[R] Ability Estimates for Repeated Measurements in the eRm Package

[Tessari]

Hello,

Thank you very much for the tip.  I think that the irt.ability() function is
what I'm looking for but I'm not sure.

To be more clear, I have obtained item parameters from the LLTM function in
the eRm package which allows for repeated measurements.  I have 10 items
measured at 2 time points, for a total of 20 item parameters.  I wish to get
the ability estimate for a person at time 1 and then separately at time 2. 
Here is the code I'm using but it doesn't seem to work.

ItemParams<-c(-0.199,-0.283,0.109 ,0.142 ,0.056
,-0.062,-0.125,0.066,0.153,0.142,
	0.102,0.019,0.411,0.443,0.357,0.239,0.176,0.368,0.454,0.443)

Time1Params<-list("1pl" = list (b = ItemParams[1:10]))

Time2Params<-list("1pl" = list (b = ItemParams[10:20]))

irt.ability(c(1,0,1,1,1,1,0,1,1,1),Time1Params,method="MLE")

irt.ability(c(1,1,1,1,0,0,1,1,1,1),Time2Params,method="MLE")

Also, I've tried to locate the MP Vignette but have been unsuccessful.

Thanks again for your timely response.  It's greatly appreciated!

Best,

Kim


Doran, Harold wrote:
> 
> Not sure I completely understand what you want. You might try looking at
> the irt.ability() function in the MiscPscyho package for ability
> estimates.
> 
>> -----Original Message-----
>> From: r-help-bounces at r-project.org 
>> [mailto:r-help-bounces at r-project.org] On Behalf Of Tessari
>> Sent: Wednesday, September 02, 2009 11:50 AM
>> To: r-help at r-project.org
>> Subject: [R] Ability Estimates for Repeated Measurements in 
>> the eRm Package
>> 
>> 
>> Dear R Users, 
>> 
>> I am using the LLTM and the LRSM functions in the eRm package 
>> to do repeated measurements where there are 2 measurement 
>> points for a list of 10 items.  I am trying to get ability 
>> estimates but am having trouble.  I don't think that it is 
>> appropriate to use the pmat function since the person 
>> parameters are based on all 20 items.  Rather, I think it 
>> would be more appropriate to have the person parameters be 
>> based on the 10 items at Time 1 and then the next 10 items at 
>> Time 2.  However, I don't want to form 2 separate Rasch 
>> models since I think it's important to have all 20 item 
>> parameters calculated at once.
>> 
>> Any advice would be greatly appreciated.  Also, if more 
>> information is needed, I could send my sample code.
>> 
>> Best,
>> 
>> Kim
>> --
>> View this message in context: 
>> http://www.nabble.com/Ability-Estimates-for-Repeated-Measureme
> nts-in-the-eRm-Package-tp25260278p25260278.html
>> Sent from the R help mailing list archive at Nabble.com.
>> 
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide 
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>> 
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
> 
> 

-- 
View this message in context: http://www.nabble.com/Ability-Estimates-for-Repeated-Measurements-in-the-eRm-Package-tp25260278p25284582.html
Sent from the R help mailing list archive at Nabble.com.