A Trailblazer in Statistical Analysis
Recognizing his internationally renowned research contributions and teaching excellence, UC Davis recently honored Professor Chih-Ling Tsai with the title of Distinguished Professor. The designation is the highest campus-level professional faculty title.
A pioneering expert in the practical application of statistics in business, including regression analysis, model selection, high-dimensional data, time series and biostatistics, Tsai has published more than 100 research papers during his career. His current work is in the extremely competitive field of high dimensional data analysis, in particular when the number of variables in a dataset is greater than the sample size. Where typical statistical methods become less effective with a higher number of variables, Tsai’s methods can effectively identify the most important information in a dataset with a large number of variables. The statistical model Tsai helped develop can be applied to many fields, including business, biological science, computer science and social science.
Tsai has recently completed two working papers in high dimensional data analysis. In “Testing Covariates in High Dimensional Regression,” he and his co-authors applied their theoretical results for studying how keywords contribute to a retailer’s online sales. “We have developed a method to identify significant keywords from the larger set of possible keywords,” said Tsai. This is important since different keywords yield different sales results.
In “Network Regression for Covariance Estimation,” Tsai and his co-authors applied their statistical model to a real dataset from a major wireless phone company, using it to quantify the influence an individual customer has on the phone usage of other customers. If the company could identify those customers who most frequently communicated with others using the same service, it could invest in incentives to encourage that influential customer for promotions, which would increase overall usage and, as a consequence, revenue.