Rate My Professor Pierre Du

Duchesne's research focuses on applied statistics, with particular emphasis on time series analysis, sampling theory, multivariate analysis, econometrics, and financial econometrics. His contributions include developing portmanteau tests for model validation, robust estimation methods, wavelet-based testing for serial correlation, and tools for diagnostic checking in multivariate nonlinear time series models. He has published extensively in leading journals such as Computational Statistics & Data Analysis, Journal of Time Series Analysis, Canadian Journal of Statistics, and Econometric Theory. Key publications include 'On subset least squares estimation and prediction in vector autoregressive models' (2025), 'On wavelet-based testing for serial correlation of unknown form using Fan's adaptive Neyman method' with Linyuan Li and Shan Yao (2014), 'On testing for causality in variance between two multivariate time series' with Herbert Nkwimi Tchahou (2013), and 'On consistent testing for serial correlation of unknown form in vector time series models' with Roch Roy (2004). As associate editor for Computational Statistics & Data Analysis and Canadian Journal of Statistics, and director of the M.Sc. and Ph.D. programs in statistics, he plays a pivotal role in advancing statistical methodology and education. His work impacts fields requiring robust time series modeling and complex data analysis.