funfits (PR#137)
novo@uiuc.edu
novo@uiuc.edu
Wed, 10 Mar 1999 05:42:02 +0100
Hi,
I spotted an inconsistency between the output of funfits under R, more
specifically "nnreg", and the one obtained under S-plus. Notice the difference
in the "Root MSE", "GVC" and "GVC cost=2". As a check mark, I am also including
the data summaries, confirming that I was in fact using the same data set.
Here's my output from both systems:
============================================================
$ Splus -e
S-PLUS : Copyright (c) 1988, 1996 MathSoft, Inc.
S : Copyright AT&T.
Version 3.4 Release 1 for HP 9000 Series, HP-UX 9.0.5 : 1996
Working data will be in /mnt/cba-econ/novo/.Data
> nn.nl
Summary of outout from neural net fit
see the component summary in the output list for
more details of the fitting process
call to nnreg :
nnreg(x = inc, y = imp, k1 = 1, k2 = 7)
# hidden units DF model DF residuals Root MSE GCV GCV cost=2
1 1 4 296 293.7 87400 89810
2 2 7 293 236.9 57460 60310
3 3 10 290 217.8 49090 52660
4 4 13 287 213.4 47580 52200
5 5 16 284 215.8 49200 55250
6 6 19 281 210.7 47400 54530
7 7 22 278 213.1 49000 57790
> summary(inc)
Min. 1st Qu. Median Mean 3rd Qu. Max.
1022 1926 3181 3312 4637 6152
> summary(imp)
Min. 1st Qu. Median Mean 3rd Qu. Max.
348.8 933.5 1932 1827 2483 5015
================================================================
================================================================
# using RedHat 5.1, Linux kernel 2.0.34
[anovo@gauss data]$ R
R : Copyright 1999, The R Development Core Team
Version 0.63.2 (January 12, 1999)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type "?license" or "?licence" for distribution details.
R is a collaborative project with many contributors.
Type "?contributors" for a list.
Type "demo()" for some demos, "help()" for on-line help, or
"help.start()" for a HTML browser interface to help.
Type "q()" to quit R.
[Previously saved workspace restored]
> summary(nn.nl)
Summary of outout from neural net fit
see the component summary in the output list for
more details of the fitting process
call to nnreg :
nnreg(x = inc, y = imp, k1 = 1, k2 = 7)
# hidden units DF model DF residuals Root MSE GCV GCV cost=2
1 1 4 296 292.5 86690 89080
2 2 7 293 236.6 57330 60170
3 3 10 290 214.8 47750 51220
4 4 13 287 210.0 46120 50600
5 5 16 284 208.4 45890 51530
6 6 19 281 204.8 44780 51510
7 7 22 278 194.0 40590 47870
> summary(inc)
Min. 1st Qu. Median Mean 3rd Qu. Max.
1022 1926 3181 3312 4637 6152
> summary(imp)
Min. 1st Qu. Median Mean 3rd Qu. Max.
348.8 933.5 1932.0 1827.0 2483.0 5015.0
================================================================
Alvaro Novo
ps. The library under S-plus was provided to me by one of the original authors,
Barbara Bailey (attached her computer directory). So, I guess we are safe on
that ground.
-- -- -- -- -- -- -- --
Alvaro A. Novo
2116 S. Orchard St., #304
Urbana, IL 61801
novo@uiuc.edu
anovo@ysidro.econ.uiuc.edu
http://www.students.uiuc.edu/~novo/Alvaro.htm
217-337-4893
-- -- -- -- -- -- -- --
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._