Premium
The Link between Dynamics and Statistics in Analysis of Repeated Measurements
Author(s) -
Tsubaki Michiko
Publication year - 1999
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/(sici)1521-4036(199910)41:6<711::aid-bimj711>3.0.co;2-7
Subject(s) - statistics , mathematics , covariance , random effects model , repeated measures design , mixed model , statistical model , econometrics , medicine , meta analysis
A method of analysis of repeated measurements is proposed. When a drug is administered orally or by intramuscular injection, the concentration of the drug in the blood‐time curve can often be modeled using a one‐compartment model assuming first‐order absorption in the field of pharmacokinetics. As to incorporation of individual variation, which is important statistically in modeling of repeated measurements, variations within an individual are taken into account in the model by a Wiener process and variations between individuals are expressed as differences in parameters. Accordingly, in this study, repeated measurements are modeled by a continuous time series statistically which was obtained from a one‐compartment model assuming first‐order absorption representing the dynamics affecting the data. The proposed model is not a random or mixed effect model but a fixed effect model; however, the covariance matrix includes values which differ between individuals. This is a new type of statistical modeling for repeated measurements, with flexibility, due to use of the link between statistics and dynamics. On the basis of the above, hypotheses of equality of treatment effects and equality of parameters between individuals are tested.