Daniel Nevo

Biographical Details

Daniel Nevo is an Associate Professor in the Department of Statistics and Operations Research at Tel Aviv University. His research spans statistical theory, methodological development, and applied work, with a particular emphasis on causal inference and survival analysis. He collaborates with clinicians, epidemiologists, economists, and computer scientists in both academia and health organizations, aiming to draw causal conclusions from complex and rich datasets. Daniel is a member of the TAD Center for Artificial Intelligence and Data Science and the Tel Aviv University Center for Combating Pandemics. He serves as an Associate Editor for Biometrics and is a council member of the Israel Statistics and Data Science Association. Daniel received his PhD in Statistics from the Hebrew University of Jerusalem in 2016, followed by a three-year postdoctoral fellowship in the Departments of Biostatistics and Epidemiology at the Harvard T.H. Chan School of Public Health, before joining Tel Aviv University in 2018.

Research Interests

Daniel Nevo’s research advances causal inference methodology and applies it to real problems. One major line of his work involves causal inference for time-to-event data, and specifically alternatives to hazard ratios and complex data structures such as semi-competing risks. In those situations, defining and identifying meaningful estimands is often challenging. Daniel also works on causal inference under interference, where treatment assigned to one unit can affect others. A key assumption shared by existing methods is that the network encoding the interference structure is given and correctly specified. Daniel studies the implications of violations of this assumption and offers solutions when the network is fixed but misspecified, only proxy observations are available, or when the network is observed, but interest lies in causal effects in a new population under a different, possibly unknown, network. In a different vein, Daniel has recently been working on methods related to econometrics, including the use of negative controls to assess instrumental variable assumptions and recent work on correcting invalid regression discontinuity designs using data from multiple time periods. Daniel’s research is often motivated by real-world problems emerging from existing datasets, and he actively collaborates with domain experts on projects requiring causal reasoning and methodology.

Select Publications

Danieli, O., Nevo, D., Walk, I., Weinstein, B., & Zeltzer, D. (2025). Negative control falsification tests for instrumental variable designs. arXiv preprint arXiv:2312.15624.

Nevo, D., & Gorfine, M. (2022). Causal inference for semi-competing risks data. Biostatistics, 23(4), 1115-1132.

Hayek, S., Shaham, G., Ben-Shlomo, Y., Kepten, E., Dagan, N., Nevo, D., … & Barda, N. (2022). Indirect protection of children from SARS-CoV-2 infection through parental vaccination. Science, 375(6585), 1155-1159.

Nevo, D., Lok, J. J., & Spiegelman, D. (2021). Analysis of “learn-as-you-go” (LAGO) studies. Annals of statistics, 49(2), 793.