Re: Question About Tests of Normality and Choice of Statistical Analysis

Posted by Art Kendall on Dec 30, 2014; 9:07pm
URL: http://spssx-discussion.165.s1.nabble.com/Question-About-Tests-of-Normality-and-Choice-of-Statistical-Analysis-tp5728302p5728303.html

NO.

Rarely does  the distribution of the raw data matter.  In most instances what matters is the distribution of the residuals (errors).

What questions are you using statistical methods to answer?