Designed Experiment with Nonnormally Distributed Responses

Article

Chapman, Robert E.; Svacha, David   (2006, ASQ and Taylor & Francis Group, LLC)   Eastern Michigan University, Ypsilanti, MI; TRW Corporation, Farmington Hills, MI

Quality Engineering    Vol. 18    No. 2
QICID: 20472    April 2006    pp. 179-187
List $10.00
Member $5.00

FOR A LIMITED TIME, ACCESS TO THIS CONTENT IS FREE!
You will need to be signed in.
New to ASQ? Register here.

Article Abstract

[This abstract is based on the authors' abstract.]Temperature and two categorical factors of an electronic component are characterized using a designed experiment. The three modeling approaches used are exact distribution fitting, use of the distribution median and interquartile range, and treating the data as normally distributed. Comparisons and further analysis showed that the central tendency parameters with respect to temperature followed the Arrhenius relationship and that the temperature effects could be considered as nonlinear accelerated aging.

Keywords

Arrhenius model,Design of experiments (DOE),Linear models,Nonnormal distribution curve


Browse QIC Articles Chronologically:     Previous Article     Next Article

New Search

Featured advertisers





ASQ is a global community of people passionate about quality, who use the tools, their ideas and expertise to make our world work better. ASQ: The Global Voice of Quality.