Add Support for Additional Model Classes

[leeper]

This is a list of requested model classes to potentially support in prediction. It is sorted by completion status of model support, and then by function name. In order to support a model class, the package needs to provide a predict() method. If this is not provided, it is not (presently) supportable.

Supported

• [x] arm::bayesglm() (inherits from "glm")
• [x] aod::betabin(), aod::negbin(), aod::quasibin(), aod::quasipois(),
• [x] betareg::betareg() (class "betareg"), with predict() method (but no se.fit arg)
• [x] biglm::biglm() and biglm::bigglm()
• [x] brglm::brglm() (inherits from "glm")
• [x] mda::bruto()
• [x] ordinal::clm()
• [x] crch censored/truncated regression methods (#4)
• [x] earth::earth()
• [x] mda::fda()
• [x] gam::gam()
• [x] kernlab::gausspr()
• [x] gee::gee()
• [x] stats::glm()
• [x] glmnet::glmnet()
• [x] glmx::glmx() (class "glmx")
• [x] MASS::glm.nb() (inherits from "glm")
• [x] glmx::hetglm() (class "hetglm")
• [x] pscl::hurdle()
• [x] AER::ivreg()
• [x] caret::knnreg()
• [x] kernlab::kqr()
• [x] kernlab::ksvm()
• [x] MASS::lda()
• [x] stats::lm()
• [x] lme4 (lmer(), glmer(), ...) (but lme4:::predict.merMod() has no se.fit argument)
• [x] nlme
  • nlme:::predict.lme() has no se.fit or type arguments
  • nlme:::predict.gls() has no se.fit argument.
• [x] stats::loess() (predict() method uses se rather than se.fit)
• [x] MASS::lqs()
• [x] mda::mars()
• [x] MASS::mca()
• [x] mclogit::mclogit() (class "mclogit"), which is basically "glm"
• [x] mda::mda()
• [x] mlogit::mlogit()
• [x] mnlogit::mnlogit()
• [x] MNP::mnp()
• [x] nnet::multinom() or any nnet model generally
• [x] e1071::naiveBayes()
• [x] nls (requires setting model = TRUE in original call; and then getting term(object[["model"]]))
• [x] MASS::polr() (has predict() method with type = c("class", "probs"))
  • [x] arm::bayespolr() (covered by general "polr" method)
• [x] mda::polyreg()
• [x] caret::predict()
• [x] MASS::qda()
• [x] quantreg::rq()
• [x] rpart::rpart()
• [x] sampleSelection::selection() (class "select")
• [x] speedglm::speedglm() and speedglm::speedlm()
• [x] survival::survreg()
  • coxph class has different type values for predict(): c("lp", "risk", "expected")
• [x] survey::svyglm()
• [x] AER::tobit()
• [x] truncreg::truncreg()
• [x] pscl::zeroinfl()

Potentially supportable

• [ ] bamlss::bamlss()
• [ ] dynlm::dynlm()
• [ ] gnm::gnm()
• [ ] LARF::larf()
• [ ] bbmle::mle2()
• [ ] mpt::mpt()
• [ ] np (non-parametric regression)
• [ ] rms
• [ ] "stanreg" objects from rstanarm
• [ ] VGAM::vglm()
• [ ] mgcv::bam()
• [ ] mgcv::gam()
• [ ] gamlss::gamlss()
• [ ] mgcv::gamm()
• [ ] VGAM::vgam()
• [ ] spdep
• [ ] sphet::spreg()
• [ ] splm::spml()
• [ ] splm::spgm()

Not currently supportable

• [ ] censReg (has a margEff() generic but no predict() method)
• [ ] ordinal::clmm() (no predict() method)
• [ ] lfe::felm() (no predict() method)
• [ ] dispmod: lm.disp(), glm.binomial.disp(), glm.poisson.disp() (no predict() method)
• [ ] geepack: geeglm(), geese(), ordgee() (no predict() methods)
• [ ] ghyp (ORPHANED)
• [ ] gmm::gmm() (no predict() method)
• [ ] gmnl::gmnl() (no predict() method)
• [ ] GeneralizedHyperbolic::hyperblm() (no predict() method)
• [ ] ivprobit::ivprobit() (no predict() method)
• [ ] class::knn() (does not construct a model object)
• [ ] sem::tsls() (no predict() method)
• [ ] plm::plm() (non-exported predict method)
• [ ] plm::pglm()
• [ ] survey::svyolr() (no predict() method)

(Note: this is migrated from: https://github.com/leeper/margins/issues/3)

[bgall]

@leeper I'd add the other survey package functions. While many of them are based on survey::svyglm() which are class glm, lm, and svyglm, the survey::svyolr() function is NOT from MASS::polr() and is of class svyolr.

[tappek]

For models produced by plm::plm(), there is a predict method available since plm version 2.6-2.