CHAPTER FOUR: RESEARCH STUDY DESIGN

Introduction
Research design is the conceptual structure within which research is conducted; it
constitutes the blueprint for collection, measurement and analysis of data.
The functions of a research design
The research design has two main functions. It Identifies and/or develops procedures
and logistical arrangements required to undertake a study, and Improves the quality
of procedures to ensure their validity, objectivity, and accuracy.
Different Research Designs
Different research designs can be conveniently described if we categorize them as:
(1) Research design in case quantitative studies;
(2) Research design in case of qualitative studies, and
(3) Research design in case of mixed method research studies.
Study Designs Associated with the quantitative Approach
During the late 19th century and throughout the 20th, designs of inquiry associated
with quantitative research were the true experiments and the less rigorous
experiments called quasi experiments and correlation studies and specific single-
subject experiments. More recently, quantitative studies involved various study
designs. The various study designs in quantitative studies have been classified by
examining them from three different perspectives.

I. The number of contacts with the study population

II. The reference period of the study
III. The nature of the investigation
1. The number of contacts: Based on the number of contacts with the study
population, study designs can be classified into three groups:
a) Cross-sectional studies
b) Before-and-after studies and
c) Longitudinal studies.
a. Cross-sectional studies
Cross-sectional studies known as one-shot or status studies and some phenomenon
by taking a cross section (only once) of it at one time. Cross-sectional studies the most
commonly used design in the social sciences and best suited to studies aimed at
finding out the prevalence of a phenomenon, situation, problem, attitude or issue.
Such studies are cross-sectional with regard to both the study population and the
time of investigation. As these studies involve only one contact with the study
population, they are comparatively cheap to undertake and easy to analyze. Their
biggest disadvantage, however, is that they cannot measure change.
b. The before-and-after study design
A before-and-after design can be described as two sets of cross-sectional observations
on the same population and it is comprised of two cross-sectional observations, the
second being undertaken after a certain period. Also known as the protest/post-test
design. The main advantage of the before-and-after design is that it can measure
change. It is one of the most commonly used designs in evaluation studies (i.e., for
measuring the impact or effectiveness of a program). The difference between the two
sets of observations with respect to the dependent variable is considered to be the
impact of the program.
The disadvantages are:
• More expensive and more difficult to implement
Page 1 of 8
 • In some cases, the time lapse between the two contacts may result in attrition
in the study population
• As it measures total change, you cannot ascertain whether independent or
extraneous variables are responsible for producing change in the dependent
variable. Also, is it not possible to quantify the contribution of independent and
extraneous variables separately?
• If the study population is very young and if there is a significant time lapse
between the before-and-after observations, changes in the study population
may be because it is maturing.
Reactive Effect: Sometimes the instrument itself educates the respondents. This is
known as the reactive effect of the instrument.
Regression effect: may occur when you use a research instrument twice to gauge the
attitude of a population towards an issue is a possible shift in attitude between the
two observations. Sometimes people who place themselves on the extreme positions of
a measurement scale at the Pre-test stage, may, for a number of reasons, shift
towards the mean at the post-test stage. (They might feel that they have been too
negative or too positive at the pre-test stage. Therefore, the mere expression of an
attitude in response to a questionnaire or interview has caused them to alter their
attitude at the time of the post-test. This type of effect is known as the regression
effect.
c. Longitudinal study design
Longitudinal studies used to determine the pattern of change in relation to time.
Longitudinal studies are also useful when you need to collect factual information on a
continuing basis. Although the data collected is from the same study population, it
may or may not be from the same respondents. A longitudinal study can be seen as a
series of repetitive cross-sectional studies. Longitudinal studies have the same
disadvantages as before-and-after studies, in some instances to an even greater
degree. In addition, longitudinal studies can suffer from the conditioning effect. This
describes a situation where, if the same respondents are contacted frequently, they
begin to know what is expected of them and may respond to questions without
thought, or they may lose interest in the inquiry, with the same result. The main
advantage of a longitudinal study is that it allows the researches to measure the
pattern of change and obtain factual information requiring collection on a regular or
continuing basis.

