sace: Estimation of causal effects with outcomes truncated by death

In tbd: Estimation of Causal Effects with Outcomes Truncated by Death

Description

sace estimates survivor average causal effects (SACE) with outcomes truncated by death.

Usage

sace(Z, S, Y, X, A, subset, optim.method = "BFGS", max.step = 1000,
  singular.ok = TRUE, need.variance = TRUE, hessian = TRUE)

Arguments

Z	a logical vector. Exposure indicator. Convetionally, 1 means treatment and 0 means control. Must not have missing values.
S	a logical vector. Survival indicator. 1 means survival and 0 means death. Must not have missing values.
Y	a numeric vector. (Univariate) outcomes. May have NA where S=0 (since Y is not well-defined where S=0).
X	an optional numeric matrix or vector. Baseline covariates.
A	an optional numeric matrix or vector. Substitution variable(s) which satisfies the assumptions of "exclusion restriction" and "substitution relevance". See references. If A == NULL, then the naive method, namely OLS, will be used.
subset	an optional vector specifying a subset of obervations to be used.
optim.method	The method to be used for maximum likelihood optimization. See optim.
max.step	integer. Maximum iterating steps of maximum likelihood optimization.
singular.ok	logical. Refers to the OLS estimation of the coefficients alpha_1 and alpha_2 using lm. If FALSE (default), a singular fit raises an error.
need.variance	logical. Is variance of parameters and estimators needed? See details.
hessian	logical. If TRUE, the hessian returned by optim will be used to compute the information matrix. If FALSE, the matrix will be calculated by an explicit formula.

Details

This function sace, gives estimation of average causal effects (ACE) with outcomes truncated by death. The identification of SACE relies on the existence of a substitution variable and requires the assumptions of monotonicity, ignorability, exclusion restriction, and relevance. While the naive estimates given by the coefficient of Z from lm(Y ~ Z + X + A, subset = S == 1) are restricted among survivors and therefore may be subject to selection bias, this method gives consistent estimates of the SACE (survivor average causal effect), defined as the average causal effect among the subgroup consisting of subjects who would survive under either exposure, i.e. among the always-survivor group (G=LL). See references for details of the assumptions and the model parameterizations.

Parameters beta and gamma are estimated by MLE, using optim.

If need.variance == TRUE, the asymptotic variance estimators of both parameters and estimators will be given. This requires the numDeriv package.

Value

a list with following elements:

CALL	function call.
data	data used (within the specified subset).
optim.method	method used for optimization.
need.variance	is variance of parameters and estimators needed?
n	sample size.
mu_0_LL	average potential outcomes among control group, E[ Y(0) | G=LL ].
mu_1_LL	average potential outcomes among treatment group, E[ Y(1) | G=LL ].
sace	survivor average causal effect, equals mu_1_LL-mu_0_LL.
beta	Pr{S(1)=1| X,A}=expit(β_0+X' β_1+ A β_2), estimated by MLE.
gamma	Pr{S(0)=1| X,A}/Pr{S(1)=1| X,A}=expit(γ_0+X' γ_1+ A γ_2), estimated by MLE.
beta_gamma.convergence	indicator of convergence of MLE optimization of beta and gamma. 0 means convergence. See optim.
alpha_1	E[Y(0)| Z=0, G=LL, X, A ]=α_{10}+X' α_{11}+ A α_{12}, coefficients of lm(Y ~ 1 + X + A, subset = Z == 0).
alpha_2	E[Y(1)| Z=1, G=LL, X, A ]=α_{20}+X' α_{21}+ G α_{22}, coefficients of lm(Y ~ 1 + X + W.expit, subset = (Z == 1 & S == 1)).

The following items will be given only if need.variance == TRUE:

beta.var	estimated asymptotic covariance matrix of beta.
gamma.var	estimated asymptotic covariance matrix of gamma.
relevance.Pvalue	P value of the asymptotic chi-squared test on the relevance assumption for the substitution variable. A large P value suggests that the relevance assumption may not hold, namely, the substitution variable(s) may have little impact on the latent survival type.
alpha_1.var	estimated asymptotic covariance matrix of alpha_1.
alpha_2.var	estimated asymptotic covariance matrix of alpha_2.
mu_0_LL.var	estimated asymptotic variance of mu_0_LL.
mu_1_LL.var	estimated asymptotic variance of mu_1_LL.
sace.var	estimated asymptotic variance of the SACE.

Note

The length of vectors Z, Y, S, as well as the row number of matrix X and A must equal the sample size n.

Author(s)

Linbo Wang <[e-mail]>

Zhixuan Shao <[e-mail]>

References

Linbo Wang, Xiao-Hua Zhou, Thomas S. Richardson; Identification and estimation of causal effects with outcomes truncated by death, Biometrika, Volume 104, Issue 3, 1 September 2017, Pages 597-612, https://doi.org/10.1093/biomet/asx034

Examples

attach(simulated_data)
X <- cbind(X.X1, X.V2, X.V3)
sace.result <- sace(Z, S, Y, X, A)
sace

tbd documentation built on May 2, 2019, 12:42 p.m.