VARIABLES

A Variable is any characteristic or

quantity that varies among the
members of a particular group.
Example:
 Gender
 Height
 Length
 Interest
 CONSTANT
• A Constant is a characteristic or
quantity that is constant for all
members of a particular group.
• Any variable could be made into
a constant.
 TYPES OF VARIABLES
• Quantitative variable: This varies in amount
and degree but not in kind.
Example:
• Height, length, interest

• Categorical variable: This varies only in

kind, not in degree or amount (quantitatively
different)
Example
• Gender, Occupation
 Relationship
• Researchers in social sciences and
education often study the relationship
among/either:
• 1. Two or more quantitative variables
• 2. One categorical one quantitative variables
• 3. Two or more categorical variables
Some variables can be treated both as
quantitative and categorical variables
 INDEPENDENT VARIABLE

Independent variable are

presumed to influence other
variables. They are
sometimes called manipulating
variables or experimental
variables
 DEPENDENT VARIABLE
• A Dependent variable is
presumed to be affected by
one or more independent
variable.
• The dependent variable is
often called an outcome
variable
 DATA ANALYSIS
This refers to techniques whereby the
researcher extract from the study
information which will
 * enable a summary description of
the subject studied to be made.
 * enable us answer research
questions and/or test research
hypothesis
TWO METHODS USED FOR DATA ANALYSIS
* DESCRIPTIVE STATISTICS
* INFERENTIAL STATISTICS

DESCRIPTIVE STATISTIC aimed at describing

characteristics of the group or groups
*SIMPLEST METHOD OF ANALYSIS
*PROVIDE A GENERAL OVERVIEW OF
THE RESULTS
• INVOLVES ANALYSIS OF QUESTIONNAIRE
RESPONSES IN THE FORM OF :
– PERCENTAGES
– FREQUENCY DISTRIBUTION
– BAR CHART
– PIE CHART
– HISTOGRAMME
– MEASUREMENT OF CENTRAL TENDENCY
– MEAN
– MODE
– MIDEAN
– MEASUREMENT OF DISPERSION
– MEAN DEVIATION
– STANDARD DEVIATION
 INFERENTIAL STATISTICS
Deals with INFERENCE or
GENERALISATION about the
characteristics of a population based
on the behaviour of the sample.

Enables conclusion to be made about

a population of which the data
collected represents only a sample
 Factors which determine
inferential statistics to adopt
• Scale of measurement

• Method of subject selection

• The number of groups

• The number of independent variables

 SCALES OF MEASUREMENT
• Scales of Measurement in a nutshell refers to
various measures of the variables researchers
use in their research.
• The type of measure determine the kind of test
to be used for data analysis.
• There are FOUR forms of measurement used
in questionnaire surveys
• Nominal
• Ordinal
• Interval
• Ratio
 PROPERTIES OF SCALE OF
MEASUREMENT
• The process of measurement involves
assigning numbers to observations according
to rules
• Each scale of measurement represents a
particular property or set of properties of the
abstract number system
• The properties of the abstract number system
that are relevant to scales of measurement
are: identity, magnitude, equal interval, and
absolute/true zero.
 NOMINAL SCALES
The lowest measurement level you
can use, from a statistical point of
view.
used to categorise responses into
groups without any order or structure.
Example:
What is your gender?
Male1 Female2

Do you use computer to help manage your maintenance work?

Yes1 No2
14
 Nominal scale cont.
• PROPERTY: The number assigned to nominal
scale are just for the sake of identification and
the numbers itself cannot be used in
mathematical operations.
• Statistical Tools:
Mode
Cross tabulation - with chi-square
There are also highly sophisticated modelling
techniques available for nominal data.
 ORDINAL SCALE
 An ordinal scale is next up the list in terms of
power of measurement
 The simplest ordinal scale is a ranking
 An ordinal scale only lets you interpret gross
order and not the relative positional distances.
Example:
 Socioeconomic status
 Class
 Grades
 preferences
 Ordinal scale cont.
Example:
What is your position in class?
• First1
• Second2
• Third3
• Last4
PROPERTY: Identification and Magnitude
Here the values of the variable have numbers for
identification but also the values have some order
 Ordinal scale cont.
• Statistical Tools:
Ordinal data would use non-parametric statistics.
These would include:
Median and mode
rank order correlation
non-parametric analysis of variance
Modelling techniques can also be used with
ordinal data.
 INTERVAL SCALES
• The standard survey rating scale is an interval
scale
• used when the distances between intervals are
known (or assumed)
Example:
Temperature measurement in either
Centigrade or Fahrenheit is an example of an
interval scale.
One can talk of a 10oC rise in temperature but not
that 10oC is 10 times hotter than 1oC

Interval scale do not have a true Zero

 INTERVAL SCALES cont.

