Scribd
Upload
107 views

Module 5.hypothesis Testing

This document discusses various statistical hypothesis testing procedures including their characteristics, conditions, examples, and calculations. It covers topics such as the chi-square test, standard error, sampling and non-sampling errors, the t-test, and paired t-tests. The key points are hypothesis testing involves formulating and testing hypotheses, choosing an appropriate statistical test based on the data, and determining whether to reject or fail to reject the null hypothesis based on probability and critical value calculations.

Uploaded by

Sonali Singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
107 views

Module 5.hypothesis Testing

This document discusses various statistical hypothesis testing procedures including their characteristics, conditions, examples, and calculations. It covers topics such as the chi-square test, standard error, sampling and non-sampling errors, the t-test, and paired t-tests. The key points are hypothesis testing involves formulating and testing hypotheses, choosing an appropriate statistical test based on the data, and determining whether to reject or fail to reject the null hypothesis based on probability and critical value calculations.

Uploaded by

Sonali Singh
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 16

BRM

HYPOTHESIS TESTING

By
Dr. Neeraj Anand
Hypothesis Testing
Formulate H0 and H1

Select Appropriate Test


Choose Level of Significance

Collect Data and Calculate Test Statistic

Determine Probability Determine Critical


Associated with Test Value of Test Statistic
Statistic (z or t)
Determine if critical
Compare with Level
value falls into (Non)
of Significance, 
Rejection Region
Reject or Do not Reject H0

Draw Conclusion
Errors
Type I Error

 Type I error occurs when the sample results


lead to the rejection of the null hypothesis
when it is in fact true.
The probability of type I error (Alpha) is also
called the level of significance.

Type II Error
 Type II error occurs when, based on the sample
results, the null hypothesis is not rejected when it is
in fact false.

 The probability of type II error is denoted by Beta .
Unlike Alpha, which is specified by the researcher,
the magnitude of Beta depends on the actual
value of the population parameter (proportion).
A Broad Classification of
Hypothesis Tests
Hypothesis Tests

Tests of Tests of
Association- r Differences

Median/
Distributions Means Proportions Rankings- U
F,Chi-square Z,t Z,t
A Classification of Hypothesis Testing
Procedures for Examining Differences
Hypothesis Tests

Parametric Tests Non-parametric Tests


(Metric Tests) (Nonmetric Tests)

One Sample Two or More One Sample Two or More


Samples Samples
* t test * Chi-Square
* Z test * K-S
* Runs
* Binomial
Independent Paired
Samples Samples Independent Paired
* Two-Group Samples Samples
* Paired
t test t test * Chi-Square * Sign
* Z test * Mann-Whitney * Wilcoxon
* Median * McNemar
* K-S * Chi-Square
Chi-square Test

Characteristics
 It is based on frequencies
 It is applied for drawing inferences only
 It possesses additive property.
 It is a test of association and used for general
purpose.
Conditions for Chi-square
test
 There must be two sets of data (one Observed
and one Expected)
 Sample size should be same for two sets of data.
 The frequency in each cell must be at least five.
 This test is suitable for nominal data, therefore, the
cells in rows/ columns must represent categorical
variables.
 Min. sample size = 50
Examples
 Following is the
Operat- Operat-
information about
ors ors not
the number of
commit committi
operators committing
ting ng
errors and not
errors errors
committing errors
among trained and Trained 70 530
untrained operators
at a R.O.
Test effectiveness of
training in checking Untrain 155 745
errors. -ed
Standard Error

 The standard deviation of a sampling


distribution is called Standard Error (S.E).
 Examples:
a) The standard deviation (S.D) of the means
of all possible samples of the same size drawn
from a population is known as the standard
error (S.E) of the mean.

b) The standard deviation (S.D) of the


proportions of all possible samples of the
same size drawn from a population is known
as the standard error (S.E) of the proportion.
Significance of Standard
Error
 It can be used to determine the limits
of parameter values.
 It provides an idea about the
unreliability of the sample. The higher
is the value of S.E., more is the
unreliability of the sample.
 It can be used for testing hypothesis.

* S.D. deals with original values whereas S.E.


deals with statistics computed from the
samples of original values.
Sampling Errors

 Improper selection of sampling units


 Improper selection of sample items (Non-
probability sampling)
 Wrong method of estimation of sample size
 Demarcation of statistical units
Non- sampling errors

 Wrong selection of research instrument


 Incomplete questionnaire
 Knowledge and experience of researcher
 Personal bias of field investigator
 Errors committed during recording and editing the
data
 Improper selection of analytic tools
t test
t = {( x - µ)} / {s/ sq. rt. n}
When population S.D. is not known, the S.D. of sample is used.
When the two samples are drawn from different populations,
then proportion of samples is considered otherwise combined
proportion is calculated for same population.
Paired Comparison ‘t’ test
 It is used to test for comparing two related samples, generally
of small size and when variance of their population may not
be equal but distribution must be normal.
 Observations may be collected in the form of a pair –
matched pairs.
 Each observation in the one sample must be paired with an
observation in other sample.
Contd…
 Mostly it is applicable in Before and After treatment study.
Examples: New teaching method – Role Play/ Syndicate
sessions etc.
 Effectiveness of a drone in warehousing
 Effectiveness of new training method
 Effect of new electronic signal in Railways
 Impact of RFID on logistics operations
 Application of ERP/SAP/BPR/TQM/WMS/TMS etc. in any
organization.
Paired “t” test…
Procedure:
i) Formulate Null and Alternate Hypothesis
Ho: µ1 = µ2
Ha: µ1 < µ2 (One tail test)
ii) Calculate the difference Di in the scores (Before – After)
iii) Calculate ∑Di and then Avg. D
iv) Calculate ∑Di2
v) Calculate “t” test and compare with critical value of “t” test.
Vi) Accept/reject Null hypothesis.

You might also like