ProbitControl: Causal inference in probit outcome models with possibly...

In zijguo/RobustIV: Robust Instrumental Variable Methods in Linear Models

Causal inference in probit outcome models with possibly invalid IVs

Description

Perform causal inference in the probit outcome model with possibly invalid IVs under the majority rule.

Usage

ProbitControl(
  Y,
  D,
  Z,
  X = NULL,
  intercept = TRUE,
  invalid = FALSE,
  d1 = NULL,
  d2 = NULL,
  w0 = NULL,
  bs.Niter = 40
)

Arguments

Y	The outcome observation, a vector of length n.
D	The treatment observation, a vector of length n.
Z	The instrument observation of dimension n \times p_z.
X	The covariates observation of dimension n \times p_x.
intercept	Whether the intercept is included. (default = TRUE)
invalid	If TRUE, the method is robust to the presence of possibly invalid IVs; If FALSE, the method assumes all IVs to be valid. (default = FALSE)
d1	A treatment value for computing CATE(d1,d2|w0).
d2	A treatment value for computing CATE(d1,d2|w0).
w0	A vector for computing CATE(d1,d2|w0).
bs.Niter	The number of bootstrap resampling size for computing the confidence interval.

Value

ProbitControl returns an object of class "SpotIV", which is a list containing the following components:

betaHat	The estimate of the model parameter in front of the treatment.
beta.sdHat	The estimated standard error of betaHat.
cateHat	The estimate of CATE(d1,d2|w0).
cate.sdHat	The estimated standard deviation of cateHat.
SHat	The estimated set of relevant IVs.
VHat	The estimated set of relevant and valid IVs.
Maj.pass	The indicator that the majority rule is satisfied.

References

Li, S., Guo, Z. (2020), Causal Inference for Nonlinear Outcome Models with Possibly Invalid Instrumental Variables, Preprint arXiv:2010.09922.

Examples

Y <- mroz[,"lwage"]
D <- mroz[,"educ"]
Z <- as.matrix(mroz[,c("motheduc","fatheduc","huseduc","exper","expersq")])
X <- mroz[,"age"]
Y0 <- as.numeric((Y>median(Y)))
d2 = median(D); d1 = d2+1;
w0 = apply(cbind(Z,X)[which(D == d2),], 2, mean)
Probit.model <- ProbitControl(Y0,D,Z,X,d1 = d1,d2 = d2,w0 = w0)
summary(Probit.model)

zijguo/RobustIV documentation built on Aug. 28, 2022, 6:21 a.m.