Answers are grounded in this paper and cite their sources.
The authors propose and calibrate a “split hazard” model that allows simultaneous modeling of observed heterogeneity with respect to both probability and timing of eventual adoption. Model validation with data for the diffusion of automatic teller machines (ATM) across 3689 banks demonstrates the robustness of the model framework to conceptual and distributional assumptions.
No takes yet. Share an insight, caveat, or question.
Sinha et al. (1992) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: