2013
DOI: 10.1515/ijb-2012-0013
|View full text |Cite
|
Sign up to set email alerts
|

The Balanced Survivor Average Causal Effect

Abstract: Statistical analysis of longitudinal outcomes is often complicated by the absence of observable values in patients who die prior to their scheduled measurement. In such cases, the longitudinal data are said to be "truncated by death" to emphasize that the longitudinal measurements are not simply missing, but are undefined after death. Recently, the truncation by death problem has been investigated using the framework of principal stratification to define the target estimand as the survivor average causal effec… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2014
2014
2019
2019

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 25 publications
0
3
0
Order By: Relevance
“…We also note that the implementation of additional functionalities in future releases of the package should further expand its utility for methods research. Among such possible improvements is the evaluation of additional causal parameters, e.g., the average treatment effect on the treated (Holland 1986; Imbens 2004; Shpitser and Pearl 2009), survivorship causal effects (Joffe et al 2007; Greene et al 2013) and direct/indirect effects (Pearl 2001; Petersen et al 2006; VanderWeele 2009; VanderWeele and Vansteelandt 2014; Hafeman and VanderWeele 2011). …”
Section: Discussionmentioning
confidence: 99%
“…We also note that the implementation of additional functionalities in future releases of the package should further expand its utility for methods research. Among such possible improvements is the evaluation of additional causal parameters, e.g., the average treatment effect on the treated (Holland 1986; Imbens 2004; Shpitser and Pearl 2009), survivorship causal effects (Joffe et al 2007; Greene et al 2013) and direct/indirect effects (Pearl 2001; Petersen et al 2006; VanderWeele 2009; VanderWeele and Vansteelandt 2014; Hafeman and VanderWeele 2011). …”
Section: Discussionmentioning
confidence: 99%
“…In that paper, the assumption of monotonicity (or “no defiers”) on survivorship is required. Greene et al mitigated the difficulty of imposing monotonicity by introducing an alternative estimand, the balanced‐SACE, which does not require monotonicity for identification. However, the balanced‐SACE estimand only focuses on a particular subpopulation that the conventional SACE estimand (what we use) targets, and the subpopulation is defined by the survival time under both treatment and control, which does not apply in our application.…”
Section: Proposed Sensitivity Analysis Methods For Rommentioning
confidence: 99%
“…For the log-logistic distribution, the odds ratio (OR) of surviving longer for subjects in the active treatment group were fixed also at 1.0, 1.5, and 3.0. We generated non-fatal outcomes such that (31) with mean response x1 = 0 (control group) and x2 = 0.5 (active treatment group). We considered three distributions for x : normal, lognormal (each with mean 0 and variance 1), and t distribution with 3 degrees of freedom.…”
Section: Simulation Studymentioning
confidence: 99%