Take a look at the attached for some possible alternatives using R. Good luck with your research, David Booth

Mahyar Vahedi Saheli , in Stata you can type:

findit crossfold

and you can install the crossfold package (see the end of this post). If the crossfold package does not work, it should be quite easy to make your own k-fold cross-validation in Stata, the pseudo-algorithm will be:

preserve

* (1) Shuffle the dataset randomly:

. set seed 666

. tempvar randorder

. gen `randorder' = runiform()

. sort `randorder'

* (2) Split the dataset into k groups (let's say k = 10):

.egen splitk = cut(randorder), group(10)

* (3) Estimate your model with the k - 1 groups and test the model in the group k:

.(your model here) ... if inlist(splitk,2,3,4,5,6,7,8,9,10)

.(your performance measure here) ... if k == 1

.(your model here) ... if inlist(splitk,1,3,4,5,6,7,8,9,10)

.(your performance measure here) ... if k == 2

.(your model here) ... if inlist(splitk,1,2,4,5,6,7,8,9,10)

.(your performance measure here) ... if k == 3

...

restore

*(4) Summarize the results of the performance measures obtained in step 3

------------------------------------------------------------------------------------------------------

package crossfold from http://fmwww.bc.edu/RePEc/bocode/c

TITLE

'CROSSFOLD': module to perform k-fold cross-validation

DESCRIPTION/AUTHOR(S)

crossfold performs k-fold cross-validation on a specified model

in order to evaluate a model's ability to fit out-of-sample

data. This procedure splits the data randomly into k partitions,

then for each partition it fits the specified model using the

other k-1 groups and uses the resulting parameters to predict

the dependent variable in the unused group.

KW: cross-validation

KW: k-fold

Requires: Stata version 11

Distribution-Date: 20120223

Author: Ben Daniels

Support: email [email protected]

INSTALLATION FILES (click here to install)

crossfold.ado

crossfold.sthlp

@ Rolando Gonzales

Thanks every body for helping.