Deliang Dai

Forskning

Multivariate analysis stands as a powerful methodological framework in statistical research, enabling investigators to examine complex datasets characterized by multiple interdependent variables simultaneously. This analytical approach has become indispensable across diverse scientific disciplines where understanding intricate relationships between numerous factors is essential for drawing valid conclusions. Its applications span numerous fields including econometrics, psychometrics, environmental science, marketing and consumer research, genomics and bioinformatics, and social sciences, demonstrating its versatility in addressing complex research questions.

The rapid advancement of the Internet of Things (IoT) has precipitated an exponential growth in data availability, creating both significant challenges and novel opportunities for statistical methodology. This data revolution has particularly highlighted the need for advanced high-dimensional analysis techniques, as traditional methods often prove inadequate when dealing with modern datasets characterized by large numbers of variables relative to observations. This evolving landscape necessitates the development of innovative statistical approaches tailored to address the unique demands of high-dimensional data analysis.

My research program focuses on two interconnected strands: methodological development for high-dimensional statistical analysis and applied data science in energy-related domains. On the methodological front, I develop robust statistical techniques specifically designed for high-dimensional settings, where conventional approaches may fail. Complementing this theoretical work, I investigate practical applications of machine learning and data science methodologies to address pressing challenges in the energy sector, with particular emphasis on developing solutions that bridge the gap between advanced analytics and industrial implementation.