1

Chapter Six-Part One

Variables
 Definition of a variable
2

 A concept that can be measured is called a variable.

 A variable is a symbol to which numerals or values are
attached.
 A variable is a rational unit of analysis that can
assume any one of a number of designated sets of
values.
 A concept that can be measured on any one of the
four types of measurement scales, which have varying
degrees of precision in measurement is called a
variable (measurement scales will be discussed latter)
 Con’t
3

Concept vs. Variable

 Concepts are mental images or perceptions and
therefore their meanings vary markedly from
individual to individual; where as variables are
measurable, of course , with varying degrees of
accuracy. Measurability is the main difference
between a concept and a variable.
 A concept can not be measured where as a variable
can be subjected to measurement with some units of
measurement.
 Concepts are subjective impressions-their
understanding may differ from person to person
 Con’t
4

Concept vs. Variable ----

 It is therefore important for 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.
 Con’t
5  Some examples of concept and variable ----
Concept Variable
• Effectiveness • Gender (male, female)
• Satisfaction • Age (x-years, y-months)
. Impact • Income (high level, low
level……..)
. Excellent • Weight
• High achiever • Religion
➢ All are subjective impressions ➢Are measurable
➢ No uniformity for understanding
➢ As such can not be measured
Research Methods in Accounting and Finance
 Con’t
6

 If you are using a concept in your study, you need to

consider its operationalization-that is how it will be
measured.
 In most cases to operationalize a concept you first
need to go through the process of identifying
indicators- a set of criteria reflective of the
concept-which can then be converted into variables.
 The indicators used by the researcher must have
logical link with the concept.
 Con’t
7

 Some concepts such as “rich” can easily be

converted in to indicators and then variables.
 So researcher shall develop indicators of richness to
objectively decide the richness of a person.
 For instance- income and assets can be used as
indicators of richness so that using these indicators
the concept, rich, which can not be measured can be
converted in to measurable variable.
 Conversion of concepts in to variables
8

Concept Indicators Variables

Concept Indicators Variables Decision level
(Example) ( Working definition)

Rich •Income •Income per year •Rich If > Birr 100,000

•Assets •Total values of assets •Rich If > Birr 250,000

High •Average marks •Percentage of marks •High achiever if > 75%

academic obtained in
achievement examination
 Types of variables
9

1. Independent variable:
2. Dependent Variable:
3. Extraneous variable:
4. Intervening Variable/compounding
variable.
 1. Dependent Variable
 The variable of primary interest to the researcher.

 The researcher’s goal is to understand and describe the

DV and to predict it.

 It is the main variable lends itself for the investigation as

a viable factor.

 It is also possible to have more than one DV. This type

of study demands multivariate statistics
2. Independent Variable
 Is that one influences the dependent variable in either negative
or positive way.

 To establish that a change in the independent variable causes

the change in the DV, the four conditions must be meet

 1. IV and DV should covary: in other words, a change in DV

should be associated with a change in IV
 Cont’d…
12

 2. the IV (the presumed causal factor) should precede the DV.

In other words, there must be a time sequence in which the to
occurs: the cause must occur before the effect.

 3. No other factor should be a possible cause of the change in

DV. Hence, the researcher should control for the effect of other
variables.

 4. A logical explanation (a theory) is needed about why the IV

affects the DV
3. Moderating Variable
The MV is one that has a strong contingent effect on the IV-DV
relationship. That is, the presence of a third variable (the moderate
variable) modifies the original relationship between the independent and
dependent variables. This becomes clear through the following
examples;

 It has been found that there is a relationship between the availability

of reference and manuals that manufacturing employees have
access to, and the product rejects. That is, workers follow the
procedures laid down in the manual, they are able to manufacture
that products are flawless.
 Cont’d…Example
 Although this relationship can be said to hold true generally for all

workers, it is nevertheless contingent on the inclination or urge of the

employees to look in the manual every time a new procedure is to

be adopted. In other words, only those who have the interest and

urge to refer to the manual every time a new process is adopted will

produce flawless products. Others who do not consult the manual

will not benefit and will continue to produce defective product.

Cont’d…

Availability of Number of
reference Manual rejects

Availability of Number of
reference Manual rejects

Interest &
Inclination
 4. Mediating Variable

 A mediating variable ( intervening variable) is one that surfaces

between the time and IVs start operating to influence the DV and the
time their impact is felt on it.

 It surfaces as a function of the IVs operating in any situation, and

helps to conceptualize and explain the influence of the IVs on the DV.
In the following example, the IV (work diversity) influences the DV
(organizational effectiveness), the mediating variable that surfaces as
a function of the diversity in the work force is “creative synergy.” This
creative synergy results from a diversity workforce interacting and
bringing together their multifaced expertise in problem solving.
Cont’d…
 This helps us to understand how organizational
effectiveness can result from having diversity in the
workforce.