2. Reference period; the reference period refers to the time-frame in which a study is
exploring a phenomenon, situation, event or problem. Studies within this perspective
are thus categorized as:
a) Retrospective;
b) Prospective; and
c) Retrospective-prospective.
a. The retrospective study design
Retrospective studies investigate a phenomenon, situation, problem or issue that has
happened in the past. They are usually conducted either on the basis of the data
available for that period or on the basis of respondents recall of the situation.
For example, studies conducted on the following topics are classified as retrospective
studies:
Page 2 of 8
 ✓ The living conditions of aboriginal people in Ethiopia in the early twentieth
century.
✓ The utilization of land before World War II in Ethiopia.
✓ A historical analysis of migratory movements in Eastern Europe between 1915
and 1945.
b. The prospective study design
Prospective studies refer to the likely prevalence of a phenomenon, situation, problem,
attitude or outcome in the future. Such studies attempt to establish the outcome of
an event or what is likely to happen. Experiments are usually classified as prospective
studies as the researcher must wait for an intervention to register its effect on the
study population. The following examples are classified as prospective studies:
✓ To determine, under field conditions, the impact of maternal and child health
services on the level of infant mortality.
✓ To establish the effects of a counseling service on the extent of marital
problems.
c. The retrospective-prospective study design
Retrospective-prospective studies focus on past trends in a phenomenon and study it
into the future. In a retrospective-prospective study a part of the data is collected
retrospectively from the existing records before the intervention is introduced and
then the study population is followed to ascertain the impact of the intervention.
Trend studies, which become the basis of projections, fall into this category. Some
examples are: The impact of incentives on the productivity of the employees of an
organization.
3. Nature of the investigation; On the basis of the nature of the investigation, studies
can be classified as:
a) Experimental;
b) Non-experimental; and
c) Quasi or semi-experimental.
a. Experimental Design
In experimental design, researchers plan to measure the response variable depending
on the explanatory variable. The response variable is an outcome measure for
predicting or forecasting purposes of a study. It is also called dependent variable or
predicted variable. Any variable that explains the response variable is called
explanatory variable. It is also called independent variable or predictor variable. A true
experimental design is one in which study participants are randomly assigned to
experimental and control groups. Although randomization is typically described using
examples such as rolling dice, flipping a coin, or picking a number out of a hat, most
studies now rely on the use of random numbers tables to help them assign their
research participants. A random numbers table is nothing more than a random list of
numbers displayed or printed in a series of columns and rows. The most important
factor in the experimental design is randomization. The randomization check, as its
name suggests, is the process of examining the overall effectiveness of random
assignment. In performing randomization checks, researchers compare study groups
or conditions on a number of pre-test variables. These typically include demographic
variables such as age, gender, level of education, and any other variables that are
measured or available prior to the intervention.
Quasi-experimental Design
Page 3 of 8
Although the researcher plans to measure the response variable depending on the
explanatory variable, there is a lack of randomization in the quasi-experimental
design. It is a mixed design where random and non-random experiments are employed
together.

