res.check {GJRM} | R Documentation |
Diagnostic plots for discrete/continuous response margins
Description
It produces diagnostic plots based on (randomised) quantile residuals.
Usage
res.check(x, intervals = FALSE, n.sim = 100, prob.lev = 0.05)
Arguments
x |
A fitted |
intervals |
If |
n.sim |
Number of replicate datasets used to simulate quantiles of the residual distribution. |
prob.lev |
Overall probability of the left and right tails of the probabilities' distributions used for interval calculations. |
Details
If the model fits the response well then the plots should look normally distributed.
When fitting models with discrete and/or continuous margins, four plots will be produced. In this case,
the arguments main2
and xlab2
come into play and allow for different
labelling across the plots.
Value
qr |
It returns the (randomised) quantile residuals for the continuous or discrete margin when fitting a model that involves a binary response. |
qr1 |
As above but for first equation (this applies when fitting models with continuous/discrete margins). |
qr2 |
As above but for second equation. |
Author(s)
Maintainer: Giampiero Marra giampiero.marra@ucl.ac.uk