Random Point Processes in Time and Space

This senior graduate level textbook is the second revised edition of the textbook "Random Point Processes", written by D.L. Snyder and published in 1975. Its main thrust is point processes on multidimensional spaces, especially to processes in two dimensions. This reflects the tremendous increase that has taken place in the use of point-process models for the description of data from which images of objects of interest are formed in a wide variety of scientific and engineering disciplines. Research done by the authors at the Biomedical Computer Laboratory at Washington University has led to newly developed models for position emission tomography and electron-microscopic autoradiography. All the applications which the authors have been involved are examples of nonparametric density estimation, which provides the major motivation for new results on constrained estimation techniques. For these applications, the use of unconstrained maximum-likelihood estimation fails because the estimates are not consistent in the statistical sense; they do not converge, with increasing amounts of data, towards the quantity being estimated. Regularization of the estimates is, therefore, absolutely essential, and knowledge of this subject is crucial.