T-test

The program performs Student's t-test for significantly different means. This test is applied when two distributions x and y are thought to have the same variance, but possibly different means. The test evaluates the significance of the t=(x0-y0)/SD, where x0 and y0 are mean estimates for x and y, SD is the "pooled variance". The t value follows Student's t-distribution with Nx + Ny - 2 degrees of freedom, where Nx and Ny are sample sizes for x and y. The significance is the probability that |t| could be this large or larger just by chance, for distributions with equal means; a value of the significance smaller than, for example, 0.05 means that the observed difference is significant at 95% confidence.

File should contain table of numerical data: lines for observations (cases) columns should be separated by tabulation or user-defines symbol (; , etc); for example, if comma (,) separator is used, the file format is the same as the CSV (comma separated values) format. No missing data allowed.

This program use statistical functions from "R" free software environment for statistical computing and graphics (http://www.r-project.org).

This program requires the R-package to be installed on your computer.



T-test description

T-test parameters