Various Usage of Influence Functions for Complicated Statistics in the Context of Survey Sampling - Dr. Yu
Biostatistics Branch Seminar Series
March 6, 2020 | 10:30 AM – 11:30 AM
NCI Shady Grove 7E032/034 Rockville, Maryland
Jihnhee Yu, Ph.D.
Department of Biostatistics,
SUNY at Buffalo
Publicly available national survey data are useful for the evidence-based research to advance our understanding of important questions in the health and biomedical sciences. Appropriate variance estimation is a crucial step to evaluate the strength of evidence in the data analysis. In this talk, we explain that a common practice to obtain the variance based on the total estimates of influence functions may result in undesirable consequences such as susceptibility to data shift and severely inflated variance estimates. We propose to use the variance estimator of the mean (mean-approach) instead of the variance estimator of the total (total-approach). Then, we discuss influence functions for complicated statistics such as internal consistency reliability statistics for survey data analysis. Some real data examples using the National Comorbidity Survey Replication and the National Health and Nutrition Examination Survey are presented.
**The mission of the Biostatistics Branch (BB) is to be an outstanding biostatistics unit that can contribute to the understanding of cancer etiology and to improve public health by the development and application of quantitative methods. The BB Investigators develop statistical methods and data resources to strengthen observational studies, intervention trials, and laboratory investigations of cancer.**