A Simple Empirical Model of Sickness Absence

A simple empirical Tobit model of sickness absence is proposed and estimated. The Tobit model is used to estimate underlying propensities for sickness absence out of weekly contracted hours, where censoring is set at 0 (no absence) and 1 (absent all week). These Tobit estimates of the underlying propensities for sickness absence seem reasonable in relation to the available data. The data are taken from the UK Labour Force Surveys, Winter 1993/4 to Winter 1997/98, and relate to socio-economics characterisitics of full time employees. ; absence; absenteeism;sickness;