You are here: Project Scarlet **»** Statistical Inference **»** **Two-Sample T-Procedures**

Statistical Inference

Please select the aspect of the Two-Sample Pooled T-Procedures you would like practice with:

The Two-Sample Pooled T-Procedure is used to compare the means of two populations. Using these procedures, you can calculate a confidence interval for or test a hypothesis regarding that difference, μ_{1} − μ_{2}. In order to use these procedures, the following assumptions must be met:

- The data come from a Normal distribution for each population
- The variances of the populations are equal

These assumptions are in addition to the usual two assumptions that the samples are representative of the target populations and that the sample values are independent.

If any of these assumptions are not met, then this is not the appropriate procedure to use. Note that the actual first assumptions are that the sample means are Normally distributed. However, since you have but one sample mean, this assumption cannot be directly assessed. An equivalent assumption is that the data are from a Normal distribution, which *can* be tested.

© Ole J. Forsberg, Ph.D. 2017. All rights reserved. | . | |