bug with boot.sw98 function (PR#8999)

Full_Name: Nuno Monteiro
Version: 2.3.1
OS: Windows XP HE
Submission from: (NULL) (84.9.38.207)


I'm using the FEAR library to perform Data Envelopment analysis with a 36,000
obs dataset.

The function dea is working fine but then when I try to use the boot.sw98 to
come up with some sensitivity analysis I get the following error:

boot.sw98(XOBS=x,YOBS=y,NREP=100,DHAT=dhat,RTS=3,ORIENTATION=2)
Error in 0:L : NA/NaN argument
In addition: Warning message:
longer object length
        is not a multiple of shorter object length in: kappam * Gcounts

What does this mean? Is this because I have too many observations? What can I do
to fix it?

Please let me know if you need further information.

Thank you in advance for your cooperation.

  

Regards,
Nuno

PS here is a transcript of the script I'm using

library(FEAR)
abc <- read.csv("Jul_data.csv",header=TRUE)
x=matrix(nrow=1,ncol=39182)
x[1,]=abc$apr_repayment
y=matrix(nrow=7,ncol=39182)
y[1,]=abc$pcadv
y[2,]=abc$until
y[3,]=abc$cashback_rate
y[4,]=abc$self_certify_ind_d
y[5,]=abc$incentive_ind_d
y[6,]=abc$features_1
y[7,]=abc$discount
dhat=dea(XOBS=x,YOBS=y,RTS=3,ORIENTATION=2)
boot.sw98(XOBS=x,YOBS=y,NREP=100,DHAT=dhat,RTS=3,ORIENTATION=2)