Work force Creative Organizational

Diversity Synergy effectiveness
 5. Extraneous Variables
 An extraneous variable is a rival explanatory variable that could also
explain the relationship between the independent and dependent variables.

 The presence of an extraneous variable makes it difficult to make claims

about the relationship between the independent and dependent variables.
Extraneous variables can be eliminated in experimental research by
employing several techniques,

 In experimental research, the presence of extraneous variables creates what

is known as a confound : a situation in which it is not known whether
changes in the dependent variable were caused by the independent variable
or by an extraneous variable.
 Types of variables…….
19
From the view point of the unit of measurement, there are two ways
of categorizing variables.
1. Categorical variables: are variables that can be measured on
nominal or ordinal measurement scales and Includes:
a) Constant-when a variable can have only one value or category
as water, taxi, etc
b) Dichotomous-when variable can have only two categories as
male/female, yes/no, good/bad, rich/poor, etc.
c) Polytomous- when a variable can be divided in to more than
two categories as religion ( Christian, Muslim, Hindu, buhdisim).
➢ Note that most of categorical variable are qualitative
variables as both use either nominal or ordinal measurement
scales.
 Types of variables…….
20

2. Continuous variables: are variables having

continuity in their measurement.
Example: age(child, young, old), income (low,
middle, high) etc..
➢ Note that most of continuous variable are
quantitative variables as both use either interval
or ratio measurement scales.
 Chapter Six-Part II
21
Types of measurement scales
▪ Note that the way you measure the variables in
your study determines whether a study is qualitative
or quantitative in nature. It is therefore, important to
know about the measurement scales for variables.
▪ There are four types of measurement scales.
1. Nominal scale
2. Ordinal scale
3. Interval scale
4. Ratio scale
 Types of measurement scales..
22

1. Nominal scales: Also called classificatory scale.

 Enables classification of individuals, objects, or
responses based on a common/shared property or
characteristics.
 There is no sequential order for classification.
 A variable measured on nominal scale may have one,
two, or more subcategories depending upon the
extent of variation.
 Example: water and tree (have only one subgroup),
gender (has two subcategories as male and female),
religion and marital status (have more than two
subcategories).
Nominal Data Scale
e.g. 1=male (50%),
• Qualitative/dichotomies/categorica
l
2=Female (50%)
E.g. sex, color, marital status, type of
car, religion
1=blue (30%), 2=read
Ordaining does not work
• Mode, percentage, frequency and (40%), 3=white (30%)
range are measure of statistics
 Example of research questions for nominal
data
24

Questions Response type

Gender Male Female

0 1

Martial Status Married Not married Divorced

1 2 3

Do you have car? Yes No

0 1
 Types of measurement scales..
25

2. Ordinal scale: also called ranking scale.

 It has all the properties of a nominal scale plus one

of its own that is it ranks the subgroups in a certain
sequential order (they are arranged in ascending or
descending order)
Ordinal e.g. 1st winner, 2nd place winner, 3rd place

• Ranking winner, however the difference cannot be

measured. E.g. the 1st winner records 3.05, the
• Ordering of data is
second winner is 3.11, and the 3rd winner is
possible 5.06,
• The difference cannot be e.g.2. Excellent (A+), Very good (A), Good (B),
measured satisfactory (C), poor (F)
In all above cases we cannot measure the
differences between A+ and A, just we value
socio-economic status (low, medium, high), size
(small, medium, high),
Example of research questionnaire
for ordinal data scale

Item Excellent Very Good Good Satisfactory

Graduate students thesis result

4 3 2 1

Your level of satisfaction

4 3 2 1
 Types of measurement scales..
28

3. Interval scale: It has all the properties of ordinal scale

which also includes nominal scale plus it has a unit of
measurement that enables the responses to be placed
at equally spaced intervals in relation to the spread of
the variable
 The scale has its own starting and terminating point that
is divided in to equally spaced units/intervals.
Interval
• The order matters
• Differences can be
measured (except ratio)
• No true “0” starting point
• Cannot measured ratios
e.g. temperature (30 0f, 60 0f, 90
0f), the difference between 30 and
60=30, 60 and 90=30 but 60/30=2
does not mean 60 is 2 times hotter
than 30
0 does not measure the starting
point in interval data scale. E.g
there is negative temperature and
there does not mean the lowest
temperature
Interval data Scale
 Types of measurement scales..
31

4. Ratio scale: It has all the properties nominal,

ordinal and interval scale plus it has a fixed
starting point.
 It is an absolute scale-the difference between the

intervals is always measured from a zero point and

hence can be sued for mathematical operations.
Ratio e.g. Grade 0, 40, 30, 50, 90, 67, 70,
80, now lets order=30,40,50, 67, 80,

• The order matters 90

Income, age, height, weight etc.

