table.rq {quantreg} | R Documentation |
Function to produce a table of quantile regression results for a group of specified quantiles.
table.rq(formula, taus=c(0.05, 0.25, 0.5, 0.75, 0.95), method="br", ...)
formula |
formula for the linear model, see rq()
|
taus |
quantiles of interest |
method |
algorithmic method, for large problems method="fn"
would be preferred.
|
... |
other optional arguments passed to rq() .
|
This is only implemented for method="br"
, but modifications for
"fn"
would be quite straightforward. There is also an
implementation for making a latex table in the Splus version,
but this wasn't incorporated into the R package due to some
incompatibilities in the unix/system commands.
The function returns an array with dimensions (p, m, 3), where p is the
dimension of the parameter vector of the model specified by formula, m
is the number of quantiles specified by tau. For each coefficient at
each tau there is a point estimate and lower and upper limits of a
confidence interval. The object returned is of class table.rq
and can be plotted, or formatted into a latex style table.
data(stackloss) plot(table.rq(stack.loss~stack.x))#plot results of a quantile regression