prediction
prediction copied to clipboard
Add Support for Additional Model Classes
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"
), withpredict()
method (but nose.fit
arg) - [x]
biglm::biglm()
andbiglm::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()
, ...) (butlme4:::predict.merMod()
has nose.fit
argument) - [x] nlme
-
nlme:::predict.lme()
has nose.fit
ortype
arguments -
nlme:::predict.gls()
has nose.fit
argument.
-
- [x]
stats::loess()
(predict()
method usesse
rather thanse.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 gettingterm(object[["model"]])
) - [x]
MASS::polr()
(haspredict()
method withtype = c("class", "probs")
)- [x]
arm::bayespolr()
(covered by general"polr"
method)
- [x]
- [x]
mda::polyreg()
- [x]
caret::predict()
- [x]
MASS::qda()
- [x]
quantreg::rq()
- [x]
rpart::rpart()
- [x]
sampleSelection::selection()
(class"select"
) - [x]
speedglm::speedglm()
andspeedglm::speedlm()
- [x]
survival::survreg()
- coxph class has different
type
values forpredict()
:c("lp", "risk", "expected")
- coxph class has different
- [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 nopredict()
method) - [ ]
ordinal::clmm()
(nopredict()
method) - [ ]
lfe::felm()
(nopredict()
method) - [ ] dispmod:
lm.disp()
,glm.binomial.disp()
,glm.poisson.disp()
(nopredict()
method) - [ ] geepack:
geeglm()
,geese()
,ordgee()
(nopredict()
methods) - [ ] ghyp (ORPHANED)
- [ ]
gmm::gmm()
(nopredict()
method) - [ ]
gmnl::gmnl()
(nopredict()
method) - [ ]
GeneralizedHyperbolic::hyperblm()
(nopredict()
method) - [ ]
ivprobit::ivprobit()
(nopredict()
method) - [ ]
class::knn()
(does not construct a model object) - [ ]
sem::tsls()
(nopredict()
method) - [ ]
plm::plm()
(non-exported predict method) - [ ]
plm::pglm()
- [ ]
survey::svyolr()
(nopredict()
method)
(Note: this is migrated from: https://github.com/leeper/margins/issues/3)
@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.
For models produced by plm::plm()
, there is a predict
method available since plm
version 2.6-2.