1st Edition

Design and Analysis of Experiments with SAS

By John Lawson Copyright 2010
    596 Pages 169 B/W Illustrations
    by Chapman & Hall

    A culmination of the author’s many years of consulting and teaching, Design and Analysis of Experiments with SAS provides practical guidance on the computer analysis of experimental data. It connects the objectives of research to the type of experimental design required, describes the actual process of creating the design and collecting the data, shows how to perform the proper analysis of the data, and illustrates the interpretation of results.

    Drawing on a variety of application areas, from pharmaceuticals to machinery, the book presents numerous examples of experiments and exercises that enable students to perform their own experiments. Harnessing the capabilities of SAS 9.2, it includes examples of SAS data step programming and IML, along with procedures from SAS Stat, SAS QC, and SAS OR. The text also shows how to display experimental results graphically using SAS ODS graphics. The author emphasizes how the sample size, the assignment of experimental units to combinations of treatment factor levels (error control), and the selection of treatment factor combinations (treatment design) affect the resulting variance and bias of estimates as well as the validity of conclusions.

    This textbook covers both classical ideas in experimental design and the latest research topics. It clearly discusses the objectives of a research project that lead to an appropriate design choice, the practical aspects of creating a design and performing experiments, and the interpretation of the results of computer data analysis. SAS code and ancillaries are available at http://lawson.mooo.com

    Statistics and Data Collection
    Beginnings of Statistically Planned Experiments
    Definitions and Preliminaries
    Purposes of Experimental Design
    Types of Experimental Designs
    Planning Experiments
    Performing the Experiments
    Use of SAS Software

    Completely Randomized Designs with One Factor
    Replication and Randomization
    A Historical Example
    Linear Model for Completely Randomized Design (CRD)
    Verifying Assumptions of the Linear Model
    Analysis Strategies When Assumptions Are Violated
    Determining the Number of Replicates
    Comparison of Treatments after the F-Test

    Factorial Designs
    Classical One at a Time versus Factorial Plans
    Interpreting Interactions
    Creating a Two-Factor Factorial Plan in SAS
    Analysis of a Two-Factor Factorial in SAS
    Factorial Designs with Multiple Factors—Completely Randomized Factorial Design (CRFD)
    Two-Level Factorials
    Verifying Assumptions of the Model

    Randomized Block Designs
    Creating a Randomized Complete Block (RCB) Design in SAS
    Model for RCB
    An Example of a RCB
    Determining the Number of Blocks
    Factorial Designs in Blocks
    Generalized Complete Block Design
    Two Block Factors Latin Square Design (LSD)

    Designs to Study Variances
    Random Sampling Experiments (RSE)
    One-Factor Sampling Designs
    Estimating Variance Components
    Two-Factor Sampling Designs—Factorial RSE
    Nested SE
    Staggered Nested SE
    Designs with Fixed and Random Factors
    Graphical Methods to Check Model Assumptions

    Fractional Factorial Designs
    Introduction to Completely Randomized Fractional Factorial (CRFF)
    Half Fractions of 2k Designs
    Quarter and Higher Fractions of 2k Designs
    Criteria for Choosing Generators for 2k-p Designs
    Augmenting Fractional Factorials
    Plackett–Burman (PB) Screening Designs
    Mixed-Level Fractional Factorials Orthogonal Array (OA)

    Incomplete and Confounded Block Designs
    Balanced Incomplete Block (BIB) Designs
    Analysis of Incomplete Block Designs
    Partially Balanced Incomplete Block (PBIB) Designs—Balanced Treatment Incomplete Block (BTIB)
    Youden Square Designs (YSD)
    Confounded 2k and 2k-p Designs—Completely Confounded Blocked Factorial (CCBF) and Completely Confounded Blocked Fractional Factorial (CCBFF)
    Confounding 3 Level and p Level Factorial Designs
    Blocking Mixed Level Factorials and OAs
    Partial CBF

    Split-Plot Designs
    Split-Plot Experiments with CRD in Whole Plots (CRSP)
    RCB in Whole Plots (RBSP)
    Analysis Unreplicated 2k Split-Plot Designs
    2k-p Fractional Factorials in Split Plots (FFSP)
    Sample Size and Power Issues for Split-Plot Designