Adjusting for Nonignorable Drop-Out Using Semiparametric Nonresponse Models

Consider a study whose design calls for the study subjects to be followed from enrollment (time t = 0) to time t = T, at which point a primary endpoint of interest Y is to be measured. The design of the study also calls for measurements on a vector V t) of covariates to be made at one or more times...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of the American Statistical Association Ročník 94; číslo 448; s. 1096 - 1120
Hlavní autori: Scharfstein, Daniel O., Rotnitzky, Andrea, Robins, James M.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Washington Taylor & Francis Group 01.12.1999
American Statistical Association
Predmet:
Analytical estimating
Augmented inverse probability of censoring weighted estimators
Consistent estimators
Cox proportional hazards model
Estimators
Identification; Missing data
Mathematical independent variables
Modeling
Noncompliance; Nonparametric methods
Nonparametric models
Parametric models
Randomized trials
Selection bias
Sensitivity analysis
Statistical models
Statistical variance
Theory and Methods
Time-dependent covariates
ISSN:0162-1459, 1537-274X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Consider a study whose design calls for the study subjects to be followed from enrollment (time t = 0) to time t = T, at which point a primary endpoint of interest Y is to be measured. The design of the study also calls for measurements on a vector V t) of covariates to be made at one or more times t during the interval [0, T). We are interested in making inferences about the marginal mean μ 0 of Y when some subjects drop out of the study at random times Q prior to the common fixed end of follow-up time T. The purpose of this article is to show how to make inferences about μ 0 when the continuous drop-out time Q is modeled semiparametrically and no restrictions are placed on the joint distribution of the outcome and other measured variables. In particular, we consider two models for the conditional hazard of drop-out given (V(T), Y), where V(t) denotes the history of the process V t) through time t, t ∈ [0, T). In the first model, we assume that λ Q (t|V(T), Y) exp(α 0 Y), where α 0 is a scalar parameter and λ 0 (t|V(t)) is an unrestricted positive function of t and the process V(t). When the process Vt) is high dimensional, estimation in this model is not feasible with moderate sample sizes, due to the curse of dimensionality. For such situations, we consider a second model that imposes the additional restriction that λ 0 (t|V(t)) = λ 0 (t) exp(γ′ 0 (t)), where λ 0 t) is an unspecified baseline hazard function, W(t) = w(t, V(t)), w(·,·) is a known function that maps (t, V(t)) to R q , and γ 0 is a q × 1 unknown parameter vector. When α 0 ≠ 0, then drop-out is nonignorable. On account of identifiability problems, joint estimation of the mean μ 0 of Y and the selection bias parameter α 0 may be difficult or impossible. Therefore, we propose regarding the selection bias parameter α 0 as known, rather than estimating it from the data. We then perform a sensitivity analysis to see how inference about α 0 changes as we vary α 0 over a plausible range of values. We apply our approach to the analysis of ACTG 175, an AIDS clinical trial.
Bibliografia:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
content type line 23
ISSN:0162-1459
1537-274X
DOI:10.1080/01621459.1999.10473862