Date: Thu, 30 Sep 2004 11:46:38 -0400
Reply-To: Eric Yount <eric.yount@RTP.PPDI.COM>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: Eric Yount <eric.yount@RTP.PPDI.COM>
Subject: Re: Variable scale in Factor Analysis of survey data
In-Reply-To: <3AB849890F60404B9CD9E6CE5DFF17C70272743E@D01SVR15>
Content-Type: text/plain; charset=us-ascii; format=flowed
Wang, Zhu wrote:
> Dear all,
>
> In a survey data, I have one variable like:
>
> 1. Yes
> 2. No
> 98. Don't Know
> 99. Refused
>
> My concern is that those values 98 and 99, especially when the distribution
> is like the follows:
>
> Variable Frequency Percent Cum. Freq. Cum. Percent
> 1 190 23.60 190 23.60
> 2 544 67.58 734 91.18
> 98 70 8.70 804 99.88
> 99 1 0.12 805 100.00
>
> Should I change 98 to 3 or it does not matter in SAS? Any comments will be
> welcome.
>
> Thanks,
>
> Zhu Wang
>
Zhu,
They are categorical variables, and as such, it does not matter in any
analysis what their names are.
This is in contrast to ordinal variables, where order matters. For
example, if your categories were '<18 years of
age','18-35','36-65',etc., order might matter, but for 'Yes' and 'No,'
you can't say categorically that 'Yes' > 'No' or 'Yes' < 'No.'
Hope this helps,
Eric
______________________________________________________________________
This email transmission and any documents, files or previous email
messages attached to it may contain information that is confidential or
legally privileged. If you are not the intended recipient or a person
responsible for delivering this transmission to the intended recipient,
you are hereby notified that you must not read this transmission and
that any disclosure, copying, printing, distribution or use of this
transmission is strictly prohibited. If you have received this transmission
in error, please immediately notify the sender by telephone or return email
and delete the original transmission and its attachments without reading
or saving in any manner.
| 
