Perform projection onto submodels of selected sizes or a specified feature combination.
project(object, nv = NULL, vind = NULL, relax = NULL, ns = NULL, nc = NULL, intercept = NULL, seed = NULL, regul = 1e-04, ...)
Number of variables in the submodel (the variable combination is taken from the
Variable indices onto which the projection is done. If specified,
If TRUE, then the projected coefficients after L1-selection are computed
without any penalization (or using only the regularization determined by
Number of samples to be projected. Ignored if
Number of clusters in the clustered projection.
Whether to use intercept. Default is
A seed used in the clustering (if
Amount of regularization in the projection. Usually there is no need for regularization, but sometimes for some models the projection can be ill-behaved and we need to add some regularization to avoid numerical problems.
A list of submodels (or a single submodel if projection was performed onto a single variable combination), each of which contains the following elements:
The kl divergence from the reference model to the submodel.
Weights for each draw of the projected model.
Draws from the projected dispersion parameter.
Draws from the projected intercept.
Draws from the projected weight vector.
The order in which the variables were added to the submodel.
Whether or not the model contains an intercept.
### Usage with stanreg objects fit <- stan_glm(y~x, binomial())#> Error in stan_glm(y ~ x, binomial()): could not find function "stan_glm"vs <- varsel(fit)#> Error in get_refmodel(object, ...): object 'fit' not found# project onto the best model with 4 variables proj4 <- project(vs, nv = 4)#> Error in "vsel" %in% class(object): object 'vs' not found# project onto an arbitrary variable combination (variable indices 3,4 and 8) proj <- project(fit, vind=c(3,4,8))#> Error in "vsel" %in% class(object): object 'fit' not found