Displaying 2 results from an estimated 2 matches for "sasseen".
Did you mean:
sandeen
2009 Oct 30
0
different L2 regularization behavior between lrm, glmnet, and penalized? (original question)
...glmnet case should be similar, but I don't know the details here. It
seems glmnet uses its own peculiar way of defining the penalty, but some
choice of scaling should be able to bring glmnet in line as well.
Kind regards,
Jelle
________________________________
From: Robert V (Bob) Sasseen [mailto:sasseen@ai.sri.com]
Sent: 29 October 2009 19:32
To: Goeman, J.J. (MSTAT)
Subject: different L2 regularization behavior between lrm,
glmnet, and penalized? (original question)
Jelle,
Below is the original question. The formatting apparently got a
bit messed up when it was parsed...
2009 Oct 14
1
different L2 regularization behavior between lrm, glmnet, and penalized?
...ut if anyone familiar with these packages has
insight into why the results differ, I'd appreciate hearing about it. I'm
new to R. Thanks. (Version info below. Same results on Windows and Solaris
8, except that I haven't gotten glmnet to compile on the latter.)
Robert V (Bob) Sasseen
[1]sasseen at ai.sri.com
> # Some x values (predictive var).
> x = c(-2, -2, -2, -2, -1, -1, -1, 2, 2, 2, 3, 3, 3, 3)
> # Some z values--the observed outcome.
> # Effect is that for
> # x = -2, p = 1/4;
> # x = -1, p = 1/3;
> # x = 2, p = 2/3;
> #...