In Most business researches Likert Scale

variables are taken as having equal interval
When you are asked to rate your satisfaction
with a piece of software on a 7 point scale,
from Dissatisfied to Satisfied, you are using an
interval scale. (Because it is assumed to have
equidistant points between each of the scale in
contrast with ordinal scale that establish differences
in order)

• PROPERTY: Identification, Magnitude and Equal

Intervals.
 INTERVAL SCALES cont
STATISTICS: Interval scale use parametric
statistical techniques:
 Mean and standard deviation
 Correlation - r
 Regression
 Analysis of variance
 Factor analysis
 Plus a whole range of advanced multivariate
and modelling techniques
 RATIO SCALES
• Ratio scale have all the properties of nominal,
ordinal and interval scales. In addition, it has
absolute zero.
Example:
• Weight
• Height
• Time
• Distance
– 10 miles is twice as long as 5 miles. 0 mile is no
distance
 RATIO SCALES Cont.
• PROPERTY: Identification, Magnitude Equal
Intervals and Absolute/true zero
• RANG OF STATISTICS:
• The same as for Interval data
• The most important things to
remember when selecting a
scale of measurement are
• its appropriateness to the
variable being tested
• the range of statistical
techniques which you wish to
use in your analysis.

24
 METHOD OF SUBJECT
SELECTION
Sometimes, the entire population
will be sufficiently small, and the
researcher can include the entire
population in the study. This type
of research is called a census
study because data is gathered
on every member of the
population.
Usually, the population is too
large for the researcher to
attempt to survey all of its
members. A small, but carefully
chosen sample can be used to
represent the population. The
sample reflects the
characteristics of the population
from which it is drawn.
 SAMPLING METHODS
PROBABILITY SAMPLING
Each member of the population
has a probability of being
selected. Probability methods
include
Random sampling
Systematic sampling
Stratified sampling.
NON PROBABILITY SAMPLING
members are selected from the
population in some nonrandom
manner. These include
Convenience sampling
Judgment sampling
Quota sampling, and
Snowball sampling.
The advantage of probability sampling
is that sampling error can be
calculated. Sampling error is the
degree to which a sample might differ
from the population. When inferring to
the population, results are reported
plus or minus the sampling error. In
non probability sampling, the degree
to which the sample differs from the
population remains unknown.
 RANDOM SAMPLING
Random sampling is the purest form of
probability sampling. Each member of
the population has an equal and
known chance of being selected. When
there are very large populations, it is
often difficult or impossible to identify
every member of the population, so the
pool of available subjects becomes
biased.
 SYSTEMATIC SAMPLING
Systematic sampling is often used instead of
random sampling. It is also called an Nth name
selection technique. After the required sample
size has been calculated, every Nth record is
selected from a list of population members. As
long as the list does not contain any hidden
order, this sampling method is as good as the
random sampling method. Its only advantage
over the random sampling technique is
simplicity.
 STRATIFIED SAMPLING
Stratified sampling is commonly used
probability method that is superior to
random sampling because it reduces
sampling error.
A stratum is a subset of the population that
share at least one common characteristic.
The researcher first identifies the relevant
stratums and their actual representation in
the population. Random sampling is then
used to select subjects from each stratum.
 CONVENIENCE SAMPLING
Convenience sampling is used in
exploratory research where the
researcher is interested in getting an
inexpensive approximation of the truth.
As the name implies, the sample is
selected because they are convenient.
This non probability method is often
used during preliminary research efforts
to get a gross estimate of the results,
without incurring the cost or time
required to select a random sample.
 JUDGMENT SAMPLING
Judgment sampling is a common non
probability method. The researcher selects
the sample based on judgment. This is
usually and extension of convenience
sampling. For example, a researcher may
decide to draw the entire sample from one
"representative" city, even though the
population includes all cities. When using this
method, the researcher must be confident
that the chosen sample is truly
representative of the entire population.
 QUOTA SAMPLING
Quota sampling is the non probability
equivalent of stratified sampling. Like
stratified sampling, the researcher first
identifies the stratums and their
proportions as they are represented in the
population. Then convenience or judgment
sampling is used to select the required
number of subjects from each stratum.
This differs from stratified sampling, where
the stratums are filled by random
sampling.
 SNOWBALL SAMPLING
Snowball sampling is a special non probability
method used when the desired sample
characteristic is rare. It may be extremely difficult
or cost prohibitive to locate respondents in these
situations. Snowball sampling relies on referrals
from initial subjects to generate additional
subjects. While this technique can dramatically
lower search costs, it comes at the expense of
introducing bias because the technique itself
reduces the likelihood that the sample will
represent a good cross section from the
population.
 TYPES OF TESTS
• NON-PARAMETRIC TEST : Used for data
set comprising more than TWO sets of
variables. It comprises:
– Kruskal – Wallis H test
– Chi – Square
– Wilcoxon Match-pairs signed test
– Friedman two-way analysis of variance
• PARAMETRIC TEST

