GAM: Stata module for generalised additive models

Patrick Royston () and Gareth Ambler ()
Additional contact information
Patrick Royston: UK Medical Research Council
Gareth Ambler: University College London

Statistical Software Components from Boston College Department of Economics

Abstract: gam fits a generalized or proportional hazards additive model (GAM) by mazimizing a penalized log likelihood function. Each component of the resulting estimated function of the covariates is a cubic smoothing spline. The smoothness of each component function is determined by the 'equivalent degrees of freedom' of the corresponding covariate. Models supported: Normal (Gaussian) errors, binomial, Poisson, gamma, Cox (now with Stata's stcox), and link functions among identity, log, logit and inverse. This package is an update to accommodate the latest versions of the Windows operating system (specifically, Win 2000 and XP) and supersedes the version published in the STB (Royston P, Ambler G (1998) Generalized additive models. Stata Technical Bulletin 42: 38-43.)

Language: Stata
Requires: Stata version 6.0 for Windows
Keywords: generalized additive models; proportional hazards (search for similar items in EconPapers)
Date: Written 2002-10-18

Downloads: (external link)
http://fmwww.bc.edu/repec/bocode/g/gam.zip routine and executables (application/zip)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Ordering information: This software item can be ordered from
http://repec.org/docs/ssc.php

Access Statistics for this software item

More software in Statistical Software Components from Boston College Department of Economics
Address: Boston College, 140 Commonwealth Avenue, Chestnut Hill MA 02467 USA
Contact information at EDIRC.
Series data maintained by Christopher F Baum ().