A two-parameter model for representing the survival curve of treated cancer patients is described. IfPTis the proportion of the treated patients surviving to timeT, and[Ptilde]Tis the proportion of a normal population surviving to timeTthen the survival curve may be represented by: —PT/[Ptilde]T= c.e-logec,e-βT, wherecis the proportion cured and β is the asymptotic value asTapproaches ∞ of the instantaneous risk of dying from cancer in the uncured group. The model stems from the observation that, in the whole series, the conditional probability of dying from cancer in an interval calculated by the usual actuarial method, tends to decrease exponentially with time, and the model has been designated ‘extrapolated actuarial’ to distinguish it from the lognormal model of Boag [2], and the exponential model of Berkson and Gage [1].