Tuesday, December 9, 2008
reflecting part 2
I noticed that after I had reflected my data and transformed it, the relationship became a positive one, where betas went from negative to positive. I do conceptually understand why it turned out this way, but in my results write up, do I indicate that after i have reflected and transformed my data, there was a significant negative relationship in transformed units, and then report the positive betas that I got from the regression?
Subscribe to:
Post Comments (Atom)
1 comment:
This is the exact kind of interpretation issue that you get when using an inverse transformation. In both cases, you should explain the relation between the variables conceptually, and report the actual obtained betas.
So for instance:
Higher levels of infant mortality were associated with fewer daily calories consumed, B = 0.23, SEB = 0.10, beta = .32, p = .03. (Of course, the stats for the other predictors/mediators/moderators and for the overall equation are also included.)
That is, you will have already explained the transformation issue earlier in the paper:
To correct for moderate negative skew, infant mortality was first reverse scored and then natural log transformed.
so there is no reason to remind the reader here of this transformation.
Post a Comment