The analysis of infectious disease transmission data is complicated because disease outcomes in different individuals are inherently dependent. We show how survival analysis provides an elegant statistical framework for handling this dependency. When who-infected-whom is observed, standard methods from survival analysis can be used to estimate the probability of infectious contact as a function of time since the onset of infectiousness—including Cox regression modeling of covariate effects on infectiousness and susceptibility. When who-infects-whom is observed, the likelihood for the model is a sum over all possible transmission trees. These models can be fit using an expectation-maximization (EM) algorithm. Finally, we show how genetic sequence data from pathogen samples can be used to restrict the set of possible transmission trees, resulting in more precise estimates of transmission parameters.