# HYPOTHESIS TESTING

Presented by, Divyamathi T. I MBA

DEFINITION

Hypothesis : Statement that may be judged as true of false. Hypothesis Testing : The process of testing sample data from a statistical study to determine whether it is consistent with what is known about the sample population.

RESEARCH QUESTION
 Usually

posed in the beginning of a research

effort
 Basic

phenomena or a question about the relationship between two or more variables.

RESEARCH Q.

HYPOTHESIS

Eg. For research Q.
 "Do

flexible work hours improve employee do flexible hours influence employees'

productivity?“
 "How

work?"

The corresponding Hypothesis
 “Flexible

work hours improve employee

productivity.” (True or False / Accept or Reject)

BENEFITS OF HYPOTHESIS

Determine the focus & direction for a research effort. Development of a hypothesis forces the researcher to clearly state the purpose of the research activity.

Determine what variables will not be considered in a study, as well as those that will be considered.

GOOD HYPOTHESIS SHOULD BE:
 Logically  Be

consistent

in step with the current literature

and/or provide a good basis for any differences.
 Be  Be

testable. stated in clear & simple terms in order

to reduce confusion.

TYPES OF HYPOTHESIS
Descriptive Relational

Hypothesis
Hypothesis

Hypothesis

Correlational Causal

hypothesis

TYPES OF HYPOTHESIS TESTS

PARAMETRIC TESTS
  

More powerful test Uses interval and ratio data

From independent observations  Uses statistical hypothesis testing  Z- test  T- test  F-test test  ANOVA
X
2

NON – PARAMETRIC TESTS
 Nominal

& Ordinal data as well as related cases

 Independent  Also  Easy

uses interval & ratio data to understand & use

NON – PARAMETRIC TESTS
For Nominal Data:
 Binomial

For Ordinal Data:

or X 2 test

Konglomorov-Smirmov test Runs test test

(1 sample & 2 sample case)
 McNemar  Fish

test

 Sign
 

exact test Q test

Mann-Whitney U test Kruskal-Wallis test

 Cochran