In 1999, I joined the University of Haifa as a professor of statistics, and I currently serve as chair of the Department of Statistics. My research area is primarily methodological and aims at bridging theory and practice, including statistical inference under constraints, methods for ranking and rating and biostatistics. I earned a doctorate in biostatistics from Harvard University (1996), where my thesis advisor was the legendary Marvin Zelen. My master's degree in statistics is from Carnegie Mellon University (1992), and before that, I studied medicine at the Hadassah Medical School of the Hebrew University.
Prof. Ori Davidov
davidov@stat.haifa.ac.il
Although my training had been in Biostatistics with time my research interests have evolved and shifted. Currently, my research is focused on the development of inferential procedures for order and rank data. The key idea in the analysis of ordered data is to incorporate qualitative, external, information in data analysis. This external information comprises, most often, of a set of inequalities on the model parameters. For example, we may know a priori that some treatments result in better outcomes than others. It turns out that using such information, when appropriate, is highly beneficial in the analysis. Ordered data arises naturally in both experimental and observational studies in a wide variety of applications in the biomedical and social sciences. Since the analysis of ordered data involves restricting, or constraining, some of the parameters of the model the resulting procedures tend to be more complicated compared to their unrestricted counterparts. This means that sophisticated optimization techniques are called for and the resulting theory is more challenging compared with standard unordered methods. I enjoy this extra challenge which is part of the beauty of the field. I am currently involved in a number of different projects in this general area of research. In particular I am interested in the development of nonparametric and semiparametric methods for the analysis of such problems as the assessment of drug interactions, the analysis of multiple outcomes in clinical trials, the analysis of case control studies, and the use of constraints to better rank and compare alternatives. Another recent line of research that I am involved in is experimental design where we have used methods borrowed from game theory to improve the way many experiments are conducted.