The smartpred library

The smartpred library consists of some modified existing and new functions to fix a problem relating to modelling functions such as lm and glm. The modified versions now remember the "parameters" of special smartened functions (bs, ns, scale and poly are supplied). We call this "smart" prediction. The parameters are saved on the fitted model object, and are retrieved when predictions are made from the model. Users can easily smarten their own functions - guidelines are given.

Download for S-PLUS 6.0

[ smart60.q ] (includes survreg(), survReg(), and gls().)

Download for R 1.7.x

[ smartpred_1.1-1.tar.gz ]


All users should read the Dummies Guide to Smart Prediction. Advanced users should read the Technical Guide to Smart Prediction. If you download for S-PLUS, here is some more documentation:



The smartpred library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Because the modifications to existing software have been provided in good faith, none of the authors warrant their accuracy nor can be held responsible for the consequences of their use.

[ Last modified: Wed Jul 9 22:13:24 NZST 2003 ]

[ Nb. there have been ]

Return to Thomas Yee's personal home page

Return to Departmental Homepage