Ha. Feldman et Sm. Mckinlay, COHORT VERSUS CROSS-SECTIONAL DESIGN IN LARGE FIELD TRIALS - PRECISION, SAMPLE-SIZE, AND A UNIFYING MODEL, Statistics in medicine, 13(1), 1994, pp. 61-78
Citations number
34
Categorie Soggetti
Statistic & Probability","Medicine, Research & Experimental","Public, Environmental & Occupation Heath","Statistic & Probability
In planning large longitudinal field trials, one is often faced with a
choice between a cohort design and a cross-sectional design, with att
endant issues of precision, sample size, and bias. To provide a practi
cal method for assessing these trade-offs quantitatively, we present a
unifying statistical model that embraces both designs as special case
s. The model takes account of continuous and discrete endpoints, site
differences, and random cluster and subject effects of both a time-inv
ariant and a time-varying nature. We provide a comprehensive design eq
uation, relating sample size to precision for cohort and cross-section
al designs, and show that the follow-up cost and selection bias attend
ing a cohort design may outweigh any theoretical advantage in precisio
n. We provide formulae for the minimum number of clusters and subjects
. We relate this model to the recently published prevalence model for
COMMIT, a multi-site trial of smoking cessation programmes. Finally, w
e tabulate parameter estimates for some physiological endpoints from r
ecent community-based heart-disease prevention trials, work an example
, and discuss the need for compiling such estimates as a basis for inf
ormed design of future field trials.