Some Important Concepts Related to Designing a Quantitative Research

1) Variable and concept; an image, perception or concept that is capable of
measurement-hence capable of taking on different values-is called a variable. In other
words, a concept that can be measured is called a variable. A variable is a property
that takes on different values. Concepts are mental images or perceptions and
therefore their meanings vary markedly from individual to individual, whereas
variables are measurable. Measurability is the main difference between a concept and
a variable. A concept cannot be measured whereas a variable can be subjected to
measurement by crude/refined, or subjective/ objective units of measurement.
Concepts are subjective impressions-their understanding may differ from person to
person. It is, therefore, important for the concepts to be converted into variables as
they can be subjected to measurement even though, the degree of precision with
which they can be measured varies from scale to scale. If you are using a concept in
your study, you need to consider its operationalization, that is, how it will be
measured. To operationalize a concept, you first need to go through the process of
identifying indicators. Indicators are a set of criteria reflective of the concept-which
can then be converted into variables.
Concept Indicators variable Decision level
Achievement Average marks obtained Percentage of marks If > 75%
In examination
Types of variable
A variable can be classified in a number of ways. The classification developed here
results from looking at variables in different ways:
A) From the view point of Causation
a) Independent variables (change)
b) Dependent variables (outcome)
c) Extraneous variables (affect)
d) Intervening variables (linking or connecting)
B) From the view point of study design
a) Active variables
b) Attribute variables
C) From the view point of unit of measurement
a) Categorical variables
b) Continuous variables
c) Qualitative variables and
d) Quantitative variables
A. From the view point of causation
In studies that attempt to investigate a causal relationship or association, four sets of
variables may operate: Change variables, which are responsible for bringing about
change in a phenomenon; Outcome variables, which are the effects of a change
variable; and variables which affect the link between cause-and-effect variables;
connecting or linking variables, which in certain situations are necessary to complete
the relationship between cause-and-effect variables. In research terminology, change
variables are called independent variables; outcome/effect variables are called
Page 4 of 8
dependent variables; the unmeasured variables affecting the cause-and-effect
relationship are called extraneous variables; and the variables, that link a cause-and-
effect relationship are called intervening variables.
1. Independent variables: the cause supported to be responsible for bringing about
changes (s) in a phenomena or situation.
2. Dependent variables: the outcome of the change (s) brought about by
introduction of independent variables.
3. Extraneous variables: several other factors operating in all real-life situations
may affect changes in the dependent variable. These factors, not measured in
the study, may increase or decrease the magnitude or strength of the
relationship between dependent and independent variables.
4. Intervening variables: sometimes called confounding variables link the
independent and dependent variables; in a certain situation the relationship
between an independent and dependent variable cannot be estimated without
the intervention of another variable. The cause variable will have the assumed
effect only in the presence of an intervening variable.
B. From the view point of the study design: a study that examines association or
causation may be a controlled or contrived experiment, a quasi-experiment or an
ex-post facto of non-experimental study. In a controlled experiment the
independent or (cause) variable may be introduced or manipulated either by the
researcher or by somebody else who is providing the service, there are two sets of
variables:
1. Active variables: these variables that can be manipulated changed or controlled
2. Attribute variables: those variables that cannot be manipulated, changed, or
controlled; and that reflect the characteristics of the study population. For
example, age, gender, education, and income.
C. From the viewpoint of the unit of measurement
From the viewpoint of the unit of measurement, there are two ways of categorizing
variables: Whether the unit of measurement is categorical (as in nominal and ordinal
scales) or continuous in nature (as in interval and ratio scales); and whether it is
qualitative (as in nominal and ordinal scales) or quantitative in nature (as in interval
and ratio scales). The variables thus classified are called categorical or continuous,
and qualitative or quantitative. On the whole there is very little difference between
categorical and qualitative, and between continuous and quantitative variables.
Categorical variables can be of three types:
i. Constant;
ii. Dichotomous; and
iii. Polytomouse
When a variable can have only one value or category, e.g., taxi, tree, water, it is known
as a constant. When a variable can have only two categories as in yes/no; good/bad;
rich/poor, it is known as a dichotomous variable. When a variable can be divided in to
more than two categories, e.g., religion (Christian, Muslim, Hindu); Political parties
(EPDRF, EDP, Coalition); attitudes (strongly favorable, favorable, uncertain,
unfavorable, strongly unfavorable), it is called a Polytomouse variable.
Continuous variables, on the other hand, have continuity in their measurement. For
example, age, income, an attitude score. They can take on any value on the scale on
which they are measured. Age can be measured in years, months and days. Similarly,
income can be measured in Birr and cents.
Figure 4.1
Page 5 of 8
Categorical/continuous and qualitative/quantitative variables

Categorical Continu Qualitative Quantitative

ous
Constant Dichotomous Polytomouse
✓ Water ✓ Yes/no Attitude Income Gender Educational
✓ Tree ✓ Good/bad ✓ Strong in $ ✓ Male level ---no
✓ Taxi ✓ Rich/poor ✓ Favorable ✓ Female years
✓ Male/female ✓ Uncertain Ed. Level complete
✓ Hot/cold ✓ Unfavorable Age in ✓ High
Age years ✓ Averag Age ----
✓ Old e years/mont
✓ Young ✓ Low hs
✓ Child Age
Income Weight ✓ Old Income ----$
✓ High in (kg) ✓ Young per year
✓ Middle ✓ Child Temp---Co,
✓ Low Fo

Figure 4.2
Types of variables Causal model Independent variables
Dependent variables
Intervening
Extraneous
Study design Active variable
Attribute variable
Unit of measurement Categorical variable
Continuous variable
Qualitative variables
Quantitative variable

Measurement and Scaling Techniques

Measurement is central to any scientific inquiry. The greater the refinement in the
unit of measurement of a variable, the greater the confidence, other things being
equal, one can place in the findings. Scaling is how we get numbers that can be
meaningfully assigned to objects.
Types of Scales
The scaling procedures may be broadly classified on one or more of the following
bases:
The type of data they generate, and the means of generating data
i. Classification based on the type of data they generate
There are four measurement scales used in social science. According to S.S Stevens
(1946) the different types of measurement scale are classified in to four categories:
1) Nominal/classificatory
2) Ordinal/ranking scale
3) Interval scale
4) Ratio scale
I) Nominal/classificatory scale

