This text is a solid revision and redesign of Charles Hicks' comprehensive fourth edition of Fundamental Concepts
in the Design of Experiments. It covers the essentials of experimental design used by applied researchers in solving
problems in the field. It is appropriate for a variety of experimental methods courses found in engineering and
statistics departments. Students learn to use applied statistics for planning, running, and analyzing as an experiment.
Students learn to use applied statistics for planning, running, and analyzing an experiment. The text includes
350+ problems taken from the author's actual industrial consulting experiences to give students valuable practice
with real data and problem solving. About 60 new problems have been added for this edition. SAS (Statistical Analysis
System) computer programs are incorporated to facilitate analysis. There is extensive coverage of the analysis
of residuals, the concepts of resolution in fractional replications, the Plackett-Burman designs, and Taguchi techniques.
The new edition will place a greater emphasis on computer use, include additional problems, and add computer outputs
from statistical packages like Minitab, SPSS, and JMP.
The book is written for anyone engaged in experimental work who has a good background in statistical inference.
It will be most profitable reading to those witha background in statistical methods including analysis of variance.
This text is suitable for senior undergraduate/graduate level students in mathematics, statistics, or engineering.
It is appropriate for a variety of experimental methods courses found in engineering and statistics deparmtents
-- majors in this course are usually in applied statistics; non-majors, in industrial and electrical engineering,
or education and life sciences.
Table of Contents
Preface
1. The Experiment, the Design, and the Analysis
1.1. Introduction to Experimental Design
1.2. The Experiment
1.3. The Design
1.4. The Analysis
1.5. Examples
1.6. Summary in Outline
1.7. Further Reading
Problems
2. Review of Statistical Inference
2.1. Introduction
2.2. Estimation
2.3. Tests of Hypothesis
2.4. The Operating Characteristic Curve
2.5. How Large a Sample?
2.6. Application to Tests on Variances
2.7. Application to Tests on Means
2.8. Assessing Normality
2.9. Applications to Tests on Proportions
2.10. Analysis of Experiments with SAS
2.11. Further Reading
Problems
3. Single-Factor Experiments with No Restrictions on Randomization
3.1. Introduction
3.2. Analysis of Variance Rationale
3.3. After ANOVA--What?
3.4. Tests on Means
3.5. Confidence Limits on Means
3.6. Components of Variance
3.7. Checking the Model
3.8. SAS Programs for ANOVA and Tests after ANOVA
3.9. Summary
3.10. Further Reading
Problems
4. Single-Factor Experiments: Randomized Block and Latin Square Designs
4.1. Introduction
4.2. Randomized Complete Block Design
4.3. ANOVA Rationale
4.4. Missing Values
4.5. Latin Squares
4.6. Interpretations
4.7. Assessing the Model
4.8. Graeco-Latin Squares
4.9. Extensions
4.10. SAS Programs for Randomized Blocks and Latin Squares
4.11. Summary
4.12. Further Reading
Problems
5. Factorial Experiments
5.1. Introduction
5.2. Factorial Experiments: An Example
5.3. Interpretations
5.4. The Model and Its Assessment
5.5. ANOVA Rationale
5.6. One Observation Per Treatment
5.7. SAS Programs for Factorial Experiments
5.8. Summary
5.9. Further Reading
Problems
6. Fixed, Random, and Mixed Models
6.1. Introduction
6.2. Single-Factor Models
6.3. Two-Factor Models
6.4. EMS Rules
6.5. EMS Derivations
6.6. The Pseudo-F Test
6.7. Expected Mean Squares Via Statistical Computing Packages
6.8. Remarks
6.9. Repeatability and Reproducibility for a Measurement System
6.10. SAS Problems for Random and Mixed Models
6.11. Further Reading
Problems
7. Nested and Nested-Factorial Experiments
7.1. Introduction
7.2. Nested Experiments
7.3. ANOVA Rationale
7.4. Nested-Factorial Experiments
7.5. Repeated-Measures Design and Nested-Factorial Experiments
7.6. SAS Programs for Nested and Nested-Factorial Experiments
7.7. Summary
Further Reading
Problems
8. Experiments of Two or More Factors: Restrictions on Randomization
8.1. Introduction
8.2. Factorial Experiment in a Randomized Block Design
8.3. Factorial Experiment in a Latin Square Design
8.4. Remarks
8.5. SAS Programs
8.6. Summary
Problems
9. 2f Factorial Experiments.
9.1. Introduction
9.2. 2 Squared Factorial
9.3. 2 Cubed Factorial
9.4. 2f Remarks
9.5. The Yates Method
9.6. Analysis of 2f Factorials When n=1
9.7 Some Commments about Computer Use.
9.8. Summary
9.9. Further Reading
Problems
11.1. Introduction
11.2. A Split-Plot Design
11.3. A Split-Split-Plot Design
11.4. Using SAS to Analyze a Split-Plot Experiment
11.5. Summary
11.6. Further Reading
Problems
12. Factorial Experiment: Confounding in Blocks
12.1. Introduction
12.2. Confounding Systems
12.3. Block Confounding, No Replication
12.4. Block Confounding with Replication
12.5. Confounding in 3F Factorials
12.6. SAS Progrms
12.7. Summary
12.8. Further Reading
Problems
14. The Taguchi Approach to the Design of Experiments
14.1. Introduction
14.2. The L4 (2 Cubed) Orthogonal Array
14.3. Outer Arrays
14.4. Signal-To-Noise Ratio
14.5. The L8 (2 7) Orthogonal Array
14.6. The L16 (2 15) Orthogonal Array
14.7. The L9 (3 4) Orthogonal Array
14.8. Some Other Taguchi Designs
14.9. Summary
14.10. Further Reading
Problems
15. Regression
15.1. Introduction
15.2. Linear Regression
15.3. Curvilinear Regression
15.4. Orthogonal Polynomials
15.5. Multiple Regression
15.6. Summary
15.7. Further Reading
Problems
16. Miscellaneous Topics
16.1. Introduction
16.2. Covariance Analysis
16.3. Response Surface Experimentation
16.4. Evolutionary Operation (EVOP)
16.5. Analysis of Attribute Data
16.6. Randomized Incomplete Blocks: Restriction On Experimentation
16.7. Youden Squares
16.8. Further Reading
Problems
Summary and Special Problems
Glossary of Terms
References
Statistical Tables
Table A. Areas Under the Normal Curve
Table B. Student's t Distribution
Table C. Cumulative Chi-Square Distribution
Table D. Cumulative F Distribution
Table E.1. Upper 5% of Studentized Range q
Table E.2. Upper 1% of Studentized Range q
Table F. Coefficients of Orthogonal Polynomials
