Inference for Autoregressive Point Processes

2017 - presentpresent
The primary goal of the proposed work is to develop fundamental theory and algorithms for inference on autoregressive point processes with missing observations. Anticipated research outcomes: We anticipate that the proposed research will result in: a) a new class of methods related to the analysis of point process data arising in a variety of applications, with these results summarized in several papers describing the proposed approach and its performance relative to other candidate methods b) new mathematical theory and analyses supporting the proposed approach c) a suite of well-documented computer algorithms which will be made available to the NGA and other researchers via a public code repository d) demonstration of the predictive power and model selection accuracy of the proposed theory and methods on real data from neuroscience, social networks, crime statistics, or electronic health records.