List of supported models

List of model classes accepted by model.avg, model.sel, and dredge.

Details

Fitted model objects that can be used with model selection and model averaging functions include those produced by:

  • lm, glm (package stats);

  • rlmMASS, glm.nbMASS and polrMASS (MASS);

  • multinomnnet (nnet);

  • lmenlme, glsnlme (nlme);

  • lmerlme4, glmerlme4 (lme4);

  • cpglmcplm, cpglmmcplm (cplm);

  • gammgcv, gammmgcv* (mgcv);

  • gamm4gamm4* (gamm4);

  • gamlssgamlss (gamlss);

  • glmmMLglmmML (glmmML);

  • glmmadmb (glmmADMB from R-Forge);

  • glmmTMBglmmTMB (glmmTMB);

  • MCMCglmmMCMCglmm* (MCMCglmm);

  • asreml (non-free commercial package asreml; allows only for REML comparisons);

  • hurdlepscl, zeroinflpscl (pscl);

  • negbinaod, betabinaod (class "glimML"), package aod);

  • aodmlaods3, aodqlaods3 (aods3);

  • betaregbetareg (betareg);

  • brglmbrglm (brglm);

  • *sarlm models, spautolmspatialreg (spatialreg);

  • spmlsplm* (if fitted by ML, splm);

  • coxphsurvival, survregsurvival (survival);

  • coxmecoxme, lmekincoxme (coxme);

  • rqquantreg (quantreg);

  • clmordinal and clmmordinal (ordinal);

  • logistflogistf (logistf);

  • crunchcaper*, pglscaper (caper);

  • maxlikemaxlike (maxlike);

  • most "unmarkedFit" objects from package unmarked);

  • markRMark and related functions (class mark from package RMark). Currently dredge can only manipulate formula element of the argument model.parameters, keeping its other elements intact;

  • fitdistrMASS mostly useful for model selection with model.sel. Use of fitdistr2=updateable wrapper function is recommended.

Generalized Estimation Equation model implementations: geeglmgeepack from package geepack, geegee from gee, geemgeeM from geeM, wgeewgeesel from wgeesel, and yags from yags (on R-Forge) can be used with QIC as the selection criterion.

Further classes may also be supported, in particular if they inherit from one of the classes listed above. In general, models averaged using model.avg can belong to different types (e.g. glm and gam), provided they use the same data and response, and, obviously, if it is valid to do so. This also applies to the construction of model selection tables using model.sel.

Note

* In order to use gamm, gamm4, spml (> 1.0.0), crunch or MCMCglmm with dredge, an updateable wrapper for these functions should be created.

See also

model.avg, model.sel and dredge.