Hypothesis testing is an integral part in the process of experimental design that is used to identify significant effects in a study. A significant effect is one that is statistically determined to influence the response variable of interest and is based on the results of a hypothesis test. Any hypothesis test is prone to two types of error. When an effect is not significant in reality but the null hypothesis is rejected, then it is called a type I error and specified as α. Conversely, when an effect is significant in reality but we fail to reject the null hypothesis, then a type II error is committed and specified as β. Statistical power of a factor is defined as the probability of not committing a type II error (1- β). This research focuses on increasing the statistical power of a factor by augmenting the experimental design with appropriate runs. In this work, a methodology is proposed to integrate power calculations into the existing design of experiment framework. The research also includes a case study to demonstrate the application of the proposed method to real life problems.

Library of Congress Subject Headings

Experimental design; Statistical power analysis

Publication Date


Document Type


Student Type


Degree Name

Industrial and Systems Engineering (MS)

Department, Program, or Center

Industrial and Systems Engineering (KGCOE)


Rachel Silvestrini

Advisor/Committee Member

Brian Thorn


Physical copy available from RIT's Wallace Library at QA279 .N34 2016


RIT – Main Campus