Scribd
Upload
166 views17 pages

Hypotheses Testing: Basic Concepts

Reject H0 if standardized sample mean or observed z value is greater than the critical value - Left tailed test Reject H0 if standardized sample mean or observed z value is less than the critical value

Uploaded by

rahul
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 PPT, PDF, TXT or read online on Scribd
166 views17 pages

Hypotheses Testing: Basic Concepts

Reject H0 if standardized sample mean or observed z value is greater than the critical value - Left tailed test Reject H0 if standardized sample mean or observed z value is less than the critical value

Uploaded by

rahul
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 PPT, PDF, TXT or read online on Scribd
You are on page 1/ 17

Hypotheses Testing

Basic Concepts
What is Hypotheses Testing
• Not used for assessing the value of the
sample statistic

• Used to analyse the difference between


sample statistic and hypothesized
population parameter
• Smaller the difference more represenattive
the sample
Steps in Hypotheses Testing
• Formulation of the hypotheses

• Selection of statistical test to be used

• Selection of significance level

• Calculation of SE of the sample statistic


and standardize the sample statistic
Steps in Hypotheses Testing
• Determining the critical value

• Comparison of the value of the sample statistic


with the critical value and identify as to whether
the value falls within the accepted or rejected
region

• Deducing conclusions
Formulation of hypotheses
• State research question in the form of a H0
and H1

• H0 there is no difference between sample


statistic and population parameter
Selection of Statistical Test to be
Used
1. Type of research questions formulated

Eg
Comparing of mean life of bulbs z-test or t
test
Questions based on frequency distribution
Chi-square test
Number of Samples
• Hypotheses testing about a single mean z-
test, t-test or Chi-square test

• Testing for differences between means


and samples – more than two samples
involved –ANOVA and Chi-square
Measurement Scales Used
• Interval scales –z and t test

• Ordinal and nominal scales – Chi-square


Other Factors
• Sample size- greater than 30 and normally
distributed –z-test

• Whether population standard deviation is


unknown and sample size is small t-test
Level of significance
• Measure of degree of risk that a
researcher might reject the null hyp when
it is true
• 5% commonly used level of sig -5%
probability that we may wrongly conclude
that there is a difference between sample
and population values
Calculating sample statistic
Involves two steps

1. Compute SE of the sample statistic

2. Use SE to standardize the sample


statistic
Determining critical values
• Critical values are determined so as to

evaluate whether the standardized value

will fall into the accepted or rejected region


Two-tailed tests
• Is a hyp test where the null hyp is rejected
when the value of the sample statistic falls
above or below the hyp population
parameter
• Acceptance region falls between two
rejection regions
• H0: U = U0
• Ha: U not equal to U0
One-tailed test
• Where the H0 is rejected when the value of
the sample statistic is < or > hyp population
parameter

• H0: U< or= U0


• Ha : U > U0
Or
H0 U > or = U0
Ha U < U0
Comparing value of the sample
statistic with the critical value
• As the boundaries are defined we need to
compare the standardized value with the
critical value

• Check whether it falls within the


acceptance region
Basis for rejection – two-tailed test
• Reject H0 if standardized sample mean or
observed z value is > than the upper
critical value or lesser than lower critical
calue
Basis for rejection – one-tailed test
• Right tailed test

You might also like