Date: Tue, 18 Jul 2000 18:12:05 -0600
Reply-To: "Raymond V. Liedka" <liedka@UNM.EDU>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: "Raymond V. Liedka" <liedka@UNM.EDU>
Subject: Re: Compute: the Inverse?
Content-Type: TEXT/PLAIN; charset=US-ASCII
On Tue, 18 Jul 2000, Red Herring wrote:
> Dear All,
> According to Bradley (1982)taking the inverse of a variable with a J-shaped
> distribution is often the best way to transform it toward normality. I have
> several variables with J-shaped distributions in need of transformation but
> I can't find an inverse function anywhere on my SPSS 9.0. Am I missing
> something obvious here? I would greatly appreciate any help.
> Thank you.
Inverse of X is 1/X. So just use a compute statement to create new
COMPUTE INVX = 1/X.
Raymond V. Liedka
Department of Sociology
University of New Mexico