Date:         Thu, 11 Aug 2005 20:01:51 -0300
Reply-To:     Hector Maletta <hmaletta@fibertel.com.ar>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Hector Maletta <hmaletta@fibertel.com.ar>
Subject:      Re: Combo variable syntax
Comments: To: james.moffitt@thomson.com
In-Reply-To:  <945D579F76FD5741A043511E6FE99B57C3C34C@TLRUSMNEAGMBX32.ERF.THOMSON.COM>
Content-Type: text/plain; charset="us-ascii"

It probably has to do with the maximum integer that is accepted by SPSS.
Numbers above the maximum are rounded and get scientific format. Since up to
16 decimals can be accepted you may try dividing your figure by 10**16, so
the integer part would be 10**8 and could appear as a number. Remember
establishing also the visible format for a total of 26 places with 16
decimals, one decimal point and 9 integer places, as in

FORMAT variablename (f25.16).

On the other hand, experience shows this procedure may get easily
unmanageable unless responses are highly concentrated in a (relatively)
small number of response patterns.

Hector

> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]
> On Behalf Of Jim Moffitt
> Sent: Thursday, August 11, 2005 7:37 PM
> To: SPSSX-L@LISTSERV.UGA.EDU
> Subject: Combo variable syntax
>
> I've got 25 dichotomous variables that indicate whether a
> respondent engages in a particular activity. A 1 indicates
> the respondent engages in the activity, a 2 indicates he does not.
>
> I am trying to create a new variable called combo that I can
> use to determine which combinations of activities occur most
> frequently.
>
> I wrote some syntax to create the combo variable that begins:
> "compute combo= 10**24*q48 + 10**23*q57 + 10**22*q68" and
> ends with"1*q109.
> EXECUTE."
>
> I was hoping to wind up with a new variable filled with
> 25-digit values composed of 2's and 1's.
>
> Instead, the last 9 digits of each value consists of nothing
> but zeros.
>
> Can anyone explain why this is so and suggest a remedy? TIA.
>
> __________ Informacisn de NOD32 1.1192 (20050811) __________
>
> Este mensaje ha sido analizado con  NOD32 Antivirus System
> http://www.nod32.com
>
>