Rasch Model in SPSS

[E. Bernardo]

I tried to run the Rasch Model for the 10 items using R in SPSS.  I was dismayed of the outputs as presented below.  Please comment if I need something to download from the R website and then install to my computer.   Thank you. Eins   Coefficients
	value	std.err	z.vals
Dffclt.base	-1.793	.224	-8.016
Dffclt.prstt	-2.181	.253	-8.611
Dffclt.advst	-1.435	.200	-7.163
Dffclt.ts	-.306	.157	-1.943
Dffclt.prsnt	-1.368	.196	-6.966
Dffclt.permp	-.955	.176	-5.432
Dffclt.chaid	-1.034	.179	-5.769
Dffclt.map	-.324	.158	-2.053
Dffclt.nernt	.173	.156	1.104
Dscrmn	.846	.074	11.484

[Ryan]

Eins,

 

I cannot speak to your output as I've never used this R package for SPSS. It's probably worth noting that if all your items are binary, you could fit the Rasch model via the GENLINMIXED procedure offered in SPSS 19.

 

Ryan

On Sun, Mar 20, 2011 at 9:31 AM, Eins Bernardo <[hidden email]> wrote:

I tried to run the Rasch Model for the 10 items using R in SPSS.  I was dismayed of the outputs as presented below.  Please comment if I need something to download from the R website and then install to my computer.   Thank you. Eins   Coefficients
	value	std.err	z.vals
Dffclt.base	-1.793	.224	-8.016
Dffclt.prstt	-2.181	.253	-8.611
Dffclt.advst	-1.435	.200	-7.163
Dffclt.ts	-.306	.157	-1.943
Dffclt.prsnt	-1.368	.196	-6.966
Dffclt.permp	-.955	.176	-5.432
Dffclt.chaid	-1.034	.179	-5.769
Dffclt.map	-.324	.158	-2.053
Dffclt.nernt	.173	.156	1.104
Dscrmn	.846	.074	11.484

[Daniel J. Robertson]

It looks like you’re seeing the difficulty indices and standard errors for nine items, along with a single unconstrained discrimination parameter. The Rasch extension itself uses the R package ‘ltm,’ which you can find documentation for at http://cran.r-project.org/web/packages/ltm/index.html or http://www.jstatsoft.org/v17/i05. You can also get syntax help by running the command “SPSSINC RASCH /HELP.”

 

--

Daniel Robertson

Senior Research and Planning Associate

Institutional Research and Planning

Cornell University / irp.cornell.edu

 

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Eins Bernardo
Sent: Sunday, March 20, 2011 9:31 AM
To: [hidden email]
Subject: [SPSSX-L] Rasch Model in SPSS

 

I tried to run the Rasch Model for the 10 items using R in SPSS.  I was dismayed of the outputs as presented below.  Please comment if I need something to download from the R website and then install to my computer.   Thank you. Eins   Coefficients
	value	std.err	z.vals
Dffclt.base	-1.793	.224	-8.016
Dffclt.prstt	-2.181	.253	-8.611
Dffclt.advst	-1.435	.200	-7.163
Dffclt.ts	-.306	.157	-1.943
Dffclt.prsnt	-1.368	.196	-6.966
Dffclt.permp	-.955	.176	-5.432
Dffclt.chaid	-1.034	.179	-5.769
Dffclt.map	-.324	.158	-2.053
Dffclt.nernt	.173	.156	1.104
Dscrmn	.846	.074	11.484