Take the 2-minute tour ×
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

I've been reading the Wikipedia page for Levene's test, and it cites the degrees of freedom as (k - 1, N - k), where k is the number of different groups to which the sampled cases belong, and N is the total number of cases in all groups. However, it does not explain why this is so. There is a very thorough answer here which would suffice to answer this question in relation to the chi square goodness of fit. However, I have not been able to find a satisfactory answer to the question in relation to Levene's test.

share|improve this question

1 Answer 1

up vote 4 down vote accepted

Levene's test is one of several tests that is essentially an ANOVA but using a response that converts the spread of the values into locations. In the case of Levene, the observations put into the ANOVA are:

$$Z_{ij} = |Y_{ij} - \bar{Y}_{i\cdot}|, \text{ where } \bar{Y}_{i\cdot} \mbox{ is the mean of the }i^\text{th} \text{ group } $$

which are the absolute deviations from their own sample means, for which larger spread on the $Y_{ij}$ would give typically larger $Z_{ij}$. Consequently, a difference in mean $Z$s implies a difference in spread on the $Y$s.

enter image description here

In ANOVA, if you have $k$ groups and $N$ observations, the d.f. for the overall F-test for differences in mean has $(k-1,N-k)$ df.

Levene's test simply uses the df of the ANOVA it applies to the $Z$ values.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.