A
statistical test for determining if two
samples come from the same
population. The t-test can be considered a special case of the
ANOVA.
Essentially, the t-test works like this: take two samples, and determine the mean and variance for each one. Given this information, you can determine the likelihood that the difference in means is due to random chance. The more likely that it is random, the more likely that the samples came from the same population.
Of course, this can never actually prove, in the strict sense, that two sanples are from the same population, or from different populations; it can just give you probabilities and let you decide what conclusions to make from there. In many sciences, two samples are considered to be from different populations of the probability that they are from the same population is less than five percent.
See null hypothesis.