Definition:Homogeneity of Variance

Definition

Many statistical techniques require the assumption that all population variances are equal.

Several tests have been devised for checking whether this assumption is reasonable, given some relevant data.

As follows:

• Bartlett's test works well when the data fits a normal (Gaussian) distribution, but less when when this assumption is invalid.

• Levene's test is sometimes preferred to Bartlett's test.

This article, or a section of it, needs explaining. In particular: Explain why You can help $\mathsf{Pr} \infty \mathsf{fWiki}$ by explaining it. To discuss this page in more detail, feel free to use the talk page. When this work has been completed, you may remove this instance of {{Explain}} from the code.

Some non-parametric tests that can be used:

• The Siegel-Tukey test

• The Conover squared rank test

• The Ansari-Bradley test.

and others.

This article is complete as far as it goes, but it could do with expansion. In particular: Some words of explanation as to why, on transcluded subpages if appropriate You can help $\mathsf{Pr} \infty \mathsf{fWiki}$ by adding this information. To discuss this page in more detail, feel free to use the talk page. When this work has been completed, you may remove this instance of {{Expand}} from the code. If you would welcome a second opinion as to whether your work is correct, add a call to {{Proofread}} the page.

Also see

• Results about homogeneity of variance can be found here.

Sources

• 2008: David Nelson: The Penguin Dictionary of Mathematics (4th ed.) ... (previous) ... (next): homogeneity of variance