As a statistician, Dr. Kim seeks to balance mathematical and applied statistics in his research, developing innovative statistical methodologies and then utilizing them to analyze real-life data. He developed a multiple interval estimation procedure that simultaneously estimates a large number of parameters and then applied the model to Leukemia gene expression data to better identify the genes associated with leukemia. Additionally, he developed a prediction interval for daily and cumulative COVID-19 deaths in the US, using a Poisson-based regression model that incorporated an innovative method for handling over-dispersion within the dataset. His latest research project involves a new prediction approach that maximizes the agreement measured by a concordance correlation coefficient between predictor and predictand. This novel method could provide a competitive alternative to the classical least-squares method when projects require reproducibility or imputation.
Taeho Kim
Assistant Professor
PhD: University of South Carolina, Columbia, SC
MS: Rutgers, the State University of New Jersey, New Brunswick, NJ
Explore this Profile×
Research Areas
Additional Interests
- Multiple Comparisons
- Prediction Models
- Nonparametric Estimation
Research Statement
Biography
Dr. Kim is an assistant professor in the Department of Mathematics. He earned his Ph.D. in 2019 from the Department of Statistics at the University of South Carolina, under the guidance of Dr. Edsel Peña, with a dissertation titled "Investigations on Multiple Interval Estimators." Following his Ph.D., he completed a postdoc at the University of Haifa in Israel, under the mentorship of Dr. Alexander Goldenshluger.
For leisure time, he enjoys playing sports, practicing the trumpet, and listening to jazz through an old receiver.
Selected Publication:
Kim, T., Lieberman, B., Luta, G., and Peña, E., On Optimal Correlation-Based Prediction. The American Statistician. 76(4), 313-321.
Alexander Goldenshluger and Taeho Kim, Density Deconvolution with Non-Standard Error Distributions: Rates of Convergence and Adaptive Estimation, Electronic Journal of Statistics. Volume 15, Number 1 (2021), 3394-3427.
Edsel Peña and Taeho Kim, Median Confidence Regions in a Nonparametric Model, Electronic Journal of Statistics. Volume 13, Number 2 (2019), 2348-2390.
Teaching
I am currently teaching MATH 312.