weighted.residuals {stats} | R Documentation |
Computed weighted residuals from a linear model fit.
weighted.residuals(obj, drop0 = TRUE)
obj |
R object, typically of class lm or
glm . |
drop0 |
logical. If TRUE , drop all cases with
weights == 0 . |
Weighted residuals are based on the deviance residuals, which for
a lm
fit are the raw residuals Ri
multiplied by wi^0.5, where wi are the
weights
as specified in lm
's call.
Dropping cases with weights zero is compatible with
influence
and related functions.
Numeric vector of length n', where n' is the number of
of non-0 weights (drop0 = TRUE
) or the number of
observations, otherwise.
residuals
, lm.influence
, etc.
example("lm") all.equal(weighted.residuals(lm.D9), residuals(lm.D9)) x <- 1:10 w <- 0:9 y <- rnorm(x) weighted.residuals(lmxy <- lm(y ~ x, weights = w)) weighted.residuals(lmxy, drop0 = FALSE)