Rather than splitting your table, you could just use bivariate to fit X to sex
and then do 'save standardised'.
Cheers
Gunter
-----Original Message-----
From: jmp-l-owner@lists.biostat.wustl.edu
[mailto:jmp-l-owner@lists.biostat.wustl.edu]On Behalf Of Ronald Cross
Sent: Thursday, 29 December 2005 12:53 PM
To: jmp-l@lists.biostat.wustl.edu
Subject: Re: [jmp-l] column standardizing by groups?
Go to tables in the menu and select split. You will want to split x
and set Col id to Sex. Give the output table a name and press ok.
You will have to rename columns Female and Male to X1 and X
respectively.
thx
RLC
On Dec 28, 2005, at 5:36 PM, Michael Bailey wrote:
>
> On Dec 28, 2005, at 7:27 PM, Ronald Cross wrote:
>
>> Will you provide more detail on what you mean by standardizing a
>> variable separately for men and women?
>>
>
> Sure. Variable X has different means and standard deviations for
> men and women. I want to create a new variable X1, that is X
> standardized using the male mean and standard deviation for all
> male observations, and the female mean and standard deviation for
> all female observations. I'm attaching a sample jmp file to
> illustrate. Note that variable X has different distributions for
> males and females.
>
>
> <columnstandard.jmp>
>
>
> Michael Bailey
> jm-bailey@northwestern.edu
>
>
|