The logmult's discuss from nalimilan

logmult's Issues

Standard erros for RC model not working

Thank you for maintaining this very useful package. I just came across a bug in the function logmult::rc(). Estimating standard errors via the jackknife or bootstrapping seems to be broken.

Please see the example below. I get the same when trying the bootstrap instead of the jackknife.

library(logmult)
set.seed(123)
tbl <- table(sample(letters[1:3], 100, replace = TRUE), 
             sample(LETTERS[1:3], 100, replace = TRUE))
logmult::rc(tbl, se = "jackknife", ncpus = 1)
#> Initialising
#> Running start-up iterations..
#> Running main iterations.....
#> Done
#> Computing jackknife standard errors...
#> Error in getS3method("assoc", class(model)) : 
#>   length(class) == 1L is not TRUE

My R session info is as follows:

> sessionInfo()
R version 4.1.0 Patched (2021-07-06 r80602)
Platform: x86_64-apple-darwin17.0 (64-bit)
Running under: macOS Big Sur 10.16

Matrix products: default
BLAS:   /Library/Frameworks/R.framework/Versions/4.1/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/4.1/Resources/lib/libRlapack.dylib

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] stats     graphics  grDevices datasets  utils     methods   base     

other attached packages:
[1] logmult_0.7.3 gnm_1.1-1    

loaded via a namespace (and not attached):
 [1] MASS_7.3-54     compiler_4.1.0  Matrix_1.3-4    tools_4.1.0    
 [5] nnet_7.3-16     relimp_1.0-5    qvcalc_1.0.2    grid_4.1.0     
 [9] renv_0.14.0     lattice_0.20-44

Recommend Projects