A proportional hazards model for truncated AIDS data.

An important source of information on the latency period for AIDS is the data from individuals infected by contaminated blood transfusion. However, a difficulty in the analysis and interpretation of these data is that information is available only on individuals who are infected and develop the disease prior to some specific time. In this paper, we propose an approach to the analysis of such data under a proportional hazards model. The proposed approach allows testing for group effects in the presence of multiple explanatory variables.