• Differences are 90/30=3, 0 here reference that the

students did not answer, but we cannot

measurable find negative result

A person earning Birr 60,000 per year

(including ratio) earns three times the salary of a

person earning Birr 20,000

• Has “0’ starting

point
 Chapter Six: Part III
Sampling and Sample Size Determination
34

 Population: all members of a specified group

 Target population- the population to which the researcher
ideally wants to generalize.

 Accessible population- the population to which the

researcher has access.

 Sample: A subset of population

 Subject: A specific individual participating in a study.

 Population
35

 The group you wish to generalize to is often is called

the population /universe
 Population is an aggregate of items possessing a
common trait or traits. It is a complete group of items
about which knowledge is sought. There is a distinction
between the population you would like to generalize to,
and the population that will be accessible to you. We'll
call the former the theoretical population and the
latter the accessible population.
 Furthermore, population could be finite or infinite.
 Similarly, population could be hypothetical or existent.
 Sampling Frame
36

Sampling Frame: Once you've identified the

theoretical and accessible populations, you have to
do one more thing before you can actually draw a
sample -- you have to get a list of the members of
the accessible population. (Or, you have to spell out
in detail how you will contact them to assure
representativeness). The listing of the accessible
population from which you'll draw your sample is
called the sampling frame.
 Sampling
37

 Sampling is the process of selecting units (e.g., people,

organizations) from a population of interest so that by studying
the sample you may fairly generalize your results back to the
population from which they were chosen.

 Sampling theory is a study of relationships existing between a

population and samples drawn from the population.
 Sampling Design
39

 A sample design is a definite plan for obtaining a

sample from a given population. It refers to the
technique or the procedure the researcher would
adopt in selecting items for the sample.
 Sample design may as well lay down the number of
items to be included in the sample i.e., the sample
size.
 Researchers must select/prepare a sample design
which should be reliable and appropriate for his
research.
 Sampling Design
40

 While developing a sampling design, the researcher

must pay attention to the following points:
1. Defining clearly the population/ universe to be studied.
2. Determination of the sampling unit.( Sampling unit may
be a geographical one such as state, district, village,
etc., or a construction unit such as house, flat, etc., or it
may be a social unit such as family, club, school, etc.,
or it may be an individual.
3. Identifying the sampling frame or source list. (Sampling
frame contains the names of all items of universe).If a
source list is not available, a researcher has to
prepare it.
 Sampling Design
41

4. Determining the sample size. (This refers to determining the

number of items to be selected from the population to
constitute a sample.) An optimum sample size is one which
fulfills the requirements of efficiency, representativeness,
reliability and flexibility.
5. Identifying the parameters of interest (what type of
population characteristic the researcher wants to study i.e.,
whether proportion, mean, variation… affects the sample
design to be selected).
6. Determining the Budgetary Constraints (cost consideration
has effect not only on the size of the sample but also on
overall sample design to be pursued).
7. Determining the Sampling Procedure (what type of sample is
to be used that can minimize the sampling error).
45 QUOTA SAMPLING

 The population is first segmented into mutually exclusive sub-groups, just as in stratified

sampling.

 Then judgment used to select subjects or units from each segment based on a specified
proportion.

 For example, an interviewer may be told to sample 200 females and 300 males between
the age of 45 and 60.

 It is this second step which makes the technique one of non-probability sampling.

 In quota sampling the selection of the sample is non-random.

 For example interviewers might be tempted to interview those who look most helpful. The
problem is that these samples may be biased because not everyone gets a chance of
selection. This random element is its greatest weakness and quota versus probability has
been a matter of controversy for many years
 SIMPLE RANDOM SAMPLING

48

• Applicable when population is small,

homogeneous & readily available
• All subsets of the frame are given an equal
probability. Each element of the frame thus
has an equal probability of selection.
• It provides for greatest number of possible
samples. This is done by assigning a number to
each unit in the sampling frame.
• A table of random number or lottery system is
used to determine which units are to be
selected.
 SYSTEMATIC SAMPLING
49

 Systematic sampling relies on arranging the target population according to

some ordering scheme and then selecting elements at regular intervals
through that ordered list.

 Systematic sampling involves a random start and then proceeds with the
selection of every kth element from then onwards. In this case,
k=(population size/sample size).

