San
Francisco Bay Area Chapter of American Statistical Association
Monthly
Seminar
Time: 4:30 – 6:00 pm, May 25, 2017 (4:30-5:00 networking and light refreshment, 5:00-6:00
seminar)
Location: Building 303 Bay view conference room, Gilead 303 Velocity, Foster City, CA 94404 *Free parking* Please check in at the
front desk.
Speaker: Dr. Xiaoli Qi Principal Member of Technical Staff, Tech Lead Oracle Corporation, Redwood Shores, CA
Title: Nonparametric
calibration of two common susceptibility tests using interval-censored data
with measurement error
Abstract:
Drug dilution (MIC) and
disk diffusion (DIA) are the two common tests to determine pathogen
susceptibility to antibiotics. In the drug dilution method, the classification
breakpoints are concentrations and based directly on the pharmacokinetics and
pharmacodynamics of the drug. For the disk diffusion method, these
concentration breakpoints need to be converted into zone diameters. In this
research, we've proposed a robust method of DIA breakpoint determination. Based
on M-spline theory, we employ nonparametric density estimation and
nonparametric monotone regression techniques to estimate the MIC density, the
true MIC/DIA relationship, and the DIA breakpoints. Simulation studies have
shown that this nonparametric method performs very well. Compared with the
error-rate bounded method, the resulting DIA breakpoints are considerably more
precise. This method could be applied to more general errors-in-variables model
situations with and without interval censoring.