Seminar by Bryan Shepherd, Vanderbilt University

Abstract

Detection limits (DLs), where a variable cannot be measured outside of a certain range, are common in research. DLs may vary across study sites or over time. Most approaches to handle DLs in response variables implicitly make strong parametric assumptions on the distribution of data outside DLs. We propose a new approach to deal with multiple DLs based on a widely used ordinal regression model, the cumulative probability model (CPM). The CPM is a rank-based, semiparametric linear transformation model that can handle mixed distributions of continuous and discrete outcome variables. These features are key for analyzing data with DLs because while observations inside DLs are continuous, those outside DLs are censored and generally put into discrete categories.  With a single lower DL, CPMs assign values below the DL as having the lowest rank. With multiple DLs, the CPM likelihood can be modified to appropriately distribute probability mass. We demonstrate the use of CPMs with DLs via simulations and a data example. This work is motivated by a study investigating factors associated with HIV viral load 6 months after starting antiretroviral therapy in Latin America; 56\% of observations are below lower DLs that vary across study sites and over time.

Bio

Bryan Shepherd is a professor of biostatistics at Vanderbilt University. He received his PhD in Biostatistics in 2005 from the University of Washington. His primary research interests can be broadly summarized as developing and applying novel statistical methods to studies of HIV/AIDS and other diseases of global health importance. His statistical methods research has been motivated by problems encountered in collaborative work, with a particular emphasis on causal inference, methods for analyzing messy observational data, and ordinal/rank-based analyses. Dr. Shepherd is currently the principal investigator of three grants from the National Institutes of Health: one related to ordinal data analysis, another related to correcting measurement error with electronic health record data, and another related to training biostatisticians in Nigeria. He is a fellow of the American Statistical Association.