Dianne Worth wrote: > > Oops - what I meant to say was "What if my NEGATIVELY > skewed data all have negative values, say from -1 to > -7? Does the same logic/procedure still hold?" > > Because I cannot take the log of a negative number and > instead take the absolute value of those numbers, I'll > have positively skewed data.
The log transform reduces positive skew. It would make negative skew more negative (if the values were computable). For negative skew you need to use different transformations (e.g., y-squared). If you have positive skew with zero or negative values the traditional solution is to add a constant. Thom . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
