Module - 4

Data Processing and Testing

PowerPoint Slides by
Mustafa Haider Maldar
KUD Kousali Institute of Management
Studies
 Chapter Outline
• Dependent and Independent variables
• Measurement scales
• Tabulation (Coding Sheet) and analysis of data
• Correlation & regression
• Parametric & Non-Parametric Tests
• Basic concepts, Type-I & Type II errors
• Hypothesis testing for means and proportions
for small and large samples
 Chapter Outline
• Statistical calculations using SPSS:
• Creating a Data File
• Defining Variables & data
• Frequencies, Crosstabs
• Hypothesis Testing Reliability test (and above
tests)
• factor analysis
• Chi- square test for goodness of fits and
independence
 Chapter Outline
• Statistical calculations using SPSS:
• T-Test, Z-Test, F-Test, U-Test
• Kruskal-Wallis Test
• Mann-Whitney U Test
• Wilcoxon
• Multivariate analysis ANOVA one way and two
way classification
 Dependent and Independent Variable
• Variables are things you measure ,manipulate
and control in research
• A measurable characteristics that varies
• It may change from person to person or even
within one person over time
• Example –Age , height, temperature etc
 Dependent and Independent Variable
• Independent Variable – A dependent variable relies
on and can be changed by the manipulation of an
independent variable.
• Research has control over such variable .
• Dependent Variable – The research observe the
change in DV.
• shows the effect of manipulating independent
variable.
• It is in the form of cause and effect .
• Example - Coffee and sleep
 Dependent and Independent Variable
• Cause ----- Effect
• IV ----------DV
• Coffee ----- Sleep
• IV ---------------------DV
• Manipulation------- Observe
Dependent and Independent Variable
 Intervening and Control Variable
• Intervening variable - Not observable but like
dependent and independent variable.
• Example - fan regulator

• Control variable – Must be held in constant.

• Example – Teacher and students

 Intervening and Control Variable
• Intervening variable - Not observable but like
dependent and independent variable.
• Example - fan regulator

• Control variable – Must be held in constant.

• Example – Teacher and students

 Intervening and Control Variable
• Intervening variable - Not observable but like
dependent and independent variable.
• Example - fan regulator

• Control variable – Must be held in constant.

• Example – Teacher and students

 Intervening and Control Variable
• Intervening variable - Not observable but like
dependent and independent variable.
• Example - fan regulator

• Control variable – Must be held in constant.

