Heterogeneous diffusion models let one combine the analysis of intrinsic propensities with that of intrapopulation contagion, and to disaggregate contagion effects into individual susceptibilities, the infectiousness of prior adopters, and the social proximity of prior-potential adopter pairs. This paper reports the results of a series of Monte Carlo simulation studies that investigate estimation issues for this class of models. Graphical analysis of population-level hazard rates is shown to provide little insight into these processes. We focus on the properties of maximum likelihood estimators, considering variation across parameter values and different forms of model misspecification. When models are correctly specified, we find few conditions under which estimation appears problematic. Difficult cases involve binary networks where network linkages have very strong effects or network density is high. Estimation deteriorates in some characteristic ways when models are misspecified. For example, propensity and susceptibility effects are readily confused. An effective model specification strategy is to include variables in all theoretically plausible components of the model rather than to test alternative covariate locations sequentially. Processes where a covariate affects the hazard in multiple ways (for example, has both propensity and infectiousness effects) are successfully parsed in correctly specified models. In general, results offer considerable encouragement for analysts who wish to estimate and test heterogeneous diffusion models.

* University of Tsukuba
** Cornell University
*** Stanford University