Professional Documents
Culture Documents
1
§ Specify the sources and procedure you intend to collect data
§ The population to be studied and how sampling can be obtained
§ Techniques to be used in processing and analyzing data
§ Other critical issues relating the study (such as, the constraints faced by the researcher
- access to data, time, location, funds, etc.
§ Ethical issues or reliability of information.
There are several types of research designs, depending on the types of research and
scope of the research. Some of these include:
2
iv. Cross-sectional design - In this the type of design, the cause and effects
variables are measured at the same time. For instance, where the cause is
advertisement reading; as a variable and the effect is purchase: as another
variable, they are both measured at the same time. This type of research
design is also referred to as correlational research design.
v. Time series design: – The time-series design is used when to establish a stable
baseline. In other words, observing and establishing the normal fluctuation of
the dependent variable over time, such as 5 to 10 years. Note that time series
design can take the form of interrupted, simple, reversal (ABA) or multiple
time series, as such a researcher needs to specify which the time series
adopted.
vi. Case study design: This involves two discrete dimensions:
• Single case v. multiple case;
• Holistic case v. embedded case.
A single case is often used where it represents a critical case or, alternatively, an
extreme or unique case. Conversely, a single case may be selected because it is
typical or because it provides an opportunity to observe and analyse a
phenomenon that few have considered before in a particular organisation for
which they work. A case study strategy can also incorporate multiple cases, that
is, more than one case. The rationale for using multiple cases focuses upon the
need to establish whether the findings of the first case occur in other cases and, as
a consequence, the need to generalise from these findings.
It should be noted that, various research designs are also possible with different
research types, since a research design is only tentative in the sense that as the
study progresses, new facts, new ideas and new conditions may necessitate a
change in the original paradigm or strategy. For instance, the other research
3
designs may include:
Although, research design have grown over the years as computer technology has
advanced our data analysis and ability to analyze complex models and as individuals
have articulated new procedures for conducting social science research, an overview
of research designs in social sciences is often associated with the methodological
choice of the research. These groupings can be discussed under the following:
I. Quantitative Design
The quantitative strategies include:
v Experimental studies: An experimental study is a methodology used in physical
sciences to investigate the relationship between variables, where the independent
variable is deliberately manipulated to observe the effect on dependent variable.
Experimental studies permit causal relationships to be identified. The aim is to
manipulate the independent variable (for example noise levels in factor
environment) in order to observe the effect on the dependent variable (for
example the productivity of factory workers). This nature of experiment is
conducted in a systematic way in a laboratory. In fact, this is referred to as
4
hypothesis-testing research. Similarly, a research in which an independent
variable is not manipulated is called ‘non-experimental hypothesis-testing
research
v Survey design: The survey strategy is usually associated with the deductive
approach. It is a popular and common strategy in business and management
research and is most frequently used to answer who, what, where, how much and
how many questions. It therefore tends to be used for exploratory and descriptive
research. Surveys are popular as they allow the collection of a large amount of
data from a sizeable population in a highly economical way. Often obtained by
using a questionnaire administered to a sample, these data are standardized,
allowing easy comparison. In addition, the survey strategy is perceived as
authoritative by people in general and is both comparatively easy to explain and
to understand. Every day a news bulletin or a newspaper reports the results of a
new survey that indicates, for example, that a certain percentage of the population
thinks or behaves in a particular way.
5
methodology is designed to collect primary or secondary data from a sample of
individuals through their responses to questions, with a view to analyzing them
statistically and generalizing the results to a population. Thus, population is a
body of people or objects under consideration for statistical purposes, and sample
is a subset of a population. Regardless of the researcher’s scope, survey research
owes its continuing popularity or strength due its versatility efficiency and
generalizability features.
Third, indicate why a survey is the preferred type of data collection procedure for the
study. In this rationale, consider the advantages of survey designs, such as the
economy of the design and the rapid turnaround in data collection.
Fourth, specify the form of data collection, such as: mail, telephone, using an
Internet survey and administering it online, personal interviews, group
administration or structured questionnaire.
Five, regardless of the form of data collection, provide a rationale for the procedure,
using arguments based on its strengths and weaknesses, costs, data availability, and
convenience.
Generally, purposes of surveys can be divided into three types: descriptive survey,
analytical or explanatory survey, and concepts forming, each has its purpose:
6
v Descriptive survey – the purpose of descriptive survey is to provide an accurate
representation of phenomena at one point in time or at various times. For
example, it is common to find questions that are concerned with fact finding,
often involving issues relating opinion polls, consumer research, or that require
demographic data as, in cases of identifying the proportion of respondents in
different age categories, salary levels, educational levels or wealth categories.
There is almost no limit to the range of variables of this sort that could be
addressed through a research surveys. Such questions could be said to have a
descriptive purpose.
v An analytical or explanatory survey – this is conducted to determine whether
there is a relationship between pairs of variables or multiple variables. Such
studies need the researcher to develop a theoretical framework from the literature
so as to identify the dependent and independent variables in the relationship.
v Concept-forming survey – However, there is a third category of questions that
can be described as having a concept-forming purpose. This is often identified
after scrutiny of the literature to identify themes. In this case, the survey
questionnaire is to be designed to characterize these themes with a view to
develop the concept.
A survey methodology can also be sued in an interpretive study. In this case, selecting
a sufficient large and unbiased sample for the survey is not necessary, because the
aim of the research is not to generalize to the population, but to gain insights from the
cases in the sample. These aspects need proper understanding by the researcher,
because of its suitability under a positivist paradigm. Once the survey design is
completed, the researcher needs to proceed to design for the collection of data
through: questionnaires (postal or internet questionnaires), interviews (telephone or
face-to-face).
