| % File src/library/stats/man/predict.Rd |
| % Part of the R package, https://www.R-project.org |
| % Copyright 1995-2020 R Core Team |
| % Distributed under GPL 2 or later |
| |
| \name{predict} |
| \title{Model Predictions} |
| \usage{ |
| predict (object, \dots) |
| } |
| \alias{predict} |
| \arguments{ |
| \item{object}{a model object for which prediction is desired.} |
| \item{\dots}{additional arguments affecting the predictions produced.} |
| } |
| \description{ |
| \code{predict} is a generic function for predictions from the results of |
| various model fitting functions. The function invokes particular |
| \emph{methods} which depend on the \code{\link{class}} of |
| the first argument. |
| } |
| \details{ |
| Most prediction methods which are similar to those for linear models |
| have an argument \code{newdata} specifying the first place to look for |
| explanatory variables to be used for prediction. Some considerable |
| attempts are made to match up the columns in \code{newdata} to those |
| used for fitting, for example that they are of comparable types and |
| that any factors have the same level set in the same order (or can be |
| transformed to be so). |
| |
| Time series prediction methods in package \pkg{stats} have an argument |
| \code{n.ahead} specifying how many time steps ahead to predict. |
| |
| Many methods have a logical argument \code{se.fit} saying if standard |
| errors are to returned. |
| } |
| \value{ |
| The form of the value returned by \code{predict} depends on the |
| class of its argument. See the documentation of the |
| particular methods for details of what is produced by that method. |
| } |
| \seealso{ |
| \code{\link{predict.glm}}, |
| \code{\link{predict.lm}}, |
| \code{\link{predict.loess}}, |
| \code{\link{predict.nls}}, |
| \code{\link{predict.poly}}, |
| \code{\link{predict.princomp}}, |
| \code{\link{predict.smooth.spline}}. |
| |
| \link{SafePrediction} for prediction from (univariable) polynomial and |
| spline fits. |
| |
| For time-series prediction, |
| \code{\link{predict.ar}}, |
| \code{\link{predict.Arima}}, |
| \code{\link{predict.arima0}}, |
| \code{\link{predict.HoltWinters}}, |
| \code{\link{predict.StructTS}}. |
| } |
| \references{ |
| Chambers, J. M. and Hastie, T. J. (1992) |
| \emph{Statistical Models in S}. |
| Wadsworth & Brooks/Cole. |
| } |
| \examples{ |
| \dontshow{old <- Sys.getlocale("LC_COLLATE") |
| invisible(Sys.setlocale("LC_COLLATE", "C"))} |
| require(utils) |
| |
| ## All the "predict" methods found |
| ## NB most of the methods in the standard packages are hidden. |
| ## Output will depend on what namespaces are (or have been) loaded. |
| ## IGNORE_RDIFF_BEGIN |
| for(fn in methods("predict")) |
| try({ |
| f <- eval(substitute(getAnywhere(fn)$objs[[1]], list(fn = fn))) |
| cat(fn, ":\n\t", deparse(args(f)), "\n") |
| }, silent = TRUE) |
| ## IGNORE_RDIFF_END |
| \dontshow{invisible(Sys.setlocale("LC_COLLATE", old))} |
| } |
| \keyword{methods} |