Analysis of Variance

ANALYSIS OF VARIANCE

For non-parametric alternatives to the one-way ANOVAs for independent and correlated samples, see the Kruskal-Wallis Test and the Friedman Test under 'Ordinal Data.'

One-Way ANOVA for up to five samples. The design can be either for independent samples or correlated samples (repeated measures or randomized blocks). This page will also perform pair-wise comparisons of sample means via the Tukey HSD test.
[Alternative one-way ANOVA pages: older and somewhat clunkier]

Two-Way Factorial ANOVA for Independent Samples, for up to four rows by four columns. This page will also calculate the critical values of Tukey's HSD for purposes of post-ANOVA comparisons.
[Alternative two-way ANOVA pages: older and somewhat clunkier]

Two-Factor ANOVA with Repeated Measures on One Factor, for designs in which there are 2-4 randomized blocks of matched subjects, with 2-4 repeated measures for each subject.
Two-Factor ANOVA with Repeated Measures on Both Factors, for designs in which there are 2-4 levels of each of two variables, A and B, with each subject measured under each of the AxB combinations.
2x2x2 ANOVA for Independent Samples. For designs with three independent variables, A, B, and C, each with two levels. This situation yields 2x2x2=8 unique treatment combinations— a1b1c1, a1b1c2, and so forth— one for each of 8 independent samples of subjects.
Orthogonal Latin Square Designs for n = j². Click here for a brief description of this type of design.
  4x4    5x5

Alternative ANOVA Pages. Although the following pages are somewhat clunkier than the ones listed above, their data-entry format might prove more fail-safe for the beginning student. Note, however, that these pages will be rather awkward to use with large sample sizes.

One-Way ANOVA in Cell-Entry Format. As these pages open, you will be prompted to enter the size of the largest of your several samples (for the independent- samples design) or the number of subjects or randomized blocks for which you have multiple measures (in the correlated- samples design).
For k Independent Samples:  k = 3    k = 4
For k Correlated Samples:    k = 3    k = 4

Two-Way Independent-Samples ANOVA in Cell-Entry Format. As these pages open, you will be prompted to enter the size of the largest of your several samples.
2x2   2x3   3x3
Return to top

One-Way ANOVA in Cell-Entry Format. As these pages open, you will be prompted to enter the size of the largest of your several samples (for the independent- samples design) or the number of subjects or randomized blocks for which you have multiple measures (in the correlated- samples design). For k Independent Samples: k = 3 k = 4 For k Correlated Samples: k = 3 k = 4
Two-Way Independent-Samples ANOVA in Cell-Entry Format. As these pages open, you will be prompted to enter the size of the largest of your several samples. 2x2 2x3 3x3 Return to top