Room 21-254C CHS
Department of Biostatistics
UCLA School of Public Health
Los Angeles, CA 90095-1772
- BS Mathematics (1999) Boğaziçi University, Istanbul, Turkey
- MS Statistics (2001) University of California, Davis
- PhD Statistics (2004) University of California, Davis
My main areas of statistical methodology research are longitudinal and functional data analysis. My program of independent and creative research is motivated by my collaborative research in psychiatry and nephrology. I serve as a senior consulting faculty member in SIStat, UCLA Biostatistics core in the Semel Institute of Neuroscience and Human Behavior. Through this role, I collaborate on a wide range of scientific projects on ASD, schizophrenia, bipolar disorder, ADHD, major depressive disorder, posttraumatic stress disorder and social cognition in HIV. A dominant theme in my collaborations in psychiatry is studying the heterogeneous nature of Autism Spectrum Disorder (ASD). My research in autism has led to my methodology R01 grant (along with two colleagues from UCLA Department of Biostatistics) from NIH National Institutes of General Medical Sciences to develop novel longitudinal functional methods for the analysis of electroencephalogram (EEG) data from children with ASD. This proposal is specifically concerned with complex patient-level information, acquired in the form of high frequency functional data, such as data recorded during both event-related and continuous exposure electroencephalography (EEG) studies. We conceptualize such structures as longitudinally observed functional data, where longitudinal time indexes longer-term changes in the processes during the experiment and functional time indexes short term dynamics.
My independent research program in examining outcomes in patients on dialysis, such as the risk of cardiovascular events and infections is funded by my R01 grant from NIH National Institute of Diabetes and Digestive and Kidney Diseases since 2011. The goal of this line of work is to develop a rigorous framework to estimation and inference for multilevel time-dynamic modeling that accommodates multilevel data structures (e.g., patients nested within dialysis facilities, hospitals or care providers, and observations over time nested within patients). Our work centers around the specific dual sets of goals: 1) patient-level inference, such as patient-centered decision making and understanding the time-varying effects of patient risk factors on outcomes over time; and 2) facility-level inference, including quantification of facility-level factors’ effects on patient outcome, prediction and assessment of facility performance with appropriate risk, case-mix adjustment.
- Biostat 202A Application of Statistical Theories in Biomedical Research
- Biostat 202B Topics in Estimation