plot {crisp} | R Documentation |
Plots Fit from crisp
or crispCV
.
Description
This function plots fit of the class crispCV
, or class crisp
with a user-specified tuning parameter.
Usage
## S3 method for class 'crisp'
plot(x, lambda.index, title = NULL, x1lab = NULL,
x2lab = NULL, min = NULL, max = NULL, cex.axis = 1, cex.lab = 1,
color1 = "seagreen1", color2 = "steelblue1", color3 = "darkorchid4",
...)
## S3 method for class 'crispCV'
plot(x, title = NULL, x1lab = NULL, x2lab = NULL,
min = NULL, max = NULL, cex.axis = 1, cex.lab = 1,
color1 = "seagreen1", color2 = "steelblue1", color3 = "darkorchid4",
...)
Arguments
x |
An object of class |
lambda.index |
The index for the desired value of lambda, i.e., |
title |
The title of the plot. By default, the value of lambda is noted. |
x1lab |
The axis label for the first covariate. By default, it is "X1". |
x2lab |
The axis label for the second covariate. By default, it is "X2". |
min , max |
The minimum and maximum y-values, respectively, to use when plotting the fit. By default, they are chosen to be the minimum and maximum of all of the fits, i.e., the minimum and maximum of |
cex.axis |
The magnification to be used for axis annotation relative to the current setting of |
cex.lab |
The magnification to be used for x and y labels relative to the current setting of |
color1 , color2 , color3 |
The colors to use to create the color gradient for plotting the response values. At least the first two must be specified, or the defaults of |
... |
Additional arguments to be passed, which are ignored in this function. |
Value
None.
Examples
## Not run:
#See ?'crisp-package' for a full example of how to use this package
#generate data (using a very small 'n' for illustration purposes)
set.seed(1)
data <- sim.data(n = 15, scenario = 2)
#fit model for a range of tuning parameters, i.e., lambda values
#lambda sequence is chosen automatically if not specified
crisp.out <- crisp(X = data$X, y = data$y)
#or fit model and select lambda using 2-fold cross-validation
#note: use larger 'n.fold' (e.g., 10) in practice
crispCV.out <- crispCV(X = data$X, y = data$y, n.fold = 2)
#plot the estimated relationships between two predictors and outcome
#do this for a specific fit
plot(crisp.out, lambda.index = 25)
#or for the fit chosen using cross-validation
plot(crispCV.out)
## End(Not run)