The initial basis of this book was a series of my research papers, that I listed in References. I have many people to thank for the book's existence. Regarding higher order asymptotic efficiency I thank Professors Kei Takeuchi and M. Akahira for their many comments. I used their concept of efficiency for time series analysis. During the summer of 1983, I had an opportunity to visit The Australian National University, and could elucidate the third-order asymptotics of some estimators. I express my sincere thanks to Professor E.J. Hannan for his warmest encouragement and kindness. Multivariate time series analysis seems an important topic. In 1986 I visited Center for Mul tivariate Analysis, University of Pittsburgh. I received a lot of impact from multivariate analysis, and applied many multivariate methods to the higher order asymptotic theory of vector time series. I am very grateful to the late Professor P.R. Krishnaiah for his cooperation and kindness. In Japan my research was mainly performed in Hiroshima University. There is a research group of statisticians who are interested in the asymptotic expansions in statistics. Throughout this book I often used the asymptotic expansion techniques. I thank all the members of this group, especially Professors Y. Fujikoshi and K. Maekawa foItheir helpful discussion. When I was a student of Osaka University I learned multivariate analysis and time series analysis from Professors Masashi Okamoto and T. Nagai, respectively. It is a pleasure to thank them for giving me much of research background.

Autorentext

Yuichi Goto is an assistant professor in Department of Mathematical Sciences, Faculty of Mathematics at Kyushu University. He earned his Ph.D. from Waseda University in 2021 and he was an assistant professor in Waseda University for one year. He completed a master's course in one year (one year early) and a doctor's course in two years (one year early). His research interests include time series analysis, especially frequency domain analysis, integer-valued time series, and analysis of variance. He received the Azusa Ono Memorial Award in 2021 and IMS New Researcher Travel Awards in 2023. Hideaki Nagahata is a project assistant professor in Risk Analysis Research Center at the Institute of Statistical Mathematics. His research interests include multivariate time series analysis and quantitative aspects of risk modelling. He has worked on the estimation of loss given default (LGD) with local banks and quantifying the risk of compensation triggered on the CompoundLivestock Feed Supply Stabilization System with the Ministry of Agriculture, Forestry, and Fisheries. Masanobu Taniguchi is an Emeritus professor at Waseda University. His research interests include time series analysis, mathematical statistics, multivariate analysis, information geometry, signal processing, econometric theory, and financial engineering. His main contributions in time series analysis are collected in his book: "Asymptotic Theory of Statistical Inference for Time Series" (New York : Springer-Verlag, 2000). He received the Ogawa Prize (Japan) in 1989, the Econometric Theory Award (USA) in 2000, the Japan Statistical Society Prize in 2004, Analysis Award in 2013 (Mathematical Society of Japan), Award of Japanese Minister of Education, Culture, Sports, Science & Technology in 2022, and the Distinguished Author Award in 2020 (Journal of Time Series Analysis, UK). He is a fellow of the Institute of Mathematical Statistics (USA, 1987 - ). Anna Clara Monti is a professor in the Department of Law, Economics, Management, and Quantitative Methods at University of Sannio. She acted as dean of the Faculty of Economics and the Faculty of Law. Her research interests concern statistical inference, robustness, ordinal response models, and time series. She has published several papers in international journals of statistics, e.g. Biometrika, JRSS(B), JASA, etc. Xiaofei Xu is an assistant professor in School of Mathematics and Statistics at Wuhan University. Before joining Wuhan University, she worked as an assistant professor in Waseda Unversity. She got Ph.D. degree in statistics in 2020. Her research interests include functional data analysis, count time series analysis, non-stationarity and high dimensionality, and energy forecasting. Xiaofei has published several papers in famous international journals including Annals of Applied Statistics and Journal of Business and Economic Statistics.

Klappentext

This book gives higher order asymptotic results in time series analysis. Especially, higher order asymptotic optimality of estimators and power comparison of tests for ARMA processes are discussed. It covers higher order asymptotics of statistics of multivariate stationary processes. Numerical studies are given, and they show that the higher order asymptotic theory is useful and important for time series analysis. Also the validities of Edgeworth expansions of some estimators are proved for dependent situations. Many results will serve as the basis for the further theoretical development and their applications.

Inhalt
1 A Survey of the First-Order Asymptotic Theory for Time Series Analysis.- 2 Higher Order Asymptotic Theory for Gaussian Arma Processes.- 2.1. Higher order asymptotic efficiency and Edgeworth expansions.- 2.2. Second-order asymptotic efficiency for Gaussian ARMA processes.- 2.3. Third-order asymptotic efficiency for Gaussian ARMA processes.- 2.4. Normalizing transformations of some statistics of Gaussian ARMA processes.- 2.5. Higher order asymptotic efficiency in time series regression models.- 3 Validity of Edgeworth Expansions in Time Series Analysis.- 3.1. Berry-Esseen theorems for quadratic forms of Gaussian stationary processes.- 3.2. Validity of Edgeworth expansions of generalized maximum likelihood estimators for Gaussian ARMA processes.- 4 Higher Order Asymptotic Sufficiency, Asymptotic Ancillarity in Time Series Analysis.- 4.1. Higher order asymptotic sufficiency for Gaussian ARMA processes.- 4.2. Asymptotic ancillarity in time series analysis.- 5 Higher Order Investigations for Testing Theory in Time Series Analysis.- 5.1. Asymptotic expansions of the distributions of a class of tests under the null hypothesis.- 5.2. Comparisons of powers of a class of tests under a local alternative.- 6 Higher Order Asymptotic Theory for Multivariate Time Series.- 6.1. Asymptotic expansions of the distributions of functions of the eigenvalues of sample covariance matrix in multivariate time series.- 6.2. Asymptotic expansions of the distributions of functions of the eigenvalues of canonical correlation matrix in multivariate time series.- 7 Some Practical Examples.- References.- Author Index.