Comparison of Two Wood Plastic Composite Extruders Using Bootstrap Confidence Intervals on Measurements of Sample Failure Data

ABSTRACT

Wood plastic composite (WPC) boards are an emerging engineered wood composite that is a substitute for solid wood and other wood composite materials used for exterior applications, primarily decking. We are interested in understanding the strength of these boards and estimating the lower percentiles of failure under perpendicular pressure. The strength of WPC is determined by the perpendicular pressure required to permanently deform a board (modulus of elasticity, MOE) and the perpendicular pressure required to rupture the board (modulus of rupture, MOR). Two WPC production-size extrusion lines at the same facility are compared in this article by comparing the distributions of pressure to failure for samples of WPC extruded from each line. Parametric bootstrapping is used to calculate confidence intervals of the 1st, 5th, and 10th percentiles of the MOE and the MOR from each line. Furthermore, both parametric and nonparametric bootstrapping are performed to estimate confidence intervals on the differences between the two lines for the 1st, 5th, and 10th percentiles of the MOE and the MOR. A statistical difference between the strength of the WPC extruded from the two lines is found in the MOR.

KEYWORDS:

• Bonferroni method
• bootstrap
• confidence interval
• hypothesis test
• wood plastic composite

ACKNOWLEDGMENTS

This research was partially supported by The University of Tennessee Agricultural Experiment Station, Center for Renewable Carbon, McIntire-Stennis TEN00MS-89, USDA CSREES Special Wood Utilization Research Grant R11-2216-100, and The University of Tennessee College of Business Administration. We also thank two anonymous reviewers for their helpful comments and suggestions that led to substantial improvements to this article.

Notes

^a The population's distribution can be estimated from the distribution of the original sample (sample obtained in step 1). A common method for fitting distributions is maximum likelihood estimation and scoring criteria for selecting the best distribution among several candidates (e.g., AIC).

^a Smallest values are underlined.

Additional information

Notes on contributors

David J. Edwards

David J. Edwards is Assistant Professor of Statistics in the Department of Statistical Sciences and Operations Research at Virginia Commonwealth University. Dr. Edwards' research interests are in the areas of experimental design and reliability data analysis. He has an especial interest in sequential experimentation and response surface methodology. He is a member of the American Statistical Association and the American Society for Quality. He is on the Editorial Review Board of the Journal of Quality Technology.

Ramón V. León

Ramón V. León is Associate Professor of Statistics at the University of Tennessee, Knoxville. Until June 1991, he was supervisor of the Quality Engineering Research and Technology Group of the Quality Process Center of AT&T Bell Laboratories. Dr. León received his Ph.D. in probability and statistics from The Florida State University. Before joining AT&T Bell Laboratories in 1981, Dr. León was on faculty of The Florida State University and Rutgers University.

Timothy M. Young

Timothy M. Young is a Full Professor in the Center for Renewable Carbon at the University of Tennessee. He earned a Ph.D. in Natural Resources from the University of Tennessee. He has written 170+ articles in academic and trade journals for the forest products industry and other areas, such as reliability and management. He has extensive grants from the private sector and the U.S. Department of Agriculture. His current areas of research include the application of real-time statistical process control, commercial data warehousing in the context of statistical human machine interface platforms, statistical data mining, and improved reliability.

Frank M. Guess

Frank M. Guess is a Full Professor in the Department of Statistics at the University of Tennessee. Dr. Guess has had grants from IBM, Air Force Office of Scientific Research, and the Army Office of Research. He was on the invited Program Committee in 2005 for the 10th Anniversary MIT's Information Quality Conference, plus also served on the Program Committees for 2006 and 2007 MIT IQ Conference. He has published over 50 papers in reliability and statistics journals.

Kevin A. Crookston

Kevin A. Crookston graduated May 2009 from the University of Tennessee with an MS degree in Industrial Statistics. He earned his BS April 2007 in Statistics with an emphasis in Quality Science and Manufacturing from Brigham Young University. While pursuing an education, Crookston also interned at ITT Aerospace Industries in Californian and at ATK Launch Systems in Utah. He now works in Arizona.