Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
Infrequency of purchase models are alternatives to those derived from the classical "utility maximization with binding non-negativity constraints" scheme for modelling purchases that occur at random dates. An extension of those models is proposed that takes into account additional information about the exact number of times households purchased during the survey period. Various methods of estimation are described and an empirical illustration is presented with data drawn from the French Food Expenditure Survey (INSEE).