prediction: Extract Predictions from a Model Object
In prediction: Tidy, Type-Safe 'prediction()' Methods

View source: R/prediction.R

prediction-package

R Documentation

Extract Predictions from a Model Object

Description

Extract predicted values via predict from a model object, conditional on data, and return a data frame.

Usage

prediction(model, ...)

## Default S3 method:
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  vcov = stats::vcov(model),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'Arima'
prediction(model, calculate_se = TRUE, ...)

## S3 method for class 'ar'
prediction(model, data, at = NULL, calculate_se = TRUE, ...)

## S3 method for class 'arima0'
prediction(model, data, at = NULL, calculate_se = TRUE, ...)

## S3 method for class 'betareg'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link", "precision", "variance", "quantile"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'bigLm'
prediction(model, data = NULL, calculate_se = FALSE, ...)

## S3 method for class 'bigglm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  calculate_se = TRUE,
  ...
)

## S3 method for class 'biglm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  calculate_se = TRUE,
  ...
)

## S3 method for class 'bruto'
prediction(
  model,
  data = NULL,
  at = NULL,
  type = "fitted",
  calculate_se = FALSE,
  ...
)

## S3 method for class 'clm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = TRUE,
  category,
  ...
)

## S3 method for class 'coxph'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("risk", "expected", "lp"),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'crch'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  type = c("response", "location", "scale", "quantile"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'earth'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = TRUE,
  category,
  ...
)

## S3 method for class 'fda'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'Gam'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link", "terms"),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'gausspr'
prediction(
  model,
  data,
  at = NULL,
  type = NULL,
  calculate_se = TRUE,
  category,
  ...
)

## S3 method for class 'gee'
prediction(model, calculate_se = FALSE, ...)

## S3 method for class 'glimML'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'glimQL'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'glm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  vcov = stats::vcov(model),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'glmnet'
prediction(
  model,
  data,
  lambda = model[["lambda"]][1L],
  at = NULL,
  type = c("response", "link"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'glmx'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'gls'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'hetglm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link", "scale"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'hurdle'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "count", "prob", "zero"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'hxlr'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  type = c("class", "probability", "cumprob", "location", "scale"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'ivreg'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'knnreg'
prediction(model, data, at = NULL, calculate_se = FALSE, ...)

## S3 method for class 'kqr'
prediction(model, data, at = NULL, calculate_se = FALSE, ...)

## S3 method for class 'ksvm'
prediction(
  model,
  data,
  at = NULL,
  type = NULL,
  calculate_se = TRUE,
  category,
  ...
)

## S3 method for class 'lda'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'lm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  vcov = stats::vcov(model),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'lme'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'loess'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  calculate_se = TRUE,
  ...
)

## S3 method for class 'lqs'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'mars'
prediction(
  model,
  data = NULL,
  at = NULL,
  type = "fitted",
  calculate_se = FALSE,
  ...
)

## S3 method for class 'mca'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'mclogit'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  vcov = stats::vcov(model),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'merMod'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  type = c("response", "link"),
  re.form = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'mlogit'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'mnlogit'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'mnp'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'multinom'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'naiveBayes'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'nls'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'nnet'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'plm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'polr'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'polyreg'
prediction(
  model,
  data = NULL,
  at = NULL,
  type = "fitted",
  calculate_se = FALSE,
  ...
)

## S3 method for class 'ppr'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'princomp'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'qda'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'rlm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  vcov = stats::vcov(model),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'rpart'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'rq'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = TRUE,
  ...
)

## S3 method for class 'selection'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = "response",
  calculate_se = FALSE,
  ...
)

## S3 method for class 'speedglm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = FALSE,
  ...
)

## S3 method for class 'speedlm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  calculate_se = FALSE,
  ...
)

## S3 method for class 'survreg'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "lp", "quantile", "uquantile"),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'svm'
prediction(model, data = NULL, at = NULL, calculate_se = TRUE, category, ...)

## S3 method for class 'svyglm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = TRUE,
  ...
)

## S3 method for class 'train'
prediction(
  model,
  data = find_data(model),
  at = NULL,
  type = c("raw", "prob"),
  ...
)

## S3 method for class 'tree'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = NULL,
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'truncreg'
prediction(model, data, at = NULL, calculate_se = FALSE, ...)

