Change Point Test for the Conditional Mean of Time Series of Counts Based on Support Vector Regression

This study considers support vector regression (SVR) and twin SVR (TSVR) for the time series of counts, wherein the hyper parameters are tuned using the particle swarm optimization (PSO) method. For prediction, we employ the framework of integer-valued generalized autoregressive conditional heteroskedasticity (INGARCH) models. As an application, we consider change point problems, using the cumulative sum (CUSUM) test based on the residuals obtained from the PSO-SVR and PSO-TSVR methods. We conduct Monte Carlo simulation experiments to illustrate the methods’ validity with various linear and nonlinear INGARCH models. Subsequently, a real data analysis, with the return times of extreme events constructed based on the daily log-returns of Goldman Sachs stock prices, is conducted to exhibit its scope of application.

Robust Change Point Test for General Integer-Valued Time Series Models Based on Density Power Divergence

In this study, we consider the problem of testing for a parameter change in general integer-valued time series models whose conditional distribution belongs to the one-parameter exponential family when the data are contaminated by outliers. In particular, we use a robust change point test based on density power divergence (DPD) as the objective function of the minimum density power divergence estimator (MDPDE). The results show that under regularity conditions, the limiting null distribution of the DPD-based test is a function of a Brownian bridge. Monte Carlo simulations are conducted to evaluate the performance of the proposed test and show that the test inherits the robust properties of the MDPDE and DPD. Lastly, we demonstrate the proposed test using a real data analysis of the return times of extreme events related to Goldman Sachs Group stock.

Consistent and powerful non-Euclidean graph-based change-point test with applications to segmenting random interfered video data

The change-point detection has been carried out in terms of the Euclidean minimum spanning tree (MST) and shortest Hamiltonian path (SHP), with successful applications in the determination of authorship of a classic novel, the detection of change in a network over time, the detection of cell divisions, etc. However, these Euclidean graph-based tests may fail if a dataset contains random interferences. To solve this problem, we present a powerful non-Euclidean SHP-based test, which is consistent and distribution-free. The simulation shows that the test is more powerful than both Euclidean MST- and SHP-based tests and the non-Euclidean MST-based test. Its applicability in detecting both landing and departure times in video data of bees’ flower visits is illustrated.

Can pitcher performance reveal game fixing in baseball? Developing a forensic analysis detection procedure

Gambling and game-fixing scandals have loomed over the international baseball world and a lack of sports ethics in baseball may lead to many problems. In this study I conducted a textual analysis of reports by prosecutors regarding a pitcher who was investigated but not indicted in 2009 after allegations of game fixing. Drawing upon the statistical records of the season's games for the pitcher that were contained in the prosecutor's reports and game-by-game records for each Chinese Professional Baseball League pitcher in the 2009 regular season, I used the change-point test and difference-in-differences techniques to identify anomalies in the pitcher's play. The results I obtained support information contained in the prosecutors' reports regarding the pitcher's actions. My model is confirmed as an appropriate method of applied behavior analysis for detecting corruption in baseball pitching performance.