fixedse {lfe} | R Documentation |
Compute standard errors for fixed effects
Description
fixedse computes the standard errors for the fixed effects when there is only one.
While getfe()
can provide standard errors, it does so by bootstrapping
for general estimable functions. In the special case that there's only a single fixed
effect, and the estimable function is just the levels, this function can be used to
compute the fixed effects without bootstrapping. It requires that felm()
is run with keepX=TRUE.
Usage
fixedse(est, lhs = NULL, E)
Arguments
est |
'felm' object. The result of a call to |
lhs |
character. Name of the left hand side, if more than one. |
E |
Matrix. Estimable function. Not used at the moment. |
Value
numeric. Vector of standard errors.
Examples
x <- rnorm(1000)
f <- factor(sample(5, 1000, replace = TRUE))
y <- x + (1:5)[f] + rnorm(1000)
est <- felm(y ~ x | f, keepX = TRUE)
# both bootstrap and computed se:
cbind(getfe(est, ef = efactory(est, "ref"), se = TRUE), fse = fixedse(est))
# compare with lm:
summary(lm(y ~ x + f - 1))
[Package lfe version 3.1.1 Index]