Accelerated longitudinal designs: An overview of modelling, power, costs and handling missing data

被引:127
作者
Galbraith, Sally [1 ]
Bowden, Jack [2 ]
Mander, Adrian [2 ]
机构
[1] Univ New South Wales, Sch Math & Stat, Sydney, NSW, Australia
[2] MRC Biostat Unit, Cambridge, England
基金
英国医学研究理事会;
关键词
accelerated longitudinal design; mixed model; cohort effect; dropout; MIXED-EFFECTS MODELS; COHORTS;
D O I
10.1177/0962280214547150
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Longitudinal studies are often used to investigate age-related developmental change. Whereas a single cohort design takes a group of individuals at the same initial age and follows them over time, an accelerated longitudinal design takes multiple single cohorts, each one starting at a different age. The main advantage of an accelerated longitudinal design is its ability to span the age range of interest in a shorter period of time than would be possible with a single cohort longitudinal design. This paper considers design issues for accelerated longitudinal studies. A linear mixed effect model is considered to describe the responses over age with random effects for intercept and slope parameters. Random and fixed cohort effects are used to cope with the potential bias accelerated longitudinal designs have due to multiple cohorts. The impact of other factors such as costs and the impact of dropouts on the power of testing or the precision of estimating parameters are examined. As duration-related costs increase relative to recruitment costs the best designs shift towards shorter duration and eventually cross-sectional design being best. For designs with the same duration but differing interval between measurements, we found there was a cutoff point for measurement costs relative to recruitment costs relating to frequency of measurements. Under our model of 30% dropout there was a maximum power loss of 7%.
引用
收藏
页码:374 / 398
页数:25
相关论文
共 15 条
[1]  
[Anonymous], 2010, R LANG ENV STAT COMP
[2]  
[Anonymous], 2004, Applied Longitudinal Analysis
[3]  
[Anonymous], 1987, Statistical analysis with missing data
[4]   Guidelines for the design of clinical trials with longitudinal outcomes [J].
Galbraith, S ;
Marschner, IC .
CONTROLLED CLINICAL TRIALS, 2002, 23 (03) :257-273
[5]   INTENTIONALLY INCOMPLETE LONGITUDINAL DESIGNS .1. METHODOLOGY AND COMPARISON OF SOME FULL SPAN DESIGNS [J].
HELMS, RW .
STATISTICS IN MEDICINE, 1992, 11 (14-15) :1889-1913
[6]  
Kuh Diana., 1997, A Life Course Approach to Chronic Disease Epidemiology
[7]   Tests for linkage of multiple cohorts in an accelerated longitudinal design [J].
Miyazaki, Y ;
Raudenbush, SW .
PSYCHOLOGICAL METHODS, 2000, 5 (01) :44-63
[8]   The Effects of the Number of Cohorts, Degree of Overlap Among Cohorts, and Frequency of Observation on Power in Accelerated Longitudinal Designs [J].
Moerbeek, Mirjam .
METHODOLOGY-EUROPEAN JOURNAL OF RESEARCH METHODS FOR THE BEHAVIORAL AND SOCIAL SCIENCES, 2011, 7 (01) :11-24
[9]  
Molenberghs Geert., 2000, Linear Mixed Models for Longitudinal Data
[10]   Maximin D-optimal designs for longitudinal mixed effects models [J].
Ouwens, MJNM ;
Tan, FES ;
Berger, MPF .
BIOMETRICS, 2002, 58 (04) :735-741