GraphPad Statistics Guide

Don't confuse with related analyses

Don't confuse with related analyses

Previous topic Next topic No expanding text in this topic  

Don't confuse with related analyses

Previous topic Next topic JavaScript is required for expanding text JavaScript is required for the print function Mail us feedback on this topic!  

The chi-square goodness of fit test can easily be confused with other tests. Here are some distinctions to avoid any confusion.

Relationship to the chi-square analysis of contingency tables

Note that the chi-square test is used in two quite different contexts.

One use is to compare the observed distribution with an expected distribution generated by theory.

Another use is to analyze a contingency table. In this analysis, the expected values are computed from the data, and not from an external theory.

Relationship to normality tests

Normality tests compare the observed distribution of a continuous variable, with a theoretical distribution generated by the Gaussian distribution. Prism offers three ways to do this comparison, all offered as part of the Column statistics analysis.

Relationship to the Kolmogorov-Smirnov test

The Kolmogorov-Smirnov test can be used as a nonparametric method to compare two groups of continuous data. It compares the two observed cumulative frequency distributions, and does not compare either observed distribution to an expected distribution.