GraphPad Statistics Guide

Options tab: Graphing and output: One-way ANOVA

Options tab: Graphing and output: One-way ANOVA

Previous topic Next topic No expanding text in this topic  

Options tab: Graphing and output: One-way ANOVA

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

There are two help screens for the Options tab for the one-way ANOVA dialog:

A different page explains the multiple comparisons options.

This page explains the graphing and output options.


 

Graphing

Prism gives you options to create some extra graphs, each with its own extra page of results.

If you chose a multiple comparison method that computes confidence intervals (Tukey, Dunnett, etc.) Prism can plot these confidence intervals.

You can choose to plot the residuals. For ordinary ANOVA, each residual is the difference between a value and the mean value of that group. For repeated measures ANOVA, each residual is computed as the difference between a value and the mean of all values from that particular individual (row).

If you chose the Kruskal-Wallis nonparametric test, Prism can plot the ranks of each value, since that is what the test actually analyzes.

If you chose repeated measures ANOVA, Prism can plot the differences. If you have four treatments (A, B, C, D), there will be six set of differences (A-B, A-C, B-C, A-D, B-D, C-D). Seeing these differences graphed can give you a better feel for the data.

Additional results

You can choose an extra page of results showing descriptive statistics for each column, similar to what the Column statistics analysis reports.

Prism also can report the overall ANOVA comparison using the information theory approach (AICc), in addition to the usual P value. Prism fits two models to the data -- one where all the groups are sampled from populations with identical means, and one with separate means -- and tells you the likelihood that each is correct. This is not a standard way to view ANOVA results, but it can be informative.

Output

Choose how you want P values reported, and how many significant digits you need.