 It is important that the starting point is not automatically the first in the
list, but is instead randomly chosen from within the first to the kth
element in the list.

 A simple example would be to select every 10th name from the telephone
directory (an 'every 10th' sample, also referred to as 'sampling with a skip
of 10').
 Example: In order to find the average height of the students in a school of class 1 to
class 12, the height varies a lot as the students in class 1 are of age around 6 years,
and students in class 10 are of age around 16 years. So one can divide all the students
into different subpopulations or strata such as
 Students of class 1, 2 and 3: Stratum 1 (230 students)
 Students of class 4, 5 and 6: Stratum 2 ( 300 students)
 Students of class 7, 8 and 9: Stratum 3 (350 students)
 Students of class 10, 11 and 12: Stratum 4 (250 students)
 Now draw the samples by SRS from each of the strata 1, 2, 3 and 4. All the drawn
samples combined together will constitute the final stratified sample for further analysis.
Total population is 1130, lets assume the sample size desired is 250. What will be the
sample to be chosen from each stratum proportionally?
Stratum Proportion to each
N=230 n(NI/N)=250 (230/1130)=50
N=300 250 (300/1130)=66
N=350 250 (350/1130)=77
N=250 250 (250/1130)=55
Total=1130
n=250
 Sample Size
60

 When considering collecting data, it is important to

ensure that the sample contains a sufficient number
of members of the population for adequate analysis
to take place. Larger samples will generally give
more precise information about the population.
Unfortunately, in reality, questions of expense and
time tend to limit the size of the sample.
 Size of the sample can be determined by a
researcher keeping in view the following points:
 Sample Size
61

1. Nature of the universe: Universe may be either

homogeneous or heterogeneous in nature. If the items of the
universe are homogeneous, a small sample can serve the purpose.
But if the items are heterogeneous, a large sample would be
required.
2. Number of classes proposed: If many class-groups (groups
and sub groups) are to be formed, a large sample would be
required because a small sample might not be able to give a
reasonable number of items in each class groups.
3. Nature of the study: If items are to be intensively and
continuously studied, the sample should be small. For a general
survey the size of the sample should be large, but small sample is
considered appropriate in technical surveys.
 Sample Size
62

4. Type of sampling: Sampling technique plays an

important role in determining the size of the sample.
A small random sample is apt to be much superior to
a larger but badly selected sample.
5. Standard of accuracy: If the standard of accuracy
or the level of precision is to be kept high, we shall
require relatively larger sample. For doubling the
accuracy for a fixed significance level, the sample
size has to be increased.
Research Methods in Accounting and Finance
 Level of Precision
63

 Also known as sample error,

 It is the range in which the true value of the

population is estimated to be,

 This range of often expressed in percentage points

+ve and –ve 5%
 Confidence level
64

 Also known as risk level

 Based on central limit theorem, which means when a
population is repeatedly sampled, the average
value of the attribute obtained by those samples is
equal to the true population value.
 This expressed in percentage point (95%, 90%)
 E.g. if a 95% confidence level is selected , 95% out
of 100 samples will have the true population value
within the range of precision
 Degree of variability
65

 Refers to the distribution of attributes in the

population
 The more heterogeneous a population, the larger
the size required to obtain a given level of
precision
 The less variable (more homogeneous) a population,
the smaller the sample size
66

 6. Availability of finance, trained investigators,

the condition under which the sample is being
conducted, the time available for completion of the
study are a few other considerations to which a
researcher must pay attention while selecting the
size of the sample.

Research Methods in Accounting and Finance

Strategies for determining sample
size
To determine a representative sample size from the
target population, different strategies can be used
according to the necessity of the research work.
1. Formula
2. Theory
3. Using published table
1. Formula
 Use of various formulae for determination of required sample sizes
under different situations is one of the most important strategies. There
are different formulae for determination of appropriate sample size
when different techniques of sampling are used. Formulae for
determining representative sample size when simple random sampling
technique is used. Simple random sampling is the most common and the
simplest method of sampling. Each unit of the population has the equal
chance of being drawn in the sample. Therefore, it is a method of
selecting n units out of a population of size N by giving equal
probability to all units.
(a) Formula for proportions:i) Cochran’s formula for calculating
sample size when the population is infinite:


Cont’d…

Yamane’s formula for calculating
sample size

Cont’d…

Using Published table

 A third way to determine sample size is to rely on

published tables which provide the sample size
for a given set of criteria.

E.G Krejcie and Morgan (1970) sample size decision table or Malhotra in

Marketing research
Using theory
 according to Hair et al. (1998), for research focus on attitudes a sample size 200-
400 is acceptable.