plot.mp: Interaction Plot for an "mp" Class Object.

Description Usage Arguments Details Value Examples

Description

This function plots interaction between received treatment and recommended treatment, which provides an estimate of treatment effect of the identified subgroup.

Usage

1
2
## S3 method for class 'mp'
plot(x, penalty_index, ...)

Arguments

x

A fitted "mp" class object returned by mpersonalzied function

penalty_index

The index of penalty parameter configuration in mp$penalty_parameter_sequence. When mp$penalty = "none", penalty_index is automatically set to be 1.

...

not used

Details

In the interaction plot, each point is the group mean given a received treatment and a recommended treatment. Although usually overestimating treatment effect in training set, interaction plots provides a sanity check for treatment recommendation rules. Given a specific index of penalty parameter, the function plots corresponding interaction plots.

Value

A list object with each element as the interaction plots for a penalty parameter configuration.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
set.seed(123)
sim_dat  = simulated_dataset(n = 200, problem = "meta-analysis")
Xlist = sim_dat$Xlist; Ylist = sim_dat$Ylist; Trtlist = sim_dat$Trtlist

# fit different rules with SGL penalty for this meta-analysis problem
mp_mod_diff = mpersonalized(problem = "meta-analysis",
                            Xlist = Xlist, Ylist = Ylist, Trtlist = Trtlist,
                            penalty = "lasso", single_rule = FALSE)

# interaction plot of the 5th penalty parameter
plots = plot(x = mp_mod_diff, penalty_index = 5)
set.seed(NULL)

chenshengkuang/mpersonalized documentation built on May 28, 2019, 7:16 p.m.