ivbds: Estimating bounds on treatment effects with instrumental...

In ehkennedy/npcausal: Nonparametric causal inference methods

Description

ivbds is used to estimate bounds on various effects using instrumental variables.

Usage

ivbds(y, a, z, x, nsplits=2, sl.lib=c("SL.earth","SL.gam","SL.glm","SL.glmnet",
  "SL.glm.interaction", "SL.mean","SL.ranger","rpart"), project01=T)

Arguments

y	outcome of interest.
a	binary treatment.
z	binary instrument.
x	covariate matrix.
nsplits	integer number of sample splits for nuisance estimation. If nsplits=1, sample splitting is not used, and nuisance functions are estimated on full sample (in which case validity of SEs/CIs requires empirical process conditions). Otherwise must have nsplits>1.
sl.lib	algorithm library for SuperLearner. Default library includes "earth", "gam", "glm", "glmnet", "glm.interaction", "mean", "ranger", "rpart".
project01	should the estimated compliance score be projected to space respecting 0-1 bounds and monotonicity?

Value

A list containing the following components:

res	estimates/SEs/CIs/p-values for local average treatment effect E(Y(a=1)-Y(a=0)|A(z=1)>A(z=0)), as well as IV strength and sharpness.
nuis	subject-specific estimates of nuisance functions (i.e., IV propensity score and treatment/outcome regressions)
ifvals	matrix of estimated influence function values.

References

(Also see references for function ate)

Angrist JD, Imbens GW, Rubin DB (1996). Identification of causal effects using instrumental variables. Journal of the American Statistical Association.

Abadie A (2003). Semiparametric instrumental variable estimation of treatment response models. Journal of Econometrics.

Kennedy EH, Balakrishnan S, G'Sell M (2017). Complier classification with sharp instrumental variables. Working Paper.

Examples

n <- 100; x <- matrix(rnorm(n*5),nrow=n)
z <- rbinom(n,1,0.5); a <- rbinom(n,1,0.6*z+0.2)
y <- rnorm(n)

ivbds.res <- ivbds(y,a,z,x)

ehkennedy/npcausal documentation built on Feb. 26, 2021, 2:43 a.m.