1. ## Repeated measure ANOVA

Hello guys,

Haven’t done stats for 15 years, and been struggling for weeks now on an ANOVA, lost in a rural area in Haiti with limited access to the web… Any help would be great!

I’m trying to do a repeated measure ANOVA with 2 grouping factors (TRAIT\$ and BLOC\$, with BLOC\$ nested in TRAIT\$) and 1 within factor (TIME), and here are 2 major difficulties I have:

1/ To test the equality of variances of the residues, I’m trying a Levene test. I have done the same ANOVA on the ‘absolute value’ of the residues. When I do so, none of the between subjects effects are significant (TRAIT\$ and BLOC\$); but 2 of the within subject effects are significant (TIME and TIMEXBLOC\$(TRAIT\$). Does that means there is no equality of variances for the residues and I have to transform the data?

2/the results of the repeated measure ANOVA are the following (if I assume normality and equality of variances of residues):
-Between subjects: TRAIT\$ is not significant and BLOC\$(TRAIT\$) is significant
-Within subjects: both effects of TIME and TIMEXBLOC\$(TRAIT\$) are significant. Effects of TIMEXTRAIT\$ are not significant
I don’t know what to conclude with the interactions…

Thanks for any support!

2. ## Re: Repeated measure ANOVA

I work with regression rather than ANOVA although supposedly they are the same method. Test of homoscedacity are generally done on the overall model not on one specific variable although if the overall model residuals show a problem than you often look at the residuals compared to a specific predictor in order to come up with a solution. Note that regression does not use the Levene test so this may not mean much Remember that these assumptions don't have anything to do with the effect size. They influence the standard errors only and thus the validity of your statistical test [the p values effectively].

Since regression does not split the data into between and within variation I will leave you to an expert in ANOVA. Best wishes....

3. ## The Following User Says Thank You to noetsi For This Useful Post:

Libellule (03-16-2016)

4. ## Re: Repeated measure ANOVA

Thanks Noetsi!

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts