check for Heteroskedasticity?

#1
Hi guys,

just a quick question - I need to find out whether there is Heteroskedasticity in my data. I did a scatterplot of standardised residuals on standardised predicted values, in order to check whether the data is "fanning out"... I don´t think so, but I just wanted to double-check with you guys... attached the scatterplot - what do you think?

Thanks a lot in advance!!

Best,

Simon
 

noetsi

Fortran must die
#3
I don't think I have ever seen a residual plot where there is no fanning out (change in the dispersion in the residuals) so what this means in practice is something of a guess. Particularly when you have hundreds or thousands of points.