RECONCILING RECALLED DATES OF DEVELOPMENTAL MILESTONES, EVENTS AND TRANSITIONS - A MIXED GENERALIZED LINEAR-MODEL WITH RANDOM MEAN AND VARIANCE FUNCTIONS

Reconciliation of conflicting reports on the dating of events has typi cally been approached as 'data cleaning'. We present an alternative ap proach of modelling discrepancies by a statistical measurement model. The model combines two explanations of 'telescoping', systematic compr ession of the timescale and heteroscedastic random measurement error. The model can be viewed as a mixed generalized linear model with rando m effects within both mean and variance functions, or alternatively as involving multiplicative random effects. We illustrate the model in t he context of multiple mothers' reports of the onset of puberty in the ir daughters. Estimated by penalized or predictive quasi-likelihood, t he model correctly distinguished the different mechanisms for telescop ing and provided much improved estimates of the true age-of-onset dist ribution.