Longitudinal Nested Compliance Class Model in the Presence of Time-Varying Noncompliance

• Published in: Journal of the American Statistical Association Vol. 103; no. 482; pp. 462 - 473
• Main Authors: Lin, Julia Y, Ten Have, Thomas R, Elliott, Michael R
• Format: Journal Article
• Language: English
• Published: Alexandria, VA Taylor & Francis 01.06.2008; American Statistical Association; Taylor & Francis Ltd
• Subjects: Access control; Applications; Applications and Case Studies; Bias; Biology, psychology, social sciences; Clinical trials; Compliance; Compliance certificates; Depression; Depressive disorders; Elder care; Exact sciences and technology; General topics; Geriatric depression; Health care; Health education; Intervention; Latent class analysis; Latent class model; Longitudinal compliance class model; Mathematics; Medical care; Medical personnel; Medical research; Medical sciences; Mental depression; Mental health; Modeling; Noncompliance; Older people; Parameter estimation; Patient compliance; Physicians; Potential outcomes; Primary care; Principal stratification; Probability and statistics; Psychoeducational intervention; Random allocation; Randomization; Randomized trial; Regression analysis; Sciences and techniques of general use; Securities and Exchange Commission regulation; Severity; Simulation; Specialists; Statistical methods; Statistical variance; Statistics; Suicide; Treatment compliance; United States > US; Biometrics; Invariant; Parameter estimation; Longitudinal compliance class model; Principal stratification; Statistical estimation; Suicide; Care; Nested model; Statistical method; Prevention; Randomization; Medical science; Randomized design; Simulation; Geriatric depression; Potential outcomes; Trend analysis; Randomized trial; Application; Latent class model; Biased estimation

This article discusses a nested latent class model for analyzing longitudinal randomized trials when subjects do not always adhere to the treatment to which they are randomized. In the Prevention of Suicide in Primary Care Elderly: Collaborative Trial, subjects were randomized to either the control...