Date: Thu, 8 Feb 2007 10:05:32 -0600
Reply-To: "Beadle, ViAnn" <viann@spss.com>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: "Beadle, ViAnn" <viann@spss.com>
Subject: Re: Is this possible in SPSS? MULT RESPONSE PROBLEM
In-Reply-To: A<IPSOSCRTPnhur860EWm00000e5b@ipsoscr.IPSOS.ipsos-ca.com>
Content-Type: text/plain; charset="us-ascii"
Hard to tell what your data look like here but if on one record you have a repeating data set for each car which is car name, defect type, and number of defects for that type, you are better off restructuring the file from wide to narrow (VARSTOCASE) so that each record is a car x defect and then you can get simple sums by car. Your unit of analysis is not a dealer but a car.
-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Eugenio Grant
Sent: Thursday, February 08, 2007 9:39 AM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: Is this possible in SPSS? MULT RESPONSE PROBLEM
Is this possible on SPSS
Hi I have a DataBase that has a report of Problems presented by cars, where
each case is a report for every dealer.
This is a simplified version of how the data looks like.(In reality the car
variable goes up to car30 and 1500 dealers)
Dealer
car1
prob1
prob2
car2
prob3
prob4
1
Honda
Door
Engine
Hummer
Pump
.
2
Toyota
Susp
.
VW
Brakes
Tires
3
Mitsub
Paint
Engine
.
.
.
4
Subaru
Interior
.
Honda
Susp
.
5
Honda
Susp
Bumper
Toyota
Engine
Paint
I know I can have a Mult Response per problem (Set of prob1 to prob4), but
how can I get a Mult Response of problems per car, So I can display the
occurrence of problems for Honda, Toyota, and so on.
Regards,
|