View source: R/mainFunctions.R
bytau.plot.rq.pen.seq.cv | R Documentation |
Produces plots of how coefficient estimates vary by quantile for models selected by using cross validation.
## S3 method for class 'rq.pen.seq.cv'
bytau.plot(
x,
septau = TRUE,
cvmin = TRUE,
useDefaults = TRUE,
vars = NULL,
...
)
x |
An rq.pen.seq.cv object |
septau |
Whether optimal tuning parameters are estimated separately for each quantile. |
cvmin |
Whether the minimum cv error should be used or the one standard error rule. |
useDefaults |
Set to FALSE if you want to use something besides minimum cv or 1se. |
vars |
Index of the variables to plot with 1 being the intercept, 2 being the first predictor, etc. Default is to include all variables. |
... |
Additional parameters sent to coef() |
Returns plots of coefficient estimates varying by quantile.
Ben Sherwood, ben.sherwood@ku.edu
set.seed(1)
x <- matrix(runif(800),nrow=100)
y <- 1 + x[,1] - 3*x[,5] + (1+x[,4])*rnorm(100)
lmcv <- rq.pen.cv(x,y,tau=seq(.1,.9,.1))
bytau.plot(lmcv)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.