Pankratz received B.S. (1992) and M.S. (1994) degrees in Statistics from Brigham Young University. He earned his Doctor of Philosophy degree in Statistics (1999) from Rice University. Following the completion of his Ph.D. degree, he commenced his postdoctoral career at the Mayo Clinic, Rochester, where he joined the Biostatistics Faculty. He moved to the University of New Mexico in 2014 and joined the UNM Comprehensive Cancer Center in 2018.

Personal Statement

A motivating force behind my statistical and collaborative research interests is a desire to come to a better understanding of human diseases. I am committed to working to use statistical techniques to design studies and collect and analyze data that will lead to a deeper understanding of disease development and outcome. My prior work focused on three major areas: breast cancer, vaccine research and dementia. After several years of working in a role where I focused almost entirely on nephrology, I have returned to a position where I focus primarily on cancer-related collaborations. It is the study of these diseases that provide the impetus for my personal research efforts, which lie in three specific areas. • Longitudinal Data: I am interested in understanding and developing methodologies that allow for making proper inferences from data when observations are correlated. It is useful when measurements are made repeatedly and/or on related individuals, and also in various biostatistical applications, such as in the analysis of data from stratified clinical trials. • Statistical Genetics: I am interested in understanding the impact of disease mutations in populations. My primary interests lie in the areas of population-based genetic studies. In particular, I am interested in how data from outbred populations can be applied in such areas as molecular evolution, genetic mapping, sequence analysis, and the statistical/mathematical modeling of biological systems, and also the mapping of disease genes with familial data. I am also interested in better understanding methods for assessing the contribution of genetics to the onset and burden of disease in the current era of high throughput genotyping. • Risk Models: There is tremendous interest currently in the use of risk prediction models as a part of risk assessment and counseling in the clinic. I have begun to develop my abilities in the use of clinical and other data for the purposes of development and evaluation of disease risk assessment models. I served as the co-principal investigator on a grant that was funded to study risk prediction models for breast cancer, and I have developed two risk prediction models, one for breast cancer risk assessment and one for assessing the likelihood that an elderly person would develop mild cognitive impairment.

Areas of Specialty

Biostatistics Risk Prediction Statistical Genetics Longitudinal Data Analysis Statistical Collaboration

Achievements & Awards

Top Paper Recognition: Clinical Journal of the American Society of Nephrology, 2019 Top Peer Reviewer: Global Peer Review Awards, Powered by Publons, Web of Science Group, 2019 Top Reviewer: American Journal of Gastroenterology, 2006 Top Paper Recognition: Journal of Computational and Graphical Statistics, 2003




  • Spanish

Research and Scholarship

My major areas of contributions to science can be highlighted in four broad categories: 1) Analytical approaches for Cox proportional hazards survival analysis with random effects: I have worked to formalize the statistical justification for an implementation of random effects terms into Cox proportional hazards models, and demonstrated that these approaches could be used in linkage analyses for time-to-event phenotypes. 2) Risk of developing cognitive impairment and dementia: I was highly involved in research into questions involving dementias of the elderly, and a prodromal dementia state (Mild Cognitive Impairment or MCI). I have contributed to theoretical and genetic models of dementia development, and have developed a tool that assessed the risk that an elderly individual will develop MCI. 3) Assessing and predicting risk of breast cancer in women with benign breast disease (BBD): Women who undergo breast biopsies and receive benign findings still have an increased risk of developing a future breast cancer. I have helped to better describe breast cancer risk in women with BBD, and to develop models that will assist clinical personnel as they provide care for, and consult with, these women. 4) Understanding breast cancer risk and through genetics and through mammographic density: Genetic markers contribute considerably to breast cancer risk, as does mammographic breast density. I have engaged in important work to uncover genetic markers of breast cancer risk, and have also helped to confirm the heightened risk of breast cancer among women with higher mammographic density and have worked to develop and evaluate methods are used to measure mammographic density.