I am very new to r and statistics in general. I am trying to test for homogeneity of variance on a multiple linear regression model I have created, and as I understand this is done by checking residuals against fitted values.

However, the plot I get looks nothing like any of examples and I am thus having a lot of difficulty understanding it. Plainly the different strata in the plot are related to the fact that the response variable is an ordinal 11 point scale.

The model was obtained using:

model1<-lm(imtcjob ~ hinctnta + happy + eduyrs + icpdwrk + agea + gndr, 



Residuals against fitted values


marked as duplicate by Tim Apr 18 '18 at 13:40

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

migrated from stackoverflow.com Apr 18 '18 at 13:36

This question came from our site for professional and enthusiast programmers.

  • $\begingroup$ Looking at the plot I suspect you have repeated measures and should use a mixed effects model. A violation of the assumption of independence is much more serious than heterogeneity of residual variance. $\endgroup$ – Roland Apr 18 '18 at 13:29
  • $\begingroup$ What is your question? Eg, I don't see a "?" anywhere. $\endgroup$ – gung Apr 18 '18 at 13:44
  • $\begingroup$ Sorry, my question is what does this plot mean? $\endgroup$ – H man Apr 18 '18 at 15:27

Browse other questions tagged or ask your own question.