0
$\begingroup$

enter image description here

Hi, above is the plot of residuals against the fitted value of a linear model. I am asked to determine if the assumptions for the linear model hold in this case. I don't think the constant variance for error terms holds in this case because there are some data points that are clustered while others are more spread out. I think the assumption that the mean of the error term is 0 holds because the most data points center around the band that is above and below 0. Are my answers and logic correct? Thanks in advance!

$\endgroup$
  • 2
    $\begingroup$ One thing you can try is to plot a histogram of the residuals, see if that looks normal. $\endgroup$ – Dave2e Sep 27 '19 at 14:13
  • 2
    $\begingroup$ There is virtually no evidence for heteroscedasticity in this plot. $\endgroup$ – whuber Sep 27 '19 at 14:30
1
$\begingroup$
  1. Constant Variance of Error Term (no Heteroscedasticity) holds. Regardless of the fitted values, you observe a constant spread around 0. Heteroscedasticity would look like this: enter image description here
  2. Mean of the error equals 0 also holds, as you rightly point out.
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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