CMStatistics 2018: Start Registration
View Submission - CMStatistics
B0459
Title: Analysis of quantitative high throughput screening data using a robust nonlinear mixed effects model estimation Authors:  Changwon Lim - Chung-Ang University (Korea, South) [presenting]
Chorong Park - (Korea, South)
Abstract: Quantitative high throughput screening (qHTS) data is used to assess the toxicity of a number of chemicals in short period of time by collectively analyzing them at several concentrations. The qHTS data can be analyzed by using a nonlinear mixed effects model that considers both intra-individual variability and inter-individual variability. Since qHTS data generated by repeating the same experiment several times for each chemical, it mainly analyzed using a nonlinear mixed model. In the nonlinear mixed model, one outlier can distort parameter estimates within each individual or overall estimates. We apply a one-step approach which is one of the robust estimation methods to estimate the fixed effect parameters and the variance-covariance structure. In addition, toxic chemicals were classified based on the significance of a parameter which means efficacy of the drugs.