Semiparametric efficiency and its implication on the design and analysis of group-sequential studies

Daniel O Scharfstein, Anastasios A. Tsiatis, James M. Robins

Research output: Contribution to journalArticle

Abstract

Authors have shown that the time-sequential joint distributions of many statistics used to analyze data arising from group-sequential time-to-event and longitudinal studies are multivariate normal with an independent increments covariance structure. In Theorem 1 of this article, we demonstrate that this limiting distribution arises naturally when one uses an efficient test statistic to test a single parameter in a semiparametric or parametric model. Because we are able to think of many of the statistics in the literature in this fashion, the limiting distribution under investigation is just a special case of Theorem I. Using this general structure, we then develop an information-based design and monitoring procedure that can be applied to any type of model for any type of group-sequential study provided that there is a unique parameter of interest that can be efficiently tested.

Original languageEnglish (US)
Pages (from-to)1342-1350
Number of pages9
JournalJournal of the American Statistical Association
Volume92
Issue number440
StatePublished - Dec 1997

Fingerprint

Semiparametric Efficiency
Group Sequential
Limiting Distribution
Statistics
Independent Increments
Longitudinal Study
Multivariate Normal
Semiparametric Model
Covariance Structure
Parametric Model
Theorem
Joint Distribution
Test Statistic
Monitoring
Demonstrate
Design
Semiparametric efficiency
Model
Limiting distribution

Keywords

  • Independent increment
  • Information-based design and monitoring
  • Longitudinal study
  • Maximum information trial
  • Time-to-event study

ASJC Scopus subject areas

  • Mathematics(all)
  • Statistics and Probability

Cite this

Semiparametric efficiency and its implication on the design and analysis of group-sequential studies. / Scharfstein, Daniel O; Tsiatis, Anastasios A.; Robins, James M.

In: Journal of the American Statistical Association, Vol. 92, No. 440, 12.1997, p. 1342-1350.

Research output: Contribution to journalArticle

@article{2aed07cd4af94c9b96f3529dcfe0dd72,
title = "Semiparametric efficiency and its implication on the design and analysis of group-sequential studies",
abstract = "Authors have shown that the time-sequential joint distributions of many statistics used to analyze data arising from group-sequential time-to-event and longitudinal studies are multivariate normal with an independent increments covariance structure. In Theorem 1 of this article, we demonstrate that this limiting distribution arises naturally when one uses an efficient test statistic to test a single parameter in a semiparametric or parametric model. Because we are able to think of many of the statistics in the literature in this fashion, the limiting distribution under investigation is just a special case of Theorem I. Using this general structure, we then develop an information-based design and monitoring procedure that can be applied to any type of model for any type of group-sequential study provided that there is a unique parameter of interest that can be efficiently tested.",
keywords = "Independent increment, Information-based design and monitoring, Longitudinal study, Maximum information trial, Time-to-event study",
author = "Scharfstein, {Daniel O} and Tsiatis, {Anastasios A.} and Robins, {James M.}",
year = "1997",
month = "12",
language = "English (US)",
volume = "92",
pages = "1342--1350",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "440",

}

TY - JOUR

T1 - Semiparametric efficiency and its implication on the design and analysis of group-sequential studies

AU - Scharfstein, Daniel O

AU - Tsiatis, Anastasios A.

AU - Robins, James M.

PY - 1997/12

Y1 - 1997/12

N2 - Authors have shown that the time-sequential joint distributions of many statistics used to analyze data arising from group-sequential time-to-event and longitudinal studies are multivariate normal with an independent increments covariance structure. In Theorem 1 of this article, we demonstrate that this limiting distribution arises naturally when one uses an efficient test statistic to test a single parameter in a semiparametric or parametric model. Because we are able to think of many of the statistics in the literature in this fashion, the limiting distribution under investigation is just a special case of Theorem I. Using this general structure, we then develop an information-based design and monitoring procedure that can be applied to any type of model for any type of group-sequential study provided that there is a unique parameter of interest that can be efficiently tested.

AB - Authors have shown that the time-sequential joint distributions of many statistics used to analyze data arising from group-sequential time-to-event and longitudinal studies are multivariate normal with an independent increments covariance structure. In Theorem 1 of this article, we demonstrate that this limiting distribution arises naturally when one uses an efficient test statistic to test a single parameter in a semiparametric or parametric model. Because we are able to think of many of the statistics in the literature in this fashion, the limiting distribution under investigation is just a special case of Theorem I. Using this general structure, we then develop an information-based design and monitoring procedure that can be applied to any type of model for any type of group-sequential study provided that there is a unique parameter of interest that can be efficiently tested.

KW - Independent increment

KW - Information-based design and monitoring

KW - Longitudinal study

KW - Maximum information trial

KW - Time-to-event study

UR - http://www.scopus.com/inward/record.url?scp=0031312687&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031312687&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031312687

VL - 92

SP - 1342

EP - 1350

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 440

ER -