ranef.plm: Extract the Random Effects

In ycroissant/plm: Linear Models for Panel Data

Extract the Random Effects

Description

Function to calculate the random effects from a plm object (random effects model).

Usage

## S3 method for class 'plm'
ranef(object, effect = NULL, ...)

Arguments

object	an object of class "plm", needs to be a fitted random effects model,
effect	NULL, "individual", or "time", the effects to be extracted, see Details,
...	further arguments (currently not used).

Details

Function ranef calculates the random effects of a fitted random effects model. For one-way models, the effects of the estimated model are extracted (either individual or time effects). For two-way models, extracting the individual effects is the default (both, argument effect = NULL and effect = "individual" will give individual effects). Time effects can be extracted by setting effect = "time".

Not all random effect model types are supported (yet?).

Value

A named numeric with the random effects per dimension (individual or time).

Author(s)

Kevin Tappe

See Also

fixef() to extract the fixed effects from a fixed effects model (within model).

Examples

data("Grunfeld", package = "plm")
m1 <- plm(inv ~ value + capital, data = Grunfeld, model = "random")
ranef(m1) # individual random effects

# compare to random effects by ML estimation via lme from package nlme
library(nlme)
m2 <- lme(inv ~ value + capital, random = ~1|firm, data = Grunfeld)
cbind("plm" = ranef(m1), "lme" = unname(ranef(m2)))

# two-ways RE model, calculate individual and time random effects
data("Cigar", package = "plm")
tw <- plm(sales ~ pop + price, data = Cigar, model = "random", effect = "twoways")
ranef(tw)                   # individual random effects
ranef(tw, effect = "time")  # time random effects

ycroissant/plm documentation built on July 8, 2024, 3:59 a.m.