. These particular sensitive data categories are those revealing racial or ethnic origin, political opinions, religious or philosophical beliefs, trade union membership, genetic data, biometric data, data concerning health or data relating to sexual orientation or activity. If as a researcher you are intending to process these special categories of data or information relating to criminal activity you will need to satisfy stricter conditions to be able to lawfully process that data. : 3. Controller or Processor : Researchers should consider whether in the course of their work they are acting as a controller or as a processor in relation to personal data because there are differences in the obligations and liabilities between @ controller and a processor. If the researcher is independently carrying out research where the outcomes will be marketed to customers then the researcher is likely to bea controller and as such will need to comply with all of the controller obligations of the GDPR and other similar legislation in other parts of the world should theyUnit-6 : Ethics and Scientific Integrity 43 apply. If however, the researcher is actin on the i i i i apoly however '8 on the instructions of a client and is Sa ae individuals or categories of individuals and then the outcot Cred as a report to the client then the researcher is a processor and most or the liability for data protection compliance rests with the client, If the research company is acting as a processor it will still have obligations.under the GDPR (where that applies) and should ant te that clients will want yl nticipate that cli I Zi as well as contractually that the research company will support the client in its role as a controller and meet its own obligations as the processor, 4. Lawful grounds for historical research pury w. Another lawful-ground that may be of value is that of legitimate interest provided that the legitimate interest of the research business to carry out research is not overridden by the individual rights of data subjects who may be the target of the research. 5. Ethics by design : Whilst privacy by design and security by default are still somewhat cliché phrases which highlight the need to embed. data protection by design into processes and systems, whilst at the same time ensuring technical, organisational and physical security into businesses and their management of Processing personal data, ethics by design is emerging as the next standard. Researchers need to not only address privacy and security but also consider how to embed ethics into their operations particularly with regard to processing of Personal data in circumstances that might not be anticipated by individuals Q. 3.What are the standards of conduct in research and methodology? Ans. Research standards provides guidelines for the responsible and meaningful research. Honesty : Honestly report data, results, methods and procedures, and Publication status. Do not fabricate, falsify, or misrepresent data. Objectivity : Strive to avoid bias in experimental design, data analysis, data interpretation, peer review, personnel decisions, grant writing, expert testimony, and other aspects of research.44 AMAR : Research Methodology Integrity :Keep your promises and agreements; act with sincerity; strive for consistency of thought and action. Carefulness : Avoid careless errors and negligence; Se wand really examine your own work and the work of your peers. Keep good re research activities. Openness : Share data, results, ideas, tools, resources. Be open to Ctiticism, and new ideas. Respect for Intellectual Property : Honor patents, copyrights, and other forms of intellectual property. Do not use unpublished data, methods, permission. Give credit where credit is due. N Confidentiality : Protect confidential comm records, Responsible Publication : scholarship, publication. , Tace, ethnicity, or other fas Human Sup; ai ub} . minimize hares Protection ; and rij 4 and autonomy, isks and Maxi ever plagiarize. junications, such as papers or submitted for publication, personnel records, trade or milita ry secrets, ite, mentor, and N against collea ‘ctors that are n or results Without rants and Patient Publish in order to advance research and { not to advance just your own career. Avoid wasteful and duplicative advise students, eir own decisions, \ gues or students | ‘ot related to their 7 professional competence and farning; take st | j eps to oy }