
general. It is necessary to understand how the sample represents the pop-
ulation about which inferences will be made.
Inferential Statistics
Inferential statistics, such as t-tests, analysis of variance, chi-square, and
some nonparametric statistics, do more than just compare groups that
are observed in the experiment; they allow inferences about the popula-
tion. That is, they extrapolate from a small sample to estimate what
would happen if all possible tests were run; this enables generalization
from data with known certainty. For instance, to measure the perfor-
mance of a new algorithm you might have the time and energy to run it
using every possible ...