[R] Amelia_Multiple_Imputation_with_observational_priors_noms

[Uwe Ligges]

I'd write to the Amelia maintainer. Maybe it is a bug in the package, or 
just an inappropriate error message (where the error should have been 
caught earlier).

Uwe Ligges



On 14.07.2011 20:09, Eric Miner wrote:
> I am fairly new at using R/programming in general so I apologize if I am
> leaving crucial parts of the puzzle out, but here goes.
>
>
>
> First and foremost this is the error I am receiving:
>
>
>
> Error in muPriors[priors[, 1:2]]<- priors[, 3] :
>
>    NAs are not allowed in subscripted assignments
>
>
>
> This occurs only when I am using observational priors and some number of
> nominal variables, it does not occur when I change to specifying the
> variables as ordinal, or if I do not use priors. Using a doctored version of
> the example from the Amelia User Guide this is what I came up with:
>
>
>
> library(Amelia)
>
> library(MatchIt)
>
> library(Zelig)
>
> library(foreign)
>
>
>
> data(freetrade)
>
>
>
> a.out = amelia(freetrade, m=5, ts = "year", cs = "country")
>
>
> newtrade = which(is.na(freetrade), arr.ind = TRUE)
>
> newtrade
>
> newtradeMean =
> c(30,29,28,31,32,34,30,34,26,32,30,29,28,31,32,34,30,34,26,32,30,29,28,31,32,34,30,34,26,
>
> 32,30,29,28,31,32,34,30,34,26,32,30,29,28,31,32,34,30,34,26,32,31,31,32,33,34,35,20,21,
>
> 7,8,2.0,2.1,2.2,2.0,2.5,2.3,2.5,2.1,1.9,1.8,1.7,2.9,2.0,0,0,1,.3,.4,.5,.3,.2,.3,.2,.4,.5,.3,.2,.3,.3,.4,.5,.3,.2,.3)
>
> newishtrade = cbind(newtrade,newtradeMean)
>
> newishtrade
>
> newtradeSD =
> c(5,5,5,4,3,3,2,4,5,4,5,5,5,4,3,3,2,4,5,4,5,5,5,4,3,3,2,4,5,4,5,5,5,4,3,3,2,4,5,4,5,5,5,4,3,3,2,4,5,4,3,4,5,6,4,3,4,2,
>
> 4,1,1.2,.3,.4,.3,.4,.3,.2,.3,.4,.3,.3,.3,.2,.3,.2,.3,.3,.1,.1,.2,.2,.3,.3,.1,.1,.2,.2,.3,.3,.1,.1,.2,.2,.3)
>
> newishtrade = cbind(newtrade,newtradeMean, newtradeSD)
>
> newishtrade
>
>
>
> a.out = amelia(freetrade, m=5, ts = "year", cs = "country", priors =
> newishtrade, p2s=2, noms="signed")
>
>
>
> a.out = amelia(freetrade, m=5, ts = "year", cs = "country", priors =
> newishtrade, p2s=2, ords="signed")
>
>
>
>
> I followed the trail back through the source code to try and see what was
> occurring. I learned some debugging techniques and tried to discern if it
> was something with the code or perhaps some incorrect steps in using priors
> with nominal variables. To summarize, I cannot get observational priors to
> work when I specify nominal variables. If it helps below is my sourcing
> output scattered through the various functions in the source code. Thoughts?
>
>
> amelia starting
> before prep
> amelia.prep started
> beginning prep functions
> Variables used:  tariff polity pop gdp.pc intresmi fiveop usheg
> noms.signed.2
> after prep
> running bootstrap
> does this work
> Error in muPriors[priors[, 1:2]]<- priors[, 3] :
>    NAs are not allowed in subscripted assignments
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> 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.