Estimation And Inference In Changepoint Models

This thesis is motivated by statistical challenges that arise in the analysis of calcium imaging data, a new technology in neuroscience that makes it possible to record from huge numbers of neurons at single-neuron resolution. We consider the problem of estimating a neuron’s spike times from calcium imaging data. A simple and natural model suggests a non-convex optimization problem for this task. We show that by recasting the non-convex problem as a changepoint detection problem, we can efficiently solve it for the global optimum using a clever dynamic programming strategy. Furthermore, we introduce a new framework to quantify the uncertainty associated with a set of estimated changepoints in a change-in-mean model. In particular, we propose a new framework to test the null hypothesis that there is no change in mean around an estimated changepoint. This framework can be efficiently carried out in the case of changepoints estimated by binary segmentation and its variants, l0 segmentation, or the fused lasso, and is valid in finite samples. Our setup allows us to condition on much less information than existing approaches, thereby yielding higher powered tests. These ideas can be generalized to the spike estimation problem.

The first unified treatment of time series modelling techniques spanning machine learning, statistics, engineering and computer science.

The main emphasis is on the inference problem for the change point and post-change parameters after a change has been detected. More specifically, due to the convenient form and statistical properties, the author concentrates on the CUSUM procedure. The goal is to provide some quantitative evaluations on the statistical properties of estimators on the change point and post-change parameters.

In this paper, we consider the estimation of break points in high-dimensional factor models where the unobserved factors are estimated by principal component analysis (PCA). The factor loading matrix is assumed to have a structural break at an unknown time. We establish the conditions under which the least squares (LS) estimator is consistent for the break date. Our consistency result holds for both large and smaller breaks. We also find the LS estimator's asymptotic distribution. Simulation results confirm that the break date can be accurately estimated by the LS even if the breaks are small. In two empirical applications, we implement our method to estimate break points in the U.S. stock market and U.S. macroeconomy, respectively.

'This is a solid mathematical treatment of some topics in the analysis of change-point models. The book is intended for graduate students and scientific researchers using statistics in practice.'zbMATHThis book provides a detailed exposition of the specific properties of methods of estimation and test in a wide range of models with changes. They include parametric and nonparametric models for samples, series, point processes and diffusion processes, with changes at the threshold of variables or at a time or an index of sampling.The book contains many new results and fills a gap in statistics literature, where the asymptotic properties of the estimators and test statistics in singular models are not sufficiently developed. It is suitable for graduate students and scientific researchers working in the industry, governmental laboratories and academia.

Recently there has been a keen interest in the statistical analysis of change point detec tion and estimation. Mainly, it is because change point problems can be encountered in many disciplines such as economics, finance, medicine, psychology, geology, litera ture, etc. , and even in our daily lives. From the statistical point of view, a change point is a place or time point such that the observations follow one distribution up to that point and follow another distribution after that point. Multiple change points problem can also be defined similarly. So the change point(s) problem is two fold: one is to de cide if there is any change (often viewed as a hypothesis testing problem), another is to locate the change point when there is a change present (often viewed as an estimation problem). The earliest change point study can be traced back to the 1950s. During the fol lowing period of some forty years, numerous articles have been published in various journals and proceedings. Many of them cover the topic of single change point in the means of a sequence of independently normally distributed random variables. Another popularly covered topic is a change point in regression models such as linear regres sion and autoregression. The methods used are mainly likelihood ratio, nonparametric, and Bayesian. Few authors also considered the change point problem in other model settings such as the gamma and exponential.

Econometric models are made up of assumptions which never exactly match reality. Among the most contested ones is the requirement that the coefficients of an econometric model remain stable over time. Recent years have therefore seen numerous attempts to test for it or to model possible structural change when it can no longer be ignored. This collection of papers from Empirical Economics mirrors part of this development. The point of departure of most studies in this volume is the standard linear regression model Yt = x;fJt + U (t = I, ... , 1), t where notation is obvious and where the index t emphasises the fact that structural change is mostly discussed and encountered in a time series context. It is much less of a problem for cross section data, although many tests apply there as well. The null hypothesis of most tests for structural change is that fJt = fJo for all t, i.e. that the same regression applies to all time periods in the sample and that the disturbances u are well behaved. The well known Chow test for instance assumes t that there is a single structural shift at a known point in time, i.e. that fJt = fJo (t

The book is a selection of invited chapters, all of which deal with various aspects of mathematical and statistical models and methods in reliability. Written by renowned experts in the field of reliability, the contributions cover a wide range of applications, reflecting recent developments in areas such as survival analysis, aging, lifetime data analysis, artificial intelligence, medicine, carcinogenesis studies, nuclear power, financial modeling, aircraft engineering, quality control, and transportation. Mathematical and Statistical Models and Methods in Reliability is an excellent reference text for researchers and practitioners in applied probability and statistics, industrial statistics, engineering, medicine, finance, transportation, the oil and gas industry, and artificial intelligence.