Scribd
Upload
37 views

Test-Statistics List: Test Statistics For Finding The Confidence Intervals and Hypothesis Testing

This document lists various test statistics used for confidence intervals and hypothesis testing for one or two samples of normally distributed populations. It includes test statistics for means and variances with both known and unknown parameters. For two samples, it covers test statistics for differences in means with equal or unequal, known or unknown variances. Degrees of freedom for t-distributions are also specified for each case.

Uploaded by

Rojan Pradhan
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
37 views

Test-Statistics List: Test Statistics For Finding The Confidence Intervals and Hypothesis Testing

This document lists various test statistics used for confidence intervals and hypothesis testing for one or two samples of normally distributed populations. It includes test statistics for means and variances with both known and unknown parameters. For two samples, it covers test statistics for differences in means with equal or unequal, known or unknown variances. Degrees of freedom for t-distributions are also specified for each case.

Uploaded by

Rojan Pradhan
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/ 1

Test-Statistics List

Test Statistics for finding the confidence intervals and Hypothesis Testing
1. Single Sample of a Normally Distributed Population
1.1 For the mean 𝜇 with known variance 𝝈𝟐
𝑋 −𝜇
𝑍 = 𝜎/ 𝑛
~𝑁(0,1) (Standard normally distributed)
1.2 For the mean 𝜇 with unknown variance 𝝈𝟐
𝑋 −𝜇
𝑡= ~𝑡𝑛−1 (𝑡 −Distribution with 𝑛 − 1 degrees of freedom)
𝑆/ 𝑛
1.3 For the variance 𝜎 2
(𝑛−1)𝑆 2 2
𝜒2 = 𝜎2
~𝜒𝑛−1 (𝜒 2 −Distribution with 𝑛 − 1 degrees of freedom)
2. Two Samples of the Normally Distributed Populations
2.1 For the mean difference 𝜇1 − 𝜇2 with known variances 𝝈𝟐𝟏 𝒂𝒏𝒅 𝝈𝟐𝟐
(𝑋1 −𝑋2 )−(𝜇 1 −𝜇 2 )
𝑍= ~𝑁(0,1) (Standard normally distributed)
𝜎2 2
1 +𝜎 2
𝑛1 𝑛2

2.2 For the mean difference 𝜇1 − 𝜇2 with unknown variances 𝝈𝟐𝟏 𝒂𝒏𝒅 𝝈𝟐𝟐 . if both the samples
sizes exceeds 30, then test statistics in (2.1) can be used by taking 𝝈𝟐𝟏 = 𝑺𝟐𝟏 𝒂𝒏𝒅 𝝈𝟐𝟐 = 𝑺𝟐𝟐 .
2.3 For the mean difference 𝜇1 − 𝜇2 with unknown variances 𝝈𝟐𝟏 𝒂𝒏𝒅 𝝈𝟐𝟐 but 𝝈𝟐𝟏 = 𝝈𝟐𝟐
assumed
(𝑋1 −𝑋2 )−(𝜇 1 −𝜇 2 )
𝑡= 1 1
~𝑡𝑛−1 (𝑡 −Distribution with 𝑛 − 1 degrees of freedom)
𝑆𝑃 +
𝑛1 𝑛2

𝑛 1 −1 𝑆12 + 𝑛 2 −1 𝑆22
Where, 𝑆𝑃2 = 𝑛 1 +𝑛 2 −2
is combined (pooled) sample variance.
𝑆12 𝑆22 𝑆 𝑆2
NOTE: if 𝑆22
𝑜𝑟 𝑆12
≤ 4 equivalently 𝑆1 𝑜𝑟 𝑆1
≤ 2, then 𝜎12 = 𝜎22 can be assumed and test
2
statistics of (2.3) can be used.
2.4 For the mean difference 𝜇1 − 𝜇2 with unknown variances 𝝈𝟐𝟏 𝒂𝒏𝒅 𝝈𝟐𝟐 but 𝝈𝟐𝟏 ≠ 𝝈𝟐𝟐
assumed
(𝑋1 −𝑋2 )−(𝜇 1 −𝜇 2 )
𝑡= ~𝑡𝜈 (𝑡 −Distribution with 𝜈 degrees of freedom)
𝑆2 2
1 +𝑆 2
𝑛1 𝑛2

𝑆2 2 2
1 +𝑆 2
𝑛1 𝑛2
Where, degrees of freedom, 𝜈 = 2 2 −2
𝑆2
1 𝑆2
2
𝑛1 𝑛1
+
𝑛 1 +1 𝑛 2 +1

2.5 For Paired mean difference 𝜇1 − 𝜇2 of Paired Observation


𝐷 −𝜇 𝐷
𝑡= 𝑆𝐷 ~𝑡𝑛−1 (𝑡 −Distribution with 𝑛 − 1 degrees of freedom)
𝑛
Where, 𝜇𝐷 = 𝜇1 − 𝜇2 and 𝐷 𝑎𝑛𝑑 𝑆𝐷 are, respectively, the sample mean and the sample variance
of difference of 𝑛-samples of the paired population.
𝝈𝟐
2.6 For the ratio of the variances 𝝈𝟏𝟐
𝟐
𝑆22 /𝜎22
𝐹= 𝑆12 /𝜎12
~𝐹𝑛 2 −1,𝑛 1 −1 (F-distribution with 𝑛2 − 1 𝑎𝑛𝑑 𝑛1 − 1 degrees of freedom)

You might also like