Scribd
Upload
78 views

Testing of Hypothesis

This document discusses hypothesis testing and provides information about null and alternative hypotheses, characteristics of hypotheses, the general procedure for testing hypotheses, types of errors in hypothesis testing, and different types of hypothesis tests including parametric tests, non-parametric tests, and chi-square tests. It defines key terms, outlines the steps to test a hypothesis, and notes conditions and characteristics of chi-square tests.

Uploaded by

Pavan Deshpande
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
78 views

Testing of Hypothesis

This document discusses hypothesis testing and provides information about null and alternative hypotheses, characteristics of hypotheses, the general procedure for testing hypotheses, types of errors in hypothesis testing, and different types of hypothesis tests including parametric tests, non-parametric tests, and chi-square tests. It defines key terms, outlines the steps to test a hypothesis, and notes conditions and characteristics of chi-square tests.

Uploaded by

Pavan Deshpande
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 18

TESTING OF

HYPOTHESIS
BY –
M.THAMEEM
NAMITHA
PAVAN.D
PRAMOD
HYPOTHESIS TESTING

DEFINITION: Hypothesis may be defined as a proposition or


a set of proposition set forth as an explanation for the
occurrence of some specified group of phenomena either
asserted merely as a provisional conjecture to guide some
investigation (or) accepted as highly probable in the light of
established facts.
 NULL HYPOTHESIS ( H0 ) : A
statement in which no difference (or)
effect is expected. If the null
hypothesis is not rejected, no change
will be made.

 ALTERNATIVE HYPOTHESIS ( H1
): A statement that some difference
(or ) effect is expected. Accepting the
alternative hypothesis will lead to
change in opinions (or) action.
CHARACTERIS TICS OF HYP OTHES IS
1. Hy p o t h e s is s h o u ld b e c le a r & p re c is e .
2. Hy p o t h e s is s h o u ld b e c a p a b le o f b e in g t e s t e d .
3. Hy p o t h e s is s h o u ld s t a t e re la t io n s h ip b e t w e e n
v a ria b le s .
4. Hy p o t h e s is s h o u ld b e lim it e d in s c o p e &
5. Hy p o t h e s is s h o u ld b e s t a t e d a s fa r a s p o s s ib le
in m o s t s im p le t e rm s s o t h a t t h e s a m e is
e a s ily u n d e rs t a n d a b le b y a ll c o n c e rn e d .
11. Hy p o t h e s is s h o u ld b e c o n s is t e n t w it h m o s t
kn o w n fa c t s .
12. Hy p o t h e s is s h o u ld b e a m e n a b le t o t e s t in g
w it h in a re a s o n a b le t im e .
13. Hy p o t h e s is m u s t e x p la in t h e fa c t s t h a t g iv e
GEN ERAL P ROCED URE FOR TES TIN G
HYP OTHES IS

The following steps are involved in testing hypothesis


1.Formulate the null hypothesis (HO) & the alternative
hypothesis(H1).
2.Select an appropriate statistical technique & the corresponding
test
statistic.
3.Choose the level of significance.
4.Determine the sample size &collect the data.
5.Calculate the value of the test statistics.
6. Determine the probability associated
with the test static under the null
hypothesis using the sampling
distribution of the test statistic.
7. Compare the probability associated

with the test static with the level of


significance specified.
8. Make the statistical decision to reject

or not reject the null hypothesis.


9. Express the statistical decision in

terms of the Marketing research


problem.

TES TIN G HYP OTHES IS :
Formulate H0 & H1

Select Appropriate test

Choose the level of significance

Collect data & calculate

Determine Probability Determine critical value of


Associated with test test statistics
Statistics
Determine if falls into
Compare with level of rejection (or) non
significance rejection region

Reject or don’t reject H0

Draw marketing Research


Hypothesis tests

Test of Association Test of Difference

Distribution Means proportions Medians


ERRORS IN TESTING OF
HYPOTHESIS
 There are two types of errors :
 - Type I Error
 Also known as α error.
 Reject Ho when Ho is true.

 - Type II Error
 Also known as β (Beta) error.
 Accepts Ho when Ho is not true.

Decision
Accept Ho Reject Ho
Ho(true) Correct Decision Type I Error
(α
Ho(false) Type II Error Ε rror) Decision
Correct
(β
Error)
α & β Have an
Inverse Relationship
Reduce probability of one error
and the other one goes up.

α
TESTS OF HYPOTHESES
 Tests are classified into two types :

- Parametric Tests or standard tests of


hypotheses

 - Non- Parametric Tests or distribution-


free tests of hypotheses


PARAMETRIC TESTS
It usually assume certain properties of the parent
population from which we draw samples.
 t- test : It is based on t-distribution.
 It is used when sample is small and variance is not
known.
 T= X - µ

sx
 Z- test :It is based on normal probability
distribution. It is used in case of large sample or
when variance is known. It is used for judging
the significance of median,mode, correlation
etc.
X

z = ( -µ)
I

O / √n

 F-test : is based on f-distribution. It is used to


compare the variance of the two independent
samples.
NON – PARAMETRIC TEST:
Chi- square test:

۩
. The chi-square test is the important one amongst the several tests of

significance developed by statisticians.

۩
. Chi-square symbolically written as X2 ( Ki-square ) .

۩
. It is the statistical measure used in the sampling analysis for

comparing variance to a theoretical variance.

۩
. As a non- parametric test it can be used to determine if categorical

data shows dependency.

۩
. It can also used to make comparison between theoretical population &

actual data when categories are used.


APPLICATION:
1.Test the goodness fit.
2.Test the significance between two attributes.
3.Test of homogeneity (or) significance of population variance.

FORMS & TERMS USED:


Null hypothesis: HO
HO: There is no difference
Alternative hypothesis: H1 Between the perceived
quality of two samples
Expected frequency: Fe
Observed frequency: Fo H1: There is difference
Between the perceived
nr: Total number in row Quality of two samples.
nc: Total number in column
n: Total sample size
NOTE:
1.It may be either accept (or) reject the null hypothesis
2

2.If the calculated value of X is less than the table value, the null
hypothesis is accepted.

3. But If the calculated value is equal (or) greater than the table value, the
hypothesis is rejected.

Expected frequency: nr=row number


Fe= nr nc /n nc=column number
n=total sample size
2 2
X = ∑ (O- E)

n
CONDITIONS FOR THE APPLICATION OF X2 TEST:
1. observations recorded & used are collected on a random basis.
2.All the sample must be independent.
3.No group should contain very few items.
4.The overall number of items must also be reasonably large. It should be at least 50.
5.The constraints must be linear, the equations containing no squares or powers of the frequency.
CHARACTERISTICS OF X2 TEST:
1.This test is based on frequencies& not on the parameters like mean & standard deviation.
2.The test is used for testing the hypothesis & not useful for estimation.
3.This test possess additive property.
4.This can also be applied to a complex contingency –useful in research work.
5.This is an important non parametric test.

1.
CAUTIONS IN USING X 2 TEST:
i.Neglect of frequencies of non occurrence.
ii.Failure to equalize the sum of observed & the sum of expected frequencies
iii.Wrong determination of the degree of freedom.
iv.Wrong computation.

You might also like