Scribd
Upload
13 views9 pages

Lec3 1

The document provides an overview of the basics of hypothesis testing, including key concepts such as null and alternate hypotheses, test statistics, and rejection criteria. It outlines a general procedure for hypothesis testing and presents an example involving a random number generator to illustrate the process. The learning objectives include understanding errors in hypothesis testing, significance levels, and p-values.

Uploaded by

MURALI K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
13 views9 pages

Lec3 1

The document provides an overview of the basics of hypothesis testing, including key concepts such as null and alternate hypotheses, test statistics, and rejection criteria. It outlines a general procedure for hypothesis testing and presents an example involving a random number generator to illustrate the process. The learning objectives include understanding errors in hypothesis testing, significance levels, and p-values.

Uploaded by

MURALI K
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

Basics of Hypothesis Testing References

Introduction to Statistical Hypothesis Testing

Arun K. Tangirala

Basics of Hypothesis Testing

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 1


Basics of Hypothesis Testing References

Learning objectives

I Basic concepts
I Errors in hypothesis testing
I Significance level
I p-value

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 2


Basics of Hypothesis Testing References

Recap: General procedure

1. Identify parameters of interest ✓: Average, variability, correlation, etc. X

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 3


Basics of Hypothesis Testing References

Recap: General procedure

1. Identify parameters of interest ✓: Average, variability, correlation, etc. X


2. State the null and alternate hypothesis H0 : X

equal, identical at least, at most, 


H0 : Null Hypothesis
test: = test: = test: =
unequal strictly less than strictly more than
Ha : Alternate Hypothesis
6= < >
Two-tailed (Left) Lower-tailed (Right) Upper-tailed
Type of test
Cri.cal(region( Cri.cal(region( Cri$cal(region( Cri$cal(region(

Acceptance(region((

Note: H0 is always specified as equality type for testing purposes, regardless of the actual statement.

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 4


Basics of Hypothesis Testing References

Recap: General procedure

3. Test statistic: QT Construct a mathematical function of the observations and the parameter(s)
under examination. X

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 5


Basics of Hypothesis Testing References

Recap: General procedure

3. Test statistic: QT Construct a mathematical function of the observations and the parameter(s)
under examination. X
4. Sampling distribution: Obtain the probability density or mass function of the test statistic. X

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 6


Basics of Hypothesis Testing References

Recap: General procedure

3. Test statistic: QT Construct a mathematical function of the observations and the parameter(s)
under examination. X
4. Sampling distribution: Obtain the probability density or mass function of the test statistic. X
5. Set the rejection criterion: Rc Choose an appropriate criterion,essentially a critical value for the
test statistic. Usually specified as the level of acceptable error (in the test).

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 7


Basics of Hypothesis Testing References

Recap: General procedure

3. Test statistic: QT Construct a mathematical function of the observations and the parameter(s)
under examination. X
4. Sampling distribution: Obtain the probability density or mass function of the test statistic. X
5. Set the rejection criterion: Rc Choose an appropriate criterion,essentially a critical value for the
test statistic. Usually specified as the level of acceptable error (in the test).
6. Decision: Compute the test statistic and apply the rejection criteria. If the test statistic falls into
the “rejection region”, reject H0 in favour of Ha .

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 8


Basics of Hypothesis Testing References

Example: Random number generator

A random number generator claims to produce random numbers from a population of zero mean and
unit variance.

Goal: To test that the population has zero mean with known variance 2
= 1.

Assumptions: Random sample, large sample size

1. Hypothesis: H0 : µ = 0, Ha : µ 6= 0.
(X̄ µ)
2. Test statistic: Z = p
/ n
3. Rejection criterion: Choose two critical values zc,r and zc,l (on both sides of postulated value).
4. Decision: Reject H0 if observed statistic zo > zc,r or zo < zc,l .

To be illustrated in R.

Arun K. Tangirala, IIT Madras Intro to Statistical Hypothesis Testing 9

You might also like