Re: Do I need to fix unequal variance (i.e. heteroscedasticity) problems?

From: "Data Matter" <fungile@xxxxxxxxx>
Date: 5 Apr 2005 18:52:43 -0700

How about plotting the errors against the predicted values and observe
where and how the unequal variances is happening? SAS doesn't make it
easy to visualize anything but a picture is often worth a thousand
words (in the case of SAS, decimal places)!

.

References:
- Do I need to fix unequal variance (i.e. heteroscedasticity) problems?
  - From: John Saks
- Re: Do I need to fix unequal variance (i.e. heteroscedasticity) problems?
  - From: Richard Ulrich

Prev by Date: Re: basic description of PCA terms
Next by Date: P-value from chi-square value: source code
Previous by thread: Re: Do I need to fix unequal variance (i.e. heteroscedasticity) problems?
Next by thread: Difference of two chi-squares
Index(es):
- Date
- Thread