R help - Apr 2009 - equation help

Hi everyone, I am having a bit of trouble correctly structuring an  
equation in R.


Here is the equation



Here is what I thought

for(i in 1:numItem)for(x in 1:numCat)

           Ptheta[,i,x]<-(exp(-1.702*a[i]*(theta-b[i,x+1]))

My problem is that I am not sure how to get it to read the equation as  
having two indexing points (i and x). Right now it is trying to read  
it as a matrix, but each value (i and x) are only vectors. Does anyone  
have any suggestions on how to get R to recognize this? As an example,  
numItem may = 20 and numCat may = 3 and I am trying to evaluate this  
over all values of numCat for each value of numItem.

Thanks,
Brendan

Brendan

It looks like you're working with the 2PL, what are you trying to
estimate exactly? There are a lot of built in psychometric functions
that you might consider using.
 
> -----Original Message-----
> From: r-help-bounces at r-project.org 
> [mailto:r-help-bounces at r-project.org] On Behalf Of Brendan Morse
> Sent: Monday, April 13, 2009 10:54 AM
> To: r-help at r-project.org
> Subject: [R] equation help
> 
> Hi everyone, I am having a bit of trouble correctly 
> structuring an equation in R.
> 
> 
> Here is the equation
> 
> 
> 
> Here is what I thought
> 
> for(i in 1:numItem)for(x in 1:numCat)
> 
>            Ptheta[,i,x]<-(exp(-1.702*a[i]*(theta-b[i,x+1]))
> 
> My problem is that I am not sure how to get it to read the 
> equation as having two indexing points (i and x). Right now 
> it is trying to read it as a matrix, but each value (i and x) 
> are only vectors. Does anyone have any suggestions on how to 
> get R to recognize this? As an example, numItem may = 20 and 
> numCat may = 3 and I am trying to evaluate this over all 
> values of numCat for each value of numItem.
> 
> Thanks,
> Brendan
> 
> ______________________________________________
> 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.
>

On Apr 13, 2009, at 10:54 AM, Brendan Morse wrote:
> Hi everyone, I am having a bit of trouble correctly structuring an  
> equation in R.
>
> Here is the equation
It's really a series of assignments.
>
>
> Here is what I thought
>
> for(i in 1:numItem)for(x in 1:numCat)
>
>          Ptheta[,i,x]<-(exp(-1.702*a[i]*(theta-b[i,x+1]))
I am guessing that what you really want is:

for(i in 1:numItem){
          for(x in 1:numCat){
                    Ptheta[i,x]<-(exp(-1.702*a[i]*(theta-b[i,x+1]))
                    } }  #obviously untested

That should populate the i, x entries of a matrix with your  
calculations. The extra comma in your attempt was telling R that you  
wanted a three dimensional array. The other possibility as a  
construction would be to use expand.grid
>
>
> My problem is that I am not sure how to get it to read the equation  
> as having two indexing points (i and x). Right now it is trying to  
> read it as a matrix, but each value (i and x) are only vectors.
Each value is an integer by the time it gets to the innards of the loop.
> Does anyone have any suggestions on how to get R to recognize this?  
> As an example, numItem may = 20 and numCat may = 3 and I am trying  
> to evaluate this over all values of numCat for each value of numItem.
>
> Thanks,
> Brendan
-- 
David Winsemius, MD
Heritage Laboratories
West Hartford, CT