^{Hypothesis Testing (Parametric)}

​

^{Md. Ershadul Haque, PhD}

^{Associate Professor}

^{Dept. of Statistics, University of Dhaka}

^{16-17 February, 2024�}

Two-sample t-test

Two-sample t-test (Cont…)

Problems on Repeated Measure t Test

• The independent sample t-test, also referred to as independent t-test or unpaired t-test.
• It compares the averages/means of two independent or unrelated groups to determine if there is a significant difference between the two groups.

Assumptions:

1. Subjects are randomly selected and each subject should belong to only one group.
2. No significant outliers in the two groups.
3. The data for each group should be approximately normally distributed. This assumption can be relaxed for large sample size.
4. The variance of the measurements need to be equal in each group.
• Any violation of this assumption can be corrected by using the Welch t-test by using an adjustment to the degrees of freedom. Note that the Welch t-test does not make this assumption of homogeneity of variance.

Thank you for your attention!