Efficiency of the Slope Estimator in Repeated Measurements

Abstract

In repeated measurement studies, one of the popular primary interests is to investigate the rate of changes in a response variable. Efficiency of the slope estimator is examined with different numbers of equally-spaced measurements imposed across a specified fixed study period. In this paper, we examine the implication of the frequency of repeated measurements in the efficiency of the slope estimator in studies of fixed duration. We present a closed-form formula for assessing the efficiency of the slope estimator in terms of the standard error of the slope when the true correlation is the autoregressive order I or compound symmetry in the generalized estimating equation model. Since missing values in repeated measurement studies are more often the norm than the exception, we also investigate the efficiency of the slope estimator in the presence of missing data.

Get full access to this article

View all access options for this article.

References

Overall

How many repeated measurements are useful?

J Clin Psychology. 1996;52:243–252.

Ahn

Jung

Efficiency of GEE estimators of slopes in repeated measurements: Adding subjects or adding measurements?

Drug Inf J. 2003;39: 309–316.

Maxwell

Longitudinal designs in randomized group comparisons: When will intermediate observations increase statistical power?

Psychological Methods. 1998;3:275–290.

Kraemer

Thiemann

A strategy to use soft data effectively in randomized controlled clinical trials. J Consult Clin Psychology. 1989;57:148–154.

Arndt

Jorge

Turvey

Robinson

Adding subjects or adding measurements: Which increases the precision of longitudinal research?

J Psychiatric Res. 2000;34:449–455.

Jung

Ahn

Sample size estimation for comparing slopes in repeated measurements data. Stat Med. 2003;22:1305–1315.

Liang

Zeger

Longitudinal data analysis using generalized linear models. Biometrika. 1986; 73:13–22.

Rubin

Inference and missing data. Biometrika. 1976;63:81–92.