Page 6 of 8
Is defined as a scale whose numbers serve only as labels or tags for identifying and
classifying objects with a strict one-to-one correspondence between the numbers and
the objects. Each number is assigned to only one object and each object has only one
number assigned to it. Common examples include social security numbers and
numbers assigned to football players.
When used for classifying purposes, the nominally scaled numbers serve as labels for
classes or categories. For example, you might classify the control group 1 and the
experimental group as group 2. The objects in each class are viewed as equivalent
with respect to the characteristics represented by the nominal number. All objects in
the same class have the same number and no two classes have the same number. The
numbers in a nominal scale do not reflect the amount of the characteristics possessed
by the objects. For example, your identity number does not imply that you are in
some way superior to those with lower identity number or vice versa.
Sample Nominal –Scaled Questions
Please indicate your gender. 1. Male 2. Female
Check all the brands you would consider purchasing.
1. Semein Mountains 2. Lalibela 3. Tis Abay 4. Axum
II) Ordinal Scales/ranking scale
Have all the properties of a nominal scales plus one of its own. Is defined as a ranking
scale in which numbers are assigned to objects to indicate the relative extent to which
some characteristics is possessed. Thus, it is possible to determine whether an object
has more or less of characteristics than some other object. The object ranked first has
more of the characteristics as compared to the object ranked second, but whether the
object ranked second is a close second or a poor second is not known. Common
examples of ordinal scale include quality rankings, ranking of teams in a tournament,
socio economic class, and occupational status. In business research, ordinal scale is
used to measure relative attitudes, opinions, perceptions, and preferences. Please
rank each brand in terms of your preference. Place a-1 by your first choice, a-2 by
your second choice, and so on.
1. Addis abebe
2. Awasa
3. Adama
III) Interval Scales
Have all the characteristics of an ordinal scale plus one of its own. Is defined as a
scale in which the numbers are used to rate objects such that numerically equal
distances on the scale represent equal distances in the characteristics being
measured. The difference between any two adjacent scale values is identical to the
difference between any other two adjacent values of an interval scale. There is a
constant or equal interval between scale values. The difference between 1 and 2 is the
same as the difference between 2 and 3, which is a temperature scale. In business
research, attitudinal data obtained from ratings scales are often treated as interval
data. In the interval scale, the location of the zero point is not fixed. Both the zero
point and the units of measurement are arbitrary. Therefore, two interval scales that
rate objects A, B, C, and D as 1, 2, 3, and 4, or as 22, 24, 26, and 28, are equivalent.
Because the zero point is not fixed, it is not meaningful to take ratios of scale values.
As can be seen, the ratio of D to B values changes from 2: 1 to become 7:6 when the
scale is transformed. Yet ratios of differences between scale values are permissible.
The ratio of the difference between D and B to the difference between C and B is 2: 1
in both the scales. Please rate each brand in terms of its overall performance.
Page 7 of 8
 Very poor Very good
Panasonic 1 2 3 4 5
Philips 1 2 3 4 5
Sony 1 2 3 4 5

Indicate your degree of agreement with the following statements by encircling the
appropriate number

Statement Strongly Strongly Agree

Disagree
1 1 2 3 4 5
1 I always look for bargains 1 2 3 4 5
2 I enjoy being outdoors 1 2 3 4 5
3 I love to cook. 1 2 3 4 5
iv) Ratio Scale
Has all the characteristics of nominal, ordinal, interval scale plus its own property. Is
defined as the highest scale. It allows the researcher to identify or classify objects,
rank order the objects, and compare intervals or differences. It is also meaningful to
compute ratios of scale values. Not only is the difference between 2 and 5 the same as
the difference between 14 and 17, but also 14 is seven times as large as two in an
absolute sense. Common examples of ratio scales include height, weight, and money.
Number Tourists/customers, sales, costs, and market share are variables measured
on a ratio scale. All statistical techniques can be applied to ratio data. These include
specialized statistics such as geometric Mean, harmonic mean, and coefficient of
variation. Approximately how many times in the last week have you purchased
anything over birr 5 in value at ERTALE MOTEL? 0 1 2 3 4 5 more (specify__________)

Page 8 of 8