• ANOVA: One –way and Two-way

• T-test

• Z-test

• F-test
• Visit https://explorable.com for further studies
 T-TEST
T-test is used to test the significance of
difference b/w two sample means
Example, difference in mathematics scores b/w
two groups of students taught by different
teachers
 APPROPRIATE STATISTICS
ANOVA
The Analysis Of Variance, popularly
known as the ANOVA, can be used to
compare the mean of more than two
groups.
There are two types of ANOVA test:
* One-way ANOVA
* Two-way ANOVA
A One-Way ANOVA (Analysis of Variance) is a
statistical technique by which we can test if
three or more means are equal. It tests if the
value of a single variable differs significantly
among three or more levels of a factor.
Example: Let us suppose that the Human
Resources Department of a company desires
to know if occupational stress varies according
to age.
The variable of interest is occupational stress
as measured by a scale.
The factor being studied is age. There is just
one factor (age) and hence a situation
appropriate for one-way ANOVA.
Further suppose that the employees have been
classified into three groups (levels):
less than 40
40 to 55
above 55
These three groups are the levels of factor age
Non-significance of the test statistic (F-statistic) associated with this
technique would imply that age has no effect on stress experienced by
employees in their respective occupations. On the other hand, significance
would imply that stress afflicts different age groups differently.
A Two-Way ANOVA is useful when we desire
to compare the effect of multiple levels of two
factors and we have multiple observations at
each level.

One-Way ANOVA compares three or more

levels of one factor. But some experiments
involve two factors each with multiple levels in
which case it is appropriate to use
Two-Way ANOVA.
Example of two-way ANOVA:
FACTOR LEVEL
1. Age less than 40
40 to 55
above 55
2. Gender Male
Female
In this design, factor “age” has three levels and
“gender” two. In all, there are 3 x 2 = 6 groups
or cells. With this layout, we obtain scores on
occupational stress from employee(s)
belonging to the six cells.
 F-statistics
• Any statistical test that uses
F-distribution can be called an F-test. It
is used when the sample size is small
i.e. n < 30.
• Example: suppose one is interested to
test if there is any significant difference
between the mean height of male and
female students in a particular college. In
such a situation, t-test for difference of
means can be applied.
 However one assumption of t-test is that the
variance of the two populations is equal

Unless this assumption is true in the case of the

population of heights of male and female
students. the t-test for difference of means
cannot be carried out.

