[R] Data simulation with R

Arne Henningsen ahenningsen at email.uni-kiel.de
Thu Oct 4 12:45:42 CEST 2007


Hi Matiou:

On Thursday 30 August 2007 13:25, Matiou wrote:
> Hi,
>
> I am currently on a placement here at GSK for my studies, and I'm working
> on Heckman Models. I have to make simulations, in order to see whether
> these models are efficient or not.
>
>  I have to generate a dataset under the following constraints:
>
> - outcome is 0 or 1
> - one control group, one treatment group, there must be no treatment effect
> - generate one continuous variable and one binary variable which are both
> perfectly correlated to treatment, but not correlated to outcome
> - generate one continuous variable and one binary variable which are both
> perfectly correlated to outcome, but not correlated to treatment
> - generate one continuous variable and one binary variable which are both
> perfectly correlated to both treatment and outcome
>
> Problem is, it's my first time generating data, so I'm having quite a hard
> time... I usually use SAS, but I didn't manage to generate data using it.
> Some people told me it's quite easy to do with R, but I'm not really used
> to this program. Is it really possible to simulate this kind of data with R
> ? If it is, can someone help me ?

For an example, please take a look at the "example" section of 
function "selection" in the "micEcon" package.

HTH,
Arne

> Thanks in advance.

-- 
Arne Henningsen
Department of Agricultural Economics
University of Kiel
Olshausenstr. 40
D-24098 Kiel (Germany)
Tel: +49-431-880 4445
Fax: +49-431-880 1397
ahenningsen at agric-econ.uni-kiel.de
http://www.uni-kiel.de/agrarpol/ahenningsen/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : https://stat.ethz.ch/pipermail/r-help/attachments/20071004/fd96ff44/attachment.bin 


More information about the R-help mailing list