List of publications

We present a randomization-based inferential framework for experiments characterized by a strongly ignorable assignment mechanism where units have independent probabilities of receiving treatment. Previous works on randomization tests often assume these probabilities are equal within blocks of units. We consider the general case where they differ across units and show how to perform randomization tests and obtain point estimates and confidence intervals. Furthermore, we develop rejection-sampling and importance-sampling approaches for conducting randomization-based inference conditional on any statistic of interest, such as the number of treated units or forms of covariate balance. We establish that our randomization tests are valid tests, and through simulation we demonstrate how the rejection-sampling and importance-sampling approaches can yield powerful randomization tests and thus precise inference. Our work also has implications for observational studies, which commonly assume a strongly ignorable assignment mechanism. Most methodologies for observational studies make additional modeling or asymptotic assumptions, while our framework only assumes the strongly ignorable assignment mechanism, and thus can be considered a minimal-assumption approach.

Comparing apples to apples: an environmental criminology analysis of the effects of heat and rain on violent crimes in Boston
Alice J. Sommer, Mihye Lee & Marie-Abèle C. Bind Palgrave Communicationsvolume 4, Article number: 138 (2018)   
Weather characteristics have been suggested by many social scientists to influence criminality. A recent study suggested that climate change may cause a substantial increase in criminal activities during the twenty-first century. The additional number of crimes due to climate have been ethoroughly discussed the first draft of the paper. Allstimated by associational models, which are not optimal to quantify causal impacts of weather conditions on criminality. Using the Rubin Causal Model and crime data reported daily between 2012 and 2017, this study examines whether changes in heat index, a proxy for apparent temperature, and rainfall occurrence, influence the number of violent crimes in Boston. On average, more crimes are reported on temperate days compared to extremely cold days, and on dry days compared to rainy days. However, no significant differences in the number of crimes between extremely hot days versus less warm days could be observed. The results suggest that weather forecasts could be integrated into crime prevention programs in Boston. The weather–crime relationship should be taken into account when assessing the economic, sociological, or medical impact of climate change. Researchers and policy makers interested in the effects of environmental exposures or policy interventions on crime should consider data analyses conducted with causal inference approaches.