Stochastic Processes: Inference Theory (mathematics And Its Applications)

The material accumulated and presented in this volume can be ex­ plained easily. At the start of my graduate studies in the early 1950s, I Grenander's (1950) thesis, and was much attracted to the came across entire subject considered there. I then began preparing for the neces­ sary mathematics to appreciate and possibly make some contributions to the area. Thus after a decade of learning and some publications on the way, I wanted to write a modest monograph complementing Grenander's fundamental memoir. So I took a sabbatical leave from my teaching position at the Carnegie-Mellon University, encouraged by an Air Force Grant for the purpose, and followed by a couple of years more learning opportunity at the Institute for Advanced Study to complete the project. As I progressed, the plan grew larger needing a substantial background material which was made into an independent initial volume in (1979). In its preface I said: "My intension was to present the following material as the first part of a book treating the In­ ference Theory of stochastic processes, but the latter account has now receded to a distant future," namely for two more decades! Meanwhile, a much enlarged second edition of that early work has appeared (1995), and now I am able to present the main part of the original plan. The material accumulated and presented in this volume can be exƯ plained easily. At the start of my graduate studies in the early 1950s, I Grenander's (1950) thesis, and was much attracted to the came across entire subject considered there. I then began preparing for the necesƯ sary mathematics to appreciate and possibly make some contributions to the area. Thus after a decade of learning and some publications on the way, I wanted to write a modest monograph complementing Grenander's fundamental memoir. So I took a sabbatical leave from my teaching position at the Carnegie-Mellon University, encouraged by an Air Force Grant for the purpose, and followed by a couple of years more learning opportunity at the Institute for Advanced Study to complete the project. As I progressed, the plan grew larger needing a substantial background material which was made into an independent initial volume in (1979). In its preface I said: "My intension was to present the following material as the first part of a book treating the InƯ ference Theory of stochastic processes, but the latter account has now receded to a distant future," namely for two more decades! Meanwhile, a much enlarged second edition of that early work has appeared (1995), and now I am able to present the main part of the original plan This book presents a complete mathematical treatment of classical inference theory (Neyman-Pearson, Fisher, and Wald) from the point of using it in stochastic processes, including some generalizations. It includes detailed analysis of likelihood ratios for both Gaussian and several other classes (infinitely divisible, jump Markov, diffusion and additive). Both linear and nonlinear filtering (also for general nonquadratic criteria) are treated. The corresponding Kalman-Bucy filters for continuous parameter processes are presented. Consistency and limit distributions of estimations of biospectral densities of harmonizable processes are given. Audience: Researchers and graduate students working in mathematics, statistics, and systems and communication engineering. Front Matter....Pages i-xvi Introduction and Preliminaries....Pages 1-18 Principles of Hypothesis Testing....Pages 19-72 Parameter Estimation and Asymptotics....Pages 73-131 Inference for Classes of Processes....Pages 133-222 Likelihood Ratios for Processes....Pages 223-338 Sampling Methods for Processes....Pages 339-381 More on Stochastic Inference....Pages 383-464 Prediction and Filtering of Processes....Pages 465-556 Nonparametric Estimation for Processes....Pages 557-599 Back Matter....Pages 601-645