Analysis of Categorical Response in Small Sample Experiments

Statistical design of experiments (DOE) is widely used today for process and product characterization and optimization. Owing to cost and time considerations, sometimes only a minimum number of experimental runs can be conducted, with added challenges in analysis when the experimental outcomes canno...

Full description

Saved in:
Bibliographic Details
Published in:Quality and reliability engineering international 2016-07, Vol.32 (5), p.1621-1626
Main Author: Goh, T. N.
Format: Article
Language:English
Subjects:
categorical data
Computer programs
Cost engineering
Data processing
Design of experiments
empirical optimization
likelihood transfer function
Optimization
process and product improvement
Samples
small samples
Software
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Statistical design of experiments (DOE) is widely used today for process and product characterization and optimization. Owing to cost and time considerations, sometimes only a minimum number of experimental runs can be conducted, with added challenges in analysis when the experimental outcomes cannot be measured on a continuous scale and are expressed only in qualitative terms such as ‘excellent’, ‘satisfactory’ and ‘poor’: such outcomes are variously described as ‘categorical’, ‘attribute’, ‘qualitative’, ‘discrete’ or ‘counted’ in nature. This paper offers practical techniques of handling small experiments with such non‐standard DOE response data which are otherwise impossible to analyze by standard statistical software. The suggested procedures, built upon what is called a Likelihood Transfer Function (LTF), do not require complex data analysis but would yield results consistent with the constraints of experimental conditions as well as the objectives of stakeholders. Copyright © 2015 John Wiley & Sons, Ltd.
ISSN:0748-8017
1099-1638
DOI:10.1002/qre.1894