• Example – Teacher and students
 Extraneous Variable
• These are factors that affect the DV but that
the researchers did not originally consider
when designing the experiment.
• These are unwanted variables can
unintentionally change a study results or how
a researcher interprets those results.
 Measurement of Scales
• We can measure physical objects as well as
abstract concepts.
• It is relatively complex and demanding task ,
when qualitative or abstract phenomena.
• Examples – honesty , intelligence , customer
perception and brand loyalty etc.
• These characteristics are also called as
constructs.
 Measurement of Scales
• Measurement is defined as a process of
associating numbers or symbols to
observations obtained in a research study.
• Observation could be qualitative or
quantitative.
• Quantitative data analysis can be done by
Mean , median, mode , standard deviation etc.
 Measurement of Scales
• Qualitative characteristics can be counted and
cannot be computed.
• For example : We can record a person
marital status as 1,2,3 or 4 depending on
whether the person is single, married ,
widowed or divorced.
• We can ask Yes or No
Types of Measurement Data
Types of Measurement Data
Types of Measurement of Scales
 Types of Measurement of Scales
• Classification of measurement Scales are
mention below
• Nominal Scale
• Ordinal Scale
• Interval Scale
• Ratio Scale
 Nominal Scale
• It is a system of assigning number symbols to
events in order to label them.
• The numbers are just used convenient labels
for the particular class of events and as such
have no quantitative value.
• It helps in keeping track of people, objects and
events.
• Nominal Scale is the least powerful level of
measurement.
 Nominal Scale
• It indicates no order or distance relationship
and has no arithmetic origin.
• Varying degrees of attitudes, skills,
understanding etc.
• It is used in survey methods where in surveys.
• Nominal data is numerical in name only .
• Examples – Martial Status as 1,2,3,4 we
cannot write 4>2 , 3<4 or 3-1 = 4-2.
 Ordinal Scale
• The ordinal scale places events in order, but there is no
attempt to make intervals of the scale equal in terms of
some rule.
• Rank order represent ordinal scales and are frequently
used in research relating to qualitative phenomena.
• Example - if Ram’s position in his class is 10 and Mohan’s
position is 40, it cannot be said that
• Ram’s position is four times as good as that of Mohan. The
statement would make no sense at all.
• Ordinal scales only permit the ranking of items from
highest to lowest.
 Ordinal Scale
• Thus, the use of an ordinal scale implies a
statement of ‘greater than’ or ‘less than’ (an
equality
• statement is also acceptable) without our being
able to state how much greater or less.
• We cannot do anything except set up inequalities,
we refer to data as ordinal data.
• Example – If one mineral can scratch another, it
receives a higher hardness number on of Mohs
scale from 1- 10 , 5>2 , 3<4.
 Interval Scale
• In the case of interval scale, the intervals are
adjusted in terms of some rule that has been
established as a basis for making the units
equal.
• Interval scales provide more powerful
measurement than ordinal scales for interval
scale also incorporates the concept of equality
of interval
 Interval Scale
• Addition to setting up the inequalities we can
also form difference, we refer these data as
interval data.
• Examples – temperature readings 58*, 63*,
70*, 95*, 110*, 126* and 136*
• 110* >70* , 95* < 126*.
 Ratio Scale
• Ratio scales have an absolute or true zero of
measurement.
• The term ‘absolute zero’ is not as precise as it was
once believed to be.
• For example, the zero point on a centimeter scale
indicates the complete absence of length or height.
• But an absolute zero of temperature is theoretically
unobtainable and it remains a concept existing only
in the scientist’s mind.
 Ratio Scale
• Ratio scale represents the actual amounts of
variables
• Measures of physical dimensions such as
• weight, height, distance, etc. are examples.
Generally, all statistical techniques are usable
with ratio scales and all manipulations that
one can carry out with real numbers can also
be carried out with ratio scale values
 Ratio Scale
• Proceeding from the nominal scale (the least
precise type of scale) to ratio scale (the most
precise), relevant information is obtained
increasingly. If the nature of the variables permits,
the researcher should use the scale that provides
the most precise description.
• When addition to setting up inequalities and
forming difference we can also form quotients
(operation of mathematics). We refer to such data
as ratio data.
Measurement of scales
Types of Measurement of scales
 Hypothesis
• A hypothesis is an assumption, an idea that is
proposed for the sake of argument so that it
can be tested to see if it might be true.
• A statistical hypothesis is a claim ( assertion,
statement, belief or assumption) about an
unknown population parameter value.
 Hypothesis
• Example – A judge assumes that a person
charged with a crime is innocent and subject
this assumption ( hypothesis) to a verification
by reviewing the evidence and hearing
testimony before reaching to a verdict.
 Hypothesis Testing
• A hypothesis is a statement to be tested about
the true value of population parameter using
sample statistics.
• To test the validity of the claim or assumption
about the population parameter
 A sample is drawn from the population and
analyzed.
 The results of the analysis are used to decide
whether the claim is true or not.
 Hypothesis Terminology
• Null hypothesis (H0) and Alternative
Hypothesis (H1) –
• Null hypothesis – There is no significant
difference between the population specified in
the experiments, due to any experimental or
sampling error. The null hypothesis is denoted
by H0.
 Hypothesis Testing
• Alternative Hypothesis – In an alternative
hypothesis , the simple observation are easily
influenced by some random cause. It is
denoted by Ha or H1.
• Classroom of 100 students average
percentage is 70 %.
• Sample of 20 students average percentage is
71 %.
Hypothesis Testing
 Hypothesis Testing
• Solution :
• Null Hypothesis – There is no significant
difference the lifetime of sample and
population.
• Alternative Hypothesis – There is significant
difference between the lifetime of sample and
population.
 Procedure for Hypothesis Testing
• Step 1 – Set up a hypothesis - H0 or H1 or Ha
• Step 2 - Set up a significance level – 0.1% ,
1% , 5 % , 10 %.
• Setting a Test Criteria - z test , t test , chi –
square test , f test.
• Doing Computation – Calculation
• Making Decision -
Procedure for Hypothesis Testing
 Procedure for Hypothesis Testing
• Step 2 : Set – up a Significance Level –
• p + q = 1,
• p = Probability of Occurrence ( Wrong
decision)
• q = Probability of Non – Occurrence ( Right
Decision)
Procedure for Hypothesis Testing
Procedure for Hypothesis Testing
Procedure for Hypothesis Testing
Procedure for Hypothesis Testing
Classification of Hypothesis Testing
• Hypothesis Testing –
• Parametric Tests – Parametric test is a kind of
the hypothesis test which gives generalization
s for generating records regarding the mean of
the primary / original population.
• This is often the assumption that the
population data are normally distributed.
• These test are considered for Quantitative
research
Classification of Hypothesis Testing
• Non – Parametric Tests –
• The non – parametric test does not require any
population distribution, which is meant by
distinct parameters.
• Non – parametric tests makes no assumption
about the probability distributions of the
observations.
• These test are considered for Qualitative
research
Difference between Hypothesis Testing
Classification of Hypothesis Testing
• Parametric Test –
• Z – Test (>= 30 Sample)(Sample mean data is
required (x) and S.D. of the population should
be known ).
• t – Test (< 30 sample)(Comparison of two
sample mean )
• Unpaired t – Test ( Independent variables )
• Paired t – Test (Dependent variable )
Classification of Hypothesis Testing
• Parametric Test –
• F – Test (comparing variance of population
and sample )
• ANOVA ( Comparing more than two sample
mean )
Classification of Hypothesis Testing
• Non - Parametric Test –
• Goodness of Fit Tests (The distribution of the
variable being analyzed is the same as
hypothetical tests).
• Chi – square Test
• Shapiro – Wilk Test
• Anderson – Darling Test
• Kuiper ‘s Test
• Hosmer – Lemeshow Test
Classification of Hypothesis Testing
• Non - Parametric Test –
• Tests for Independence ( Rows and columns
of variables being tested are independent )
• Chi - square Test
• Fisher’s Exact Test
Classification of Hypothesis Testing
• Non - Parametric Test –
• Test for Homogeneity – ( the variables being
analyzed are distributed equally )
• Chi – square Test
• Wilcoxon Rank Test
• Mann-Whitney U Test
• Kruskal-Wallis Test
• Freidmann Test
• Levene Test
 Z – test
• Z – Test ( Test of Significance of Attributes ) –
• Appearance of selected “Attribute” – Success
• Non – Appearance of selected “Attribute” –
Failure.
Test for Number of Successes
Test for Proportion of Successes
Test for Difference between Proportions
 Test for Number of Successes
• Statistical data testing
• Variable – Quantitative Estimation of
Phenomenon
• Attributes – Possibility ( Chances )
Test for Number of Successes
Test for Number of Successes
Test for Number of Successes
Test for Proportion of Successes
Test for Proportion of Successes
Test for Difference between Proportions