7
research would look for similarities and differences between industries. In studies
focusing on people, employees working in different parts of an organization might be
selected to ascertain similarities and differences between groups. For instance, in the
investigation of the relationship between labour turnover and productivity. Cross-
section studies are conducted when there are time constraints or limited resources.
The data are collected once, but its difficulty is in determining the sample that is large
enough to be the representative of the population. More so, many researchers find it
difficult to explain why correlation exists or its influence to the phenomena under
study.
v Longitudinal studies: A longitudinal study is a methodology used to investigate
variables or group of subjects over a long period of time. Although, longitudinal
study is often associated with positivist cum quantitative methodology, it can also be
used under an interpretive paradigm and focus on qualitative data. The aim of
longitudinal study is to examine the dynamics of a research problem by investigating
the same variables or group of people several times (or continuously) over the period
in which the problem runs. This methodology is very time- consuming and expensive.
One of the techniques used in analyzing data collected in longitudinal study is time
series analysis.
8
important if it can be explored since it has the advantage of flexibility in classifying
methods and value creativity.
9
of change in social systems, and thus is a suitable research and consulting strategy.
The methodology is sometimes referred to as ‘action science’. This methodology is
widely in business management.
v Case study design: A case study is methodology that is used to explore a single
phenomenon (the case) in a natural setting using a variety of methods or techniques to
obtain in-depth knowledge. However, the characteristics of this type of design, is that,
it does not commence with a set of questions, and the aims is not only to explore
certain phenomena, but also to understand them within a particular context. These
characteristics are linked to interpretivist assumptions. However, if you are taking a
more positivist approach, which is allowed in case studies, you might need to develop
a theoretical framework and specific research questions. The advantage of case
studies research is; it uses multiple techniques (both quantitative and qualitative) for
collecting data, which may be both qualitative and quantitative in nature. There are
different types of case studies research:
- descriptive case studies, where the objective is to be restricted to describing current
practice.
- Illustrative case studies, where the research only attempt to illustrate new and
possible innovative practices as may be adopted by particular companies
- Experimental case studies –examine difficulties in implementing new procedures
and techniques in organizations
- Explanatory case studies, where existing theory is used to understand and explain
what is happening
- Many others, such as opportunist case study, etc.
10
closure where the researchers only collect data relevant to their theories and ignore
data that could be useful for explaining what was happening. The overall features of
grounded theory include:
- an initial attempt to develop categories that illuminate the data
- an attempt to ‘saturate’ these categories with many appropriate cases in order to
demonstrate their importance
- developing these categories into more general analytic frameworks with relevance
outside the setting, and
- develop a substantive theory derived from data. The substantive theory can also
lead the development of a formal theory after validation.
The grounded theory analytical procedure follows the coding of the data through the
open, axial and selective coding principles.
v Archival research: The final strategy we wish to consider, archival research, makes
use of administrative records and documents as the principal source of data. Although
the term archival has historical connotations, it can refer to recent as well as historical
documents. It is important that an archival research strategy is not conflated with
secondary data analysis, even though all research that makes use of data contained in
administrative records is inevitably secondary data analysis.
An archival research strategy allows research questions, which focus upon the past and
changes over time to be answered, be they exploratory, descriptive or explanatory.
However, your ability to answer such questions will inevitably be constrained by the
nature of the administrative records and documents. Even where these records exist,
they may not contain the precise information needed to answer your research
question(s) or meet your objectives. Alternatively, data may be missing or you may be
refused access or your data censored for confidentiality reasons. Using an archival
research strategy therefore necessitates you establishing what data are available and
designing your research to make the most of it.
11
v Feminist, gender and ethnicity studies: there are a number of different perspectives
on social stratification. Feminist studies are a methodology used to investigate and
seek understanding of phenomena from a feminist perspective of the role of women in
society vis - a -vis men, while gender studies are concerned with the experiences of
both men and women. On the other hand, ethnicity studies focus on the experiences of
different ethnic groups in society. At a methodological level, a feminist perspectives is
concerned with challenging ‘the traditional research paradigm from the point of view
of the politics and ideology of the women’s movement’. Generally, feminist
perspective can be used in the following three principles:
- knowledge is grounded in the experiences of women
- the research benefits women
- the researcher immerse herself or himself in or exhibits empathy for the world being
studied.
Even though adopting a feminist methodological design can present both theoretical
and practical problems, the methodology brings a new perspective in research and
offer insights and understanding of problems that might otherwise be unavailable.
This is the general term when both quantitative and qualitative data collection
techniques and analysis procedures are used in a research design. It can be used as
quantitative and qualitative data collection techniques and analysis procedures either at
the same time (parallel) or, one after the other (sequential) but does not combine them.
This means that, although mixed method research uses both quantitative and qualitative
at the research methods stage, quantitative data are analyzed quantitatively and
qualitative data are analyzed qualitatively.
IV. Triangulation
Triangulation is the use of multiple sources of data, different methods, and or more than
one researcher to investigate the same phenomenon in a study. This can reduce bias in
data sources, methods and investigators. In addition, the use of different methods by a
12
number of researchers studying the same phenomenon should lead to greater validity
and reliability compared if only one method was used. A simple example of using
multiple sources of data might be to ask many people to describe an event in the market
place or on celebration day. By collecting all these separate impressions, the researcher
could get a much richer picture of the way the participants experience the events.
Generally, triangulation in research studies can be analyzed in four main forms or
types:
Many researchers considered using triangulation, but unless you are part of the research
team, it is difficult to achieve triangulation by investigator. Also, some of the limitations
of methodological triangulation are that replication is more difficult, particularly if the
qualitative data are generated and data collection and analysis become more time
consuming and expensive.
13