Yicong Lin and his co-authors publish an article in the Journal of Computational and Graphical Statistics. In the article they introduce a novel bootstrap method.
Yicong co-authored his paper with Mingxuan Song and Bernhard van der Sluis. The article is titled Bootstrap inference for linear time-varying coefficient models in locally stationary time series and introduces a bootstrap method to capture dynamic models.
Time-varying coefficient models can capture evolving relationships. However, constructing asymptotic confidence bands for coefficient curves in these models is challenging due to slow convergence rates and the presence of various nuisance parameters. This paper introduces a novel bootstrap method, the local blockwise wild bootstrap, which accommodates locally stationary processes and is well-suited for a wide range of real-world data applications.
The article has been accepted by the Journal of Computational and Graphical Statistics and already appeared online.
Mingxuan Song is currently a research master’s student in the BDS program and Bernhard van der Sluis is a Ph.D. candidate at Erasmus Universiteit Rotterdam. Both are alumni of our EDS bachelor program.
Related Stories
Related Stories