GraphPad Statistics Guide

Lingo: Multiple comparison tests

Lingo: Multiple comparison tests

Previous topic Next topic No expanding text in this topic  

Lingo: Multiple comparison tests

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

Multiple comparison test applies whenever you make several comparisons at once.  

Post test is sometimes used interchangeably with multiple comparison test (above) but sometimes as a short form of post-hoc test (below).

Post-hoc test is used for situations where you decide which comparisons you want to make after looking at the data. You didn't plan ahead.  

Planned comparison tests  require that you focus in on a few scientifically sensible comparisons. You can't decide which comparisons to do after looking at the data. The choice must be based on the scientific questions you are asking, and be chosen when you design the experiment.  

Orthogonal comparison. When you only make a few comparison, the comparisons are called "orthogonal" when the each comparison is among different groups. Comparing Groups A and B is orthogonal to comparing Groups C and D, because there is no information in the data from groups A and B that is relevant when comparing Groups C and D. In contrast, comparing A and B is not orthogonal to comparing B and C.

Multiple comparisons procedures are used to cope with a set of comparisons at once. They analyze a family of comparisons.

When you set the customary significance level of 5% (or some other value) to apply to the entire family of comparisons, it is called a familywise error rate. When that significance level applies to only one comparison at a time (no correction for multiple comparisons), it is called a per-comparison error rate.