polle (version 1.6.2)

fit_g_functions: Fit g-functions

Description

fit_g_functions is used to fit a list of g-models.

Usage

fit_g_functions(policy_data, g_models, full_history = FALSE)

Arguments

policy_data

Policy data object created by policy_data().

g_models

List of action probability models/g-models for each stage created by g_empir(), g_glm(), g_rf(), g_sl() or similar functions.

full_history

If TRUE, the full history is used to fit each g-model. If FALSE, the single stage/"Markov type" history is used to fit each g-model.

Examples

library("polle")
### Simulating two-stage policy data
d <- sim_two_stage(2e3, seed=1)
pd <- policy_data(d,
                  action = c("A_1", "A_2"),
                  covariates = list(L = c("L_1", "L_2"),
                                    C = c("C_1", "C_2")),
                  utility = c("U_1", "U_2", "U_3"))
pd

# fitting a single g-model across all stages:
g_functions <- fit_g_functions(policy_data = pd,
                               g_models = g_glm(),
                               full_history = FALSE)
g_functions

# fitting a g-model for each stage:
g_functions <- fit_g_functions(policy_data = pd,
                               g_models = list(g_glm(), g_glm()),
                               full_history = TRUE)
g_functions