High Dimensional Data

Information and technology have revolutionized data collection. High-dimensional data, including, but not limited to, genetic data, image data such as Magnetic resonance imaging (MRI) and functional MRI, surveillance video data and network data, are available in various research fields. Data scientists need powerful, effective analytic methods to glean maximum scientific insight from these data. Thus, high-dimensional data analysis becomes fundamental in data science, and developing effective statistical procedures for high-dimensional data is one of the most active research topics in statistics and data science.

Over the last two decades, Penn State statistical faculty members have been developing many novel and powerful statistical procedures for analyzing high-dimensional data. These innovative procedures for high-dimensional data include variable selection and feature screening (Runze Li and Lingzhou Xue), statistical inference for high-dimensional mean and high-dimensional regression coefficients (Runze Li and Lingzhou Xue), statistical computing and large-scale optimization (Runze Li, Lingzhou Xue), statistical learning procedures (Jia Li, Justin Silverman, Bharath Sriperumbudur and Lingzhou Xue), dimension reduction (Bing Li and Fransesca Chiaromonte) and real-world applications of high-dimensional data methodology in biomedical study, genetic study, imaging analysis and neural science (Fransesca Chiaromonte, Nicole Lazar, Jia Li, Runze Li and Hyebin Song)