[R] aregImpute: warning message re: acepack and mace

[Uwe Ligges]

adiamond at fas.harvard.edu wrote:
> hi,
> 
> i'm trying to learn how to use aregImpute by doing the examples provided with 
> the package, and after installing Hmisc.1.6-1.zip (for Windows),

Hmisc_2.0-0 is current.

use e.g. update.packages() to update to the recent version.

> and running the very first example on R 1.7.1, i get an error message warning 
> me about "mace" (see below) and acepack.  
> 
> i found the acepack package, but its filename ends in tar.gz
> and i'm finding it difficult to open (because its designed for Unix, i guess).
> is there an acepack.zip file?  is there any way that i can play
> with aregImpute on my Windows system?

So also update those packages. If they are not already installed, use 
install.packages() to install them.

The binary packages for R-1.7.x can be found at 
CRAN/bin/windows/contrib/1.7 , if you tend to install manually.

Uwe Ligges


> thank you for your help,
> 
> alexis
> 
> 
>># Multiple imputation and estimation of variances and covariances of
>># regression coefficient estimates accounting for imputation
>># Example 1: large sample size, much missing data, no overlap in
> 
> .
> .
> .
> 
>># Use 100 imputations to better check against individual true values
>>f <- aregImpute(~y + x1 + x2 + x3, n.impute=100, data=d)
> 
> 
> Loading required package: acepack 
> Iteration:1 Error in .Fortran("mace", p = as.integer(ncol(x)), n = as.integer
> (nrow(x)),  : 
>         C/Fortran function name not in load table
> In addition: Warning message: 
> There is no package called 'acepack' in: library(package, character.only = 
> TRUE, logical = TRUE, warn.conflicts = warn.conflicts,
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help