[R] Heteroscedasticity Plots

[N. Janz]

To detect heteroscedasticity for a multiple linear OLS regression (no time 
dependencies):

What if the residuals vs. fitted values plot shows well behaved residuals 
(cloud) - but the some of the x versus residuals plots are a megaphone?

Also, it seems that textbooks and internet tutorials in R do not agree what 
is the best plot for detecting heteroscedasticity. What do you use?

I found so far:

- Y vs X

- Res vs X

- Res vs Fitted Y

- Partial regression plot


and lots of standardized/studentized/partial plots.

Thank you very much in advance!

Nicole

- 

Nicole Janz, PhD Cand.

Lecturer at Social Sciences Research Methods Centre 2012/13

University of Cambridge

Department of Politics and International Studies

www.nicolejanz.de | nj248 at cam.ac.uk | Mobile: +44 (0) 7905 70 1 69 4

Skype: nicole.janz