BAYESIAN UPDATING IN REFERENCE CENTILE CHARTS

Reference centile charts, used for monitoring the health of an individ ual over time (e.g. the weight gain of pregnant women over successive periods in their pregnancy) do not take into account the longitudinal nature of the individual profiles. There is also generally more than o ne variable which affects the outcome of interest, and information reg arding the path of a group of variables over time may prove advantageo us in terms of sensitivity. We propose a Bayesian approach to this pro blem in which the successive deviations of the individual's observatio ns from the mean of the corresponding reference distribution are used to compute updated reference centiles for future measurements on the i ndividual. The univariate and multivariate situations are discussed, a nd consideration is given to non-normal cross-sectional distributions. The theory is illustrated on data obtained from the records of weight gain and fundal height of pregnant women visiting a clinic at interva ls during pregnancy.