## S3 method for class 'vgam'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = FALSE,
  category,
  ...
)

## S3 method for class 'vglm'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "link"),
  calculate_se = TRUE,
  category,
  ...
)

## S3 method for class 'zeroinfl'
prediction(
  model,
  data = find_data(model, parent.frame()),
  at = NULL,
  type = c("response", "count", "prob", "zero"),
  calculate_se = FALSE,
  ...
)

prediction_summary(model, ..., level = 0.95)

Arguments

`model`	A model object, perhaps returned by `lm` or `glm`.
`...`	Additional arguments passed to `predict` methods.
`data`	A data.frame over which to calculate marginal effects. If missing, `find_data` is used to specify the data frame.
`at`	A list of one or more named vectors, specifically values at which to calculate the predictions. These are used to modify the value of `data` (see `build_datalist` for details on use).
`type`	A character string indicating the type of marginal effects to estimate. Mostly relevant for non-linear models, where the reasonable options are “response” (the default) or “link” (i.e., on the scale of the linear predictor in a GLM). For models of class “polr” (from `polr`), possible values are “class” or “probs”; both are returned.
`vcov`	A matrix containing the variance-covariance matrix for estimated model coefficients, or a function to perform the estimation with `model` as its only argument.
`calculate_se`	A logical indicating whether to calculate standard errors for observation-specific predictions and average predictions (if possible). The output will always contain a “calculate_se” column regardless of this value; this only controls the calculation of standard errors. Setting it to `FALSE` may improve speed.
`category`	For multi-level or multi-category outcome models (e.g., ordered probit, multinomial logit, etc.), a value specifying which of the outcome levels should be used for the `"fitted"` column. If missing, some default is chosen automatically.
`lambda`	For models of class “glmnet”, a value of the penalty parameter at which predictions are required.
`re.form`	An argument passed forward to `predict.merMod`.
`level`	A numeric value specifying the confidence level for calculating p-values and confidence intervals.

Details

This function is simply a wrapper around predict that returns a data frame containing the value of data and the predicted values with respect to all variables specified in data.

Methods are currently implemented for the following object classes:

“lm”, see lm
“glm”, see glm, glm.nb, glmx, hetglm, brglm
“ar”, see ar
“Arima”, see arima
“arima0”, see arima0
“bigglm”, see bigglm
“betareg”, see betareg
“bruto”, see bruto
“clm”, see clm
“coxph”, see coxph
“crch”, see crch
“earth”, see earth
“fda”, see fda
“Gam”, see gam
“gausspr”, see gausspr
“gee”, see gee
“glmnet”, see glmnet
“gls”, see gls
“glimML”, see betabin, negbin
“glimQL”, see quasibin, quasipois
“hurdle”, see hurdle
“hxlr”, see hxlr
“ivreg”, see ivreg
“knnreg”, see knnreg
“kqr”, see kqr
“ksvm”, see ksvm
“lda”, see lda
“lme”, see lme
“loess”, see loess
“lqs”, see lqs
“mars”, see mars
“mca”, see mca
“mclogit”, see mclogit
“mda”, see mda
“merMod”, see lmer, glmer
“mnp”, see mnp
“naiveBayes”, see naiveBayes
“nlme”, see nlme
“nls”, see nls
“nnet”, see nnet
“plm”, see plm
“polr”, see polr
“polyreg”, see polyreg
“ppr”, see ppr
“princomp”, see princomp
“qda”, see qda
“rlm”, see rlm
“rpart”, see rpart
“rq”, see rq
“selection”, see selection
“speedglm”, see speedglm
“speedlm”, see speedlm
“survreg”, see survreg
“svm”, see svm
“svyglm”, see svyglm
“tobit”, see tobit
“train”, see train
“truncreg”, see truncreg
“zeroinfl”, see zeroinfl

Where implemented, prediction also returns average predictions (and the variances thereof). Variances are implemented using the delta method, as described by Xu and Long 2005 \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1177/1536867X0500500405")}.

Value

A data frame with class “prediction” that has a number of rows equal to number of rows in data, or a multiple thereof, if !is.null(at). The return value contains data (possibly modified by at using build_datalist), plus a column containing fitted/predicted values ("fitted") and a column containing the standard errors thereof ("calculate_se"). Additional columns may be reported depending on the object class. The data frame also carries attributes used by print and summary, which will be lost during subsetting.

Examples

require("datasets")
x <- lm(Petal.Width ~ Sepal.Length * Sepal.Width * Species, data = iris)
# prediction for every case
prediction(x)

# prediction for first case
prediction(x, iris[1,])

# basic use of 'at' argument
summary(prediction(x, at = list(Species = c("setosa", "virginica"))))

# basic use of 'at' argument
prediction(x, at = list(Sepal.Length = seq_range(iris$Sepal.Length, 5)))

# prediction at means/modes of input variables
prediction(x, at = lapply(iris, mean_or_mode))

# prediction with multi-category outcome
## Not run: 
  library("mlogit")
  data("Fishing", package = "mlogit")
  Fish <- mlogit.data(Fishing, varying = c(2:9), shape = "wide", choice = "mode")
  mod <- mlogit(mode ~ price + catch, data = Fish)
  prediction(mod)
  prediction(mod, category = 3)

## End(Not run)

prediction documentation built on June 22, 2024, 10:18 a.m.