From: Esmail Bonakdarian <esmail.js_at_gmail.com>

Date: Tue, 20 May 2008 09:24:56 -0400

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Tue 20 May 2008 - 13:28:11 GMT

Date: Tue, 20 May 2008 09:24:56 -0400

Hello all,

I need to tap into the collective wisdom of the group re an issue of efficiency.

A sketch of the situation:

Let's say 4000 observations in variables Y, X1, X2 , X3 and X4.

I would like to feed various combinations of this expression

Y ~ X1+X2+X3+X4 + I(X1^2)+I(X2^2)+I(X3^2)+I(X4^2) + X1*X2 + X1*X3 + X1*X4 + X2*X3 + X2*X4 + X3*X4

repeatedly to glm(). (I really have little knowledge about how R or glm() works internally)

Let's say I call glm() 200 times with various combinations does it make sense to compute these various factors based on X1 .. X4 and store them in a file along with the original data, and then use that file for the glm() calls or will the overhead of computing these factors be so small that it's not worth computing these values ahead of time and storing them in a file?

This is simplified example, I actually have 20 original variables rather than the 4 I show above. I hope this made some sense.

Thanks,

Esmail

ps: If it makes sense to preprocess X1,X2,X3 and X4 to generate a new

file that contains the values for

X1, X2, X3, X4, I(X1^2), I(X2^2), I(X3^2), I(X4^2), X1*X2, X1*X3, X1*X4 ,X2*X3, X2*X4, X3*X4

is there an easy way to take the expression at the top of the message and convert the values in the original dataframe and compute them so that I can write them out to a new file? ______________________________________________R-help_at_r-project.org mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Tue 20 May 2008 - 13:28:11 GMT

Archive maintained by Robert King, hosted by
the discipline of
statistics at the
University of Newcastle,
Australia.

Archive generated by hypermail 2.2.0, at Tue 20 May 2008 - 13:30:40 GMT.

*
Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help.
Please read the posting
guide before posting to the list.
*