Analysis Group Associate Coauthors a Book Chapter on New Statistical Test

April 01, 2014

Analysis Group Associate Breno Neri and Luiz Renato Lima, an associate professor at the University of Tennessee, coauthored an academic paper, which was published as a chapter in the book Uncertainty Analysis in Econometrics with Applications (Advances in Intelligent Systems and Computing). "A Test for Strict Stationarity" introduces a novel statistical test that verifies whether the data possess a feature called stationarity, which means that the shape of its probability distribution is constant over time. Developed by Dr. Neri and Professor Lima, this new test is more powerful than other popular and recently developed tests for stationarity that can be found in most statistics software, including SAS. "Our test is more powerful in the sense that it detects the lack of stationarity with a higher accuracy than other tests," Dr. Neri explained. "Checking whether the data is stationary is important because, if the data lacks stationarity, most of the statistical tools commonly used to analyze the data are not valid and can produce biased results."

Learn more about the book