All Times EDT
Virtual
Cgam: An R Package for the Constrained Generalized Additive Model (308529)
*Xiyue Liao, California State University, Long BeachMary C Meyer , Colorado State University
Keywords: constrained generalized additive model,R, graphical routine
The cgam package contains routines to fit the generalized additive model where the components may be modeled with shape and smoothness assumptions. The main routine is the R package cgam and nineteen symbolic routines are provided to indicate the relationship between the response and each predictor, which satisfies constraints such as monotonicity, convexity, their combinations, tree, and umbrella orderings. The user may specify constrained splines to fit the individual components for continuous predictors, and various types of orderings for the ordinal predictors. In addition, the user may specify parametrically modeled covariates. For generalized models, the fit is obtained through iteratively re-weighted cone projections. The cone information criterion (CIC) is provided and may be used to compare fits for combinations of variables and shapes. This package is available from the Comprehensive R Archive Network (CRAN) at https://CRAN.R-project.org/package=cgam.