Accelerated Failure Time Model

A basic model for the data comprising of survival times, in which the explanatory variables measured on an individual are supposed to act multiplicatively on the time-scale, and so affect the rate at which the individual moves along the time axis.

Accordingly the interruption in model takes place in terms of the speed of progression of the disease.

In the easiest cases of comparing the two groups of patients, for instance, those receiving the treatment A and those who are receiving the treatment B, this model supposes that the survival time of an individual on one treatment is a multiple of survival time on the other treatment; as a result of which the probability that an individual on treatment A survives beyond time t is the probability of that an individual on treatment B survives beyond time _t, where _ is an unidentified positive constant. When the end-point of the interest is the death of the patient, values of _ less than one correspond to the acceleration in the time of death of an individual given to treatment A, and values of _ greater than one shows the reverse of it. The parameter _ is generally known as the acceleration factor