Congratulations to Ema Perkovic, Fang Han, and Alex Luedtke on receiving grant funding from the Division of Mathematical Sciences (DMS) at National Science Foundation (NSF)!
Ema Perkovic, Assistant Professor of Statistics, is receiving grant to support for her research on “Leveraging Background Knowledge for Identification and Estimation of Causal Effects in the Presence of Latent Variables”. Estimating causal effects is a goal in many scientific endeavors, and often, the only available data are those from observational studies. However, estimating causal effects based on observational data alone is not always possible. This project aims to study a hybrid method that leverages both expert knowledge and observational data that may help estimate a causal effect or narrow down a range of likely estimates.
Fang Han, Associate Professor of Statistics, is receiving grant support for his research on “Statistical Methods for Analyzing Complex Structured and Count Data”. This project aims to address complex questions related to causal inference and disease diagnostics by developing graph-based and nonparametric mixture model-based statistics methods that enable robust, interpretable, efficient, and fast analysis of big datasets routinely produced in biology, neuroscience, social sciences, politics, and epidemiology.
Alex Luedtke, Associate Professor of Statistics, and Marco Carone, Adjunct Associate Professor in Statistics, have been awarded support for their research on “Numerical Construction of Optimal Estimators Using Machine Learning Tools”. By facilitating more effective and reliable extraction of information from data, the use of optimal statistical procedures has the potential to lead to new scientific discoveries. Unfortunately, the development of such procedures generally requires advanced training in statistical theory and often relies on large-sample arguments, even when the available sample is small. This project addresses these challenges by introducing two novel strategies for deriving optimal statistical estimators based on computational tools.
Perkovic, Han, and Luedtke receive NSF awards
