This paper concerns the analysis of menstrual data; in particular, methodology to identify variables that contribute to the variability of menstrual cycles both within and between women. The basis for the proposed methodology is a parameterization of the mean length of a menstrual cycle conditional upon the past cycles and covariates. This approach accommodates the length-bias and censoring commonly found in menstrual data. Data from a longitudinal study of menstrual patterns and other variables among Lese women of the Ituri Forest, Zaire, illustrate the methodology. A small simulation illustrates the bias caused by incorrectly deleting the censored cycles.

A functional central limit theorem for a local square integrable martingale with persistent disconti-nuities is given. By persistent discontinuities, it is meant that the martingale has jumps which do not vanish asymptotically. This central limit theorem is motivated by problems in the analysis of longitudinal and life history data. Running Headline: A Central Limit Theorem for Martingales

INTRODUCTION The starting point of our investigations is an estimation equation of the form U n (`; ff) = 0. It contains a finite dimensional parameter ` being of primary interest and a functional parameter ff. The latter may play the role of a nuisance parameter (in the classical sense) or that of a working parameter (coming into statistical use with Liang and Zeger, 1986). A nonparametric estimator ff n Theresienstr.39, D-80333 Munich, Germany 1 is assumed to be given showing a certain kind of limit behaviour, the special type of the estimator being of no regard. For estimators ` n of ` which solve (asymptotically) the estimation equation we will prove consistency and asymptotic normality. A special feature of the present paper is a consequent functionally orientated approach. The Taylor method---well established for

This paper provides a concise definition for ignorable dropout. This is done primarily from a frequentist perspective. The definition of ignorable dropout depends on both the population of inference and the type of statistical methodology used for inference. Different types of dropouts are described and compared to those found in the literature. Ignorability conditions are then given for the following types of inference: Likelihood-based