Date: Fri, 9 Sep 2005 08:29:11 -0400
Reply-To: Lisa Stickney <Lts1@enter.net>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Lisa Stickney <Lts1@enter.net>
Subject: Re: Data Layout
Content-Type: text/plain; charset="iso-8859-1"
Hi Vassilis,
I agree with Hector. Recently I did something just like this. I asked respondents to select (from a list) which of the following . . . (please select all that apply). When coding each possible item became a dummy variable. What I did when coding was used 1 (if the item was selected) or 0 (if not selected) only if the respondent answered the question. I saved missing values for people who chose not to answer the question at all. As it turned out that became important when I was writing up my results because it allowed me to accurately calculate my repsonse rates without going back through 197 surveys. I hope this helps.
Best,
Lisa
P.h.D. Student
The Fox School of Business
and Management
Temple University
----- Original Message -----
From: "Hector Maletta" <hmaletta@fibertel.com.ar>
Newsgroups: bit.listserv.spssx-l
To: <SPSSX-L@LISTSERV.UGA.EDU>
Sent: Thursday, September 08, 2005 2:40 PM
Subject: Re: Data Layout
> Since apparently the number of items mrked by each subject is variable, you
> better choose the Multiple Dichotomies coding system, i.e. open one column
> or variable for each item (a total of 15 variables), and put 0 or 1 in each
> depending on the subject having omitted or marked it respectively. You can
> of course use other codes intead of 0 and 1, but those are quite convenient
> for many purposes. Items not chosen may remain blank or be marked with 0,
> and I personally like to code them to zero, also for a number of reasons.
>
> Hector
>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]
>> On Behalf Of Vassilis Hartzoulakis
>> Sent: Thursday, September 08, 2005 3:14 PM
>> To: SPSSX-L@LISTSERV.UGA.EDU
>> Subject: Data Layout
>>
>> Greetings
>> I have a number of subjects who have expressed their
>> preferences among a number of 15 items.
>> e.g. Some have chosen items 1, 4, 5 and 9... others have
>> chosen items 1, 6, 9, 11, 13 and 15 etc....
>> What might be a good layout for SPSS to help me find the most (and the
>> least) popular items?
>> Thank you
>> Vassilis
>>
>> __________ Informacisn de NOD32 1.1212 (20050908) __________
>>
>> Este mensaje ha sido analizado con NOD32 Antivirus System
>> http://www.nod32.com
>>
>>
>
| 
