This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these messages)
|
James Robert Thompson (June 18, 1938 – December 4, 2017) was an American mathematician, statistician, and university professor whose most influential work combined applied mathematics and nonparametric statistics with computing technologies to advance the fields of financial engineering and computational finance, model disease progression, assess problems in public health, and optimize quality control in industrial manufacturing.[1][2][3]
Thompson was a longtime faculty member of Rice University in Houston, Texas. He joined the university in 1970 as an associate professor in the Wiess School of Natural Sciences’ Department of Mathematical Sciences. He became the founding chair of the Department of Statistics in 1987. The department moved to the George R. Brown School of Engineering in 1990. Thompson retired from Rice in 2016 as the Noah Harding Emeritus Professor of Statistics.[4]
During his career, Thompson authored or co-authored 14 books,[5] including his most cited books Models for Investors in Real World Markets,[6] Empirical Model Building: Data, Models, and Reality 2nd ed.,[7] and Statistical Process Control for Quality Improvement, co-authored with Jacek Koronacki.[8] Thompson was a principal investigator for the United States Army Research Office (ARO), National Aeronautics and Space Administration (NASA), and the United Nations Industrial Development Organization (UNIDO). From 1991-1993, he directed a team of 12 Polish statisticians to teach statistical process control in the newly-liberated Polish factories after the fall of communism. The training manual and teachings are reflected in the previously mentioned book Statistical Process Control: The Deming Paradigm and Beyond.
Thompson and his collaborators are most recently known for the quantitative exploration of the capital asset pricing model (CAPM), and several approaches in exploratory data analysis, which involve looking at data from different angles. These non-parametric approaches to portfolio formulation included the Simugram™, variants of his Max-Median rule and Tukey weightings.[9][10]
The MaxMedian rule is nonproprietary and was designed for investors who wish to do their own investing on a laptop with the purchase of 20 stocks.[11][12] Simugram™ is an empirical data-based paradigm for portfolio selection. The algorithm synchronizes the historical performance of stocks in a selection set. The information from Simugram™ is then used to develop a high return, low risk portfolio. US Patent 7,720,738 B2, May 18, 2010.[13] The simulation-based data analysis challenges the Efficient Market Hypothesis (EMH) and the Black-Scholes-Merton option pricing formula, making Thompson an early critic of the hypothesis in financial economics.[14] The research was funded by $10 million NSF grants awarded to Rice University in 2003 and 2008 for Vertical Integration of Research and Education in the Mathematical Sciences (VIGRE).[15][16]
Thompson was a long-term collaborator who united physicians and medical researchers in the Texas Medical Center with university researchers in mathematics and biostatistics to analyze coronary artery disease, cancer, and HIV/AIDS. In 1977, he began working with clinicians and researchers at the Baylor College of Medicine to statistically correlate the relationship between plasma lipid concentrations and coronary artery disease.[17]
Thompson also served as an adjunct professor (1977–2017) at the University of Texas MD Anderson Cancer Center and the University of Texas School of Public Health. He was known for the development of the Multivariate Simulation-Based Parameter Estimation (SIMEST) model, which was used to estimate breast cancer parameters and simulate the growth and spread of malignant tumors.[18][19][20] His work in mathematical biology also positioned him as an early proponent of the prevention and control of contagious diseases, such as HIV/AIDS, by case isolation, quarantine, and public education. He is particularly known for his work in correlating the effect that the HIV epidemic had on an increased number of tuberculosis cases in the United States.[21][22][23]
Thompson was a member of the International Statistical Institute (1982). He was elected Fellow of the American Statistical Association (1984) and founded the ASA Houston Chapter in 1981. He was also elected Fellow of the Institute of Mathematical Statistics (1988).[24]