Fixed and random effects estimators for truncated or censored limited dependent variable
pldv(
formula,
data,
subset,
weights,
na.action,
model = c("fd", "random", "pooling"),
index = NULL,
R = 20,
start = NULL,
lower = 0,
upper = +Inf,
objfun = c("lsq", "lad"),
sample = c("cens", "trunc"),
...
)
a symbolic description for the model to be estimated,
a data.frame
,
see lm
,
see lm
,
see lm
,
one of "fd"
, "random"
or "pooling"
,
the indexes, see pdata.frame()
,
the number of points for the gaussian quadrature,
a vector of starting values,
the lower bound for the censored/truncated dependent variable,
the upper bound for the censored/truncated dependent variable,
the objective function for the fixed effect model,
one of "lsq"
for least squares and "lad"
for least absolute
deviations,
"cens"
for a censored (tobit-like) sample,
"trunc"
for a truncated sample,
further arguments.
An object of class c("plm","panelmodel")
.
pldv
computes two kinds of models : maximum likelihood estimator
with an assumed normal distribution for the individual effects and
a LSQ/LAD estimator for the first-difference model.
HONO:92plm