gam_est {causaldrf}  R Documentation 
The GAM estimator
Description
This estimates the ADRF using a method similar to that described in Hirano and Imbens (2004), but with spline basis terms in the outcome model.
Usage
gam_est(Y,
treat,
treat_formula,
data,
grid_val,
treat_mod,
link_function,
...)
Arguments
Y 
is the the name of the outcome variable contained in 
treat 
is the name of the treatment variable contained in

treat_formula 
an object of class "formula" (or one that can be
coerced to that class) that regresses 
data 
is a dataframe containing 
grid_val 
contains the treatment values to be evaluated. 
treat_mod 
a description of the error distribution to be used in the
model for treatment. Options include: 
link_function 
is either "log", "inverse", or "identity" for the
"Gamma" 
... 
additional arguments to be passed to the gam() outcome function. 
Details
This function estimates the ADRF similarly to the method described by Hirano and Imbens (2004), but with a generalized additive model in the outcome model.
Value
gam_est
returns an object of class "causaldrf",
a list that contains the following components:
param 
parameter estimates for a gam fit. 
t_mod 
the result of the treatment model fit. 
out_mod 
the result of the outcome model fit. 
call 
the matched call. 
References
Schafer, J.L., Galagate, D.L. (2015). Causal inference with a continuous treatment and outcome: alternative estimators for parametric doseresponse models. Manuscript in preparation.
Hirano, Keisuke, Imbens, Guido W (2004). The propensity score with continuous treatments. Applied Bayesian modeling and causal inference from incompletedata perspectives.
Flores, Carlos A and FloresLagunes, Alfonso and Gonzalez, Arturo and Neumann, Todd C (2012). Estimating the effects of length of exposure to instruction in a training program: the case of job corps. Review of Economics and Statistics. 94.1, 153171
See Also
nw_est
, iw_est
, hi_est
, gam_est
,
add_spl_est
,
bart_est
, etc. for other estimates.
t_mod
, overlap_fun
to prepare the data
for use in the different estimates.
Examples
## Example from Schafer (2015).
example_data < sim_data
gam_list < gam_est(Y = Y,
treat = T,
treat_formula = T ~ B.1 + B.2 + B.3 + B.4 + B.5 + B.6 + B.7 + B.8,
data = example_data,
grid_val = seq(8, 16, by = 1),
treat_mod = "Normal")
sample_index < sample(1:1000, 100)
plot(example_data$T[sample_index],
example_data$Y[sample_index],
xlab = "T",
ylab = "Y",
main = "gam estimate")
lines(seq(8, 16, by = 1),
gam_list$param,
lty = 2,
lwd = 2,
col = "blue")
legend('bottomright',
"gam estimate",
lty=2,
lwd = 2,
col = "blue",
bty='Y',
cex=1)
rm(example_data, gam_list, sample_index)