Online Program

Return to main conference page
Thursday, February 15
PS1 Poster Session 1 and Opening Mixer Thu, Feb 15, 5:30 PM - 7:00 PM
Salons F-I

Statistical Modeling for Repeated Measures in Rubber Research (303601)

View Presentation View Presentation

Ray Laakso, The Dow Chemical Company 
Yuming Lai, The Dow Chemical Company 
Greg Li, The Dow Chemical Company 
*Wenzhao Yang, The Dow Chemical Company 

Keywords: Repeated Measures, Covariance Structure, Random Regression

EPDM is a synthetic rubber widely used in applications such as transportation, infrastructure, sports, leisure, and appliance. Dow, as a leading manufacturer of EPDM, continuously innovates in the development of EPDM products and applications to achieve superior properties including high temperature heat aging. In this Dow case study, the heat aging properties of different EPDM rubbers were repeatedly measured over time (repeated measures). Due to the time dependence, proper analysis is needed for model prediction and inference. We analyzed the data using three methods: linear regression, covariance structure and random regression. Linear regression completely pools the data by assuming a common variance for all samples across time. Covariance structure is specified to reflect the correlation pattern in the repeated measures. Random regression incorporates the sample specific effects and provides more inference in variability between samples over time. We identified the optimal samples for multiple heat aging properties that met the specification targets. In this poster, we demonstrate the power of statistical modeling and graphical tools for research optimization.