The F-test can be used to test the hypothesis

that the population variances are equal.
F-test is performed to test the significance
of the difference b/w two sample variance
 F-test's for Different Purposes
There are different types of F-tests
each for different purpose. Some of
the popular types are outlined below:
1. F-test for testing equality of
variance is used to test the hypothesis
of equality of two population
variances. The example considered
above requires the application of this
test.
2.F-test for testing equality of several
means. Test for equality of several
means is carried out by the technique
named ANOVA. For example suppose
that the efficacy of a drug is sought to
be tested at three levels say 100mg,
250mg and 500mg. A test is conducted
among fifteen human subjects taken at
random- with five subjects being
administered each level of the drug.
To test if there are significant
differences among the three levels
of the drug in terms of efficacy, the
ANOVA technique has to be
applied. The test used for this
purpose is the F-test.
Example 2: to test if significant difference exist
in the productivity of French, German and
Chinese contractors, ANOVA technique is used
F-test for testing significance of
regression is used to test the
significance of the regression model.
The appropriateness of the
multiple regression model as a whole
can be tested by this test. A
significant F indicates a linear
relationship between Y and at least
one of the X's.
 Assumptions
Irrespective of the type of F-test used, one
assumption has to be met.
•The populations from which the samples are
drawn have to be normal.
•In the case of F-test for equality of variance, a
second assumption has to be satisfied in that
the larger of the sample variances has to be
placed in the numerator of the test statistic.
• Inferential analysis is used for carrying out a
statistical significance test.
• SOME TESTS ARE APPROPRIATE IN
TESTING DIFFERENCES IN SCORES –
• T-test for comparing diff. in mean
• Chi-Square for diff./association b/w 2
sets of data
• Some are suitable for assessing whether two
sets of scores are CORRELATED
• Correlation coefficient for test of strength
of relationship
 Hypothesis testing
• Hypothesis may be stated in the form of:
– There is no significant difference
between (variables)
– There is no association ’’ ’’
– There is no relationship ’’ ’’
Hypothesis must be stated in a null
form
• The null hypothesis is the antithesis of
your research hypothesis, e.g.
• Suppose research question states “is there
any difference in cost b/w project delivered
under the Traditional contract & similar
project under Design & Build” with mean
score for cost of project under traditional as
X1 & D&B as X2,
– Then research hypothesis H1 : X1>X2
» Or H1 : X1<X2
– Null hypothesis H0: X1 = X2 meaning that
there is no difference in the mean cost
between Traditional and D&B projects
 STEPS TO CONSIDER B4 & AFTER
INFERENTIAL STATISTICAL TEST
BEFORE TEST
• 1) Formulate your research hypothesis
(predicted results)
• 2) State the null hypothesis

• 3) Decide which test to use

• Parametric test (e.g. ANOVA, T-test, Z-test)
• Non-parametric test (e.g. Chi-square test, Mann-whitney u-test,
Kruskal-Wallis H- test, Wilcoxon Match-pairs signed test)
• 4) Calculate & obtain test statistics
• Parametric test
• Non-parametric test
AFTER THE TEST
• Decide whether result is significant
• Accept H0 if calc. figure < tabulated critical value
(hence result is not significant)
• Reject H0 if calc. value > tabulated critical value
(hence result is significant)
– Normally significance levels are set at 95% or 99%
(i.e. levels of confidence).
 Comparing means
• Common methods for comparing two samples involve:
– independent sample t-tests (for interval data) where
no relationship exist amongst the data sets e.g. STATE
VS FEDERAL POLY;
– paired sample t-test, where a relationship does exist,
i.e. a single data set is tested for difference between
response to two questions STATE POLY (NON-
ACADEMIC VS ACADEMIC STAFF)
– Mann-Whitney tests (for ordinal i.e. ranked data), and
– for more than two sets of data (i.e. French, German
and UK contractors) Analysis of Variance (ANOVA).
 Association
• Investigating association (i.e. the opposite to that discussed
previously)
– commonly described as the degree of association. For example
between the rankings provided by contractors and architects.
– Can be positive and negative.
– Correlation coefficient has a range of zero to 1.0.
– Zero represents no correlation, 1.0 represents perfect
correlation.
– Statistical significance takes on the same meaning.
– Spearmans Rank Correlation test used for ORDINAL I.E.
RANKED data
– Pearson Correlation test used for INTERVAL DATA
 Statistical Prediction
• The theme of level of association can be expanded to
predict the output of something (the dependent variable)
based upon an input (the independent variable(s))
• Simple linear regression used where only two variables
are considered.
• Dependent variable (designated y) is predicted from the
value of the independent variable (designated x).
• E.g. Two sets of data: time taken to design a house, and
size of house.
• By applying a simple linear regression to these data an
equation will be derived in the form:
 Statistical Prediction
Y = c + c1 (x)

where y = the predicted design time;

c is a constant
c1 is the regression coefficient
x is the floor area
• Hence, we may employ the equation and insert any value
of x (floor area) to predict y (design time)
• See also multiple regression for dealing with multiple
independent variables