SPSSX Discussion

Analysis Techniques for Constant Sum scale data

Classic

List

Threaded

3 messages Options

sailaja

Analysis Techniques for Constant Sum scale data

Hi,

I have completed data collection with constant sum data scale where the sum of the response for each question will be 100. Could you please clarify on how to go about analysing the data? Is there any link that you could provide which details the various methods of analysing the constant sum data?

Thanks and Regards,
Sailaja

Bruce Weaver

Re: Analysis Techniques for Constant Sum scale data

Administrator

The article by Shaffer (1981) may be relevant.

http://amstat.tandfonline.com/doi/abs/10.1080/01621459.1981.10477692#.VBSIM2OumtU
www.jstor.org/stable/2287518

See also Greer & Dunlap (1997).

http://psycnet.apa.org/psycinfo/1997-06270-006

HTH.

sailaja wrote

Hi,

I have completed data collection with constant sum data scale where the sum of the response for each question will be 100. Could you please clarify on how to go about analysing the data? Is there any link that you could provide which details the various methods of analysing the constant sum data?

Thanks and Regards,
Sailaja

--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

PLEASE NOTE THE FOLLOWING:
1. My Hotmail account is not monitored regularly. To send me an e-mail, please use the address shown above.
2. The SPSSX Discussion forum on Nabble is no longer linked to the SPSSX-L listserv administered by UGA (https://listserv.uga.edu/).

Rich Ulrich

Re: Analysis Techniques for Constant Sum scale data

The Greer and Dunlap citation refers to "ipsative data", which is a term that I
have thought of as something other. You can find more citations, including those
in a Wikipedia article, if you look for "compositional data." Much of the concern
(it seems) has been among geologists.

In a relevant thread in 1995 in sci.stat.math, there was a post by Dave Watson
Subject: Re: (Wrong) Statistical Analysis of Compositional Data
Message-ID: <45hre5$[hidden email]>
- in which Dave W. disparaged the rationale of Aitchison, who had been cited by
another poster in 1995, and who is cited in the current Wikipedia article.
[J. Aitchison, 1986: The Statistical Analysis of Compositional Data, Chapman & Hall,
reprinted in 2003 with additional material by The Blackburn Press.]
That post was included in my old stats-FAQ; I can send it to anyone who is interested.

I've about given up in trying to use Google-Groups to search for old Usenet posts,
but you supposedly could search by the Subject: , six months ago. I will be
interested if someone succeeds in searching on either Subject: or Message-ID:.

--
Rich Ulrich

> Date: Sat, 13 Sep 2014 11:15:24 -0700

> From: [hidden email]
> Subject: Re: Analysis Techniques for Constant Sum scale data
> To: [hidden email]
>
> The article by Shaffer (1981) may be relevant.
>
> http://amstat.tandfonline.com/doi/abs/10.1080/01621459.1981.10477692#.VBSIM2OumtU
> www.jstor.org/stable/2287518
>
> See also Greer & Dunlap (1997).
>
> http://psycnet.apa.org/psycinfo/1997-06270-006
>

> sailaja wrote
> > Hi,
> >
> > I have completed data collection with constant sum data scale where the
> > sum of the response for each question will be 100. Could you please
> > clarify on how to go about analysing the data? Is there any link that you
> > could provide which details the various methods of analysing the constant
> > sum data?
> >

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD