SMLE (version 0.3.1)

plot.smle: Plots to visualize the SMLE screening step

Description

This function returns two plot windows. By default, the first contains 4 plots to assess: 1) log-likelihood, 2) Euclidean distance between the current and the previous coefficient estimates, 3) the number of tries in tuning parameter "u" in IHT algorithm (see "Ucheck" in SMLE), and 4) the number of features changed in the current active set. By default, the second plot shows the solution path (estimated coefficient by iteration step) for selected features.

Usage

# S3 method for smle
plot(x, Display = c("top_row", "all"), num_path = NULL,
  which_path = NULL, out_plot = 5, ...)

Arguments

x

Fitted "smle" object from SMLE.

Display

For the solution path plot, show path for the most significant coefficients(top_row) or for all coefficients(all).

num_path

Number of top coefficients to be shown in solution path plot if type = "top_row". Default in solution path plot is 5.

which_path

A vector to control which features are shown in addition to the paths for the most significant coefficients if type ="top_row".

out_plot

A number from 1 to 5 indicating which plot is to be shown in the separate window; the default for solution path plot is "5". See Description for plot labels 1-4.

...

Other graphical parameters to plot.

Value

No return value, called for side effects.

Examples

# NOT RUN {
Data<-Gen_Data(correlation="MA",family = "gaussian")
fit<-SMLE(Data$Y,Data$X,k=20,family = "gaussian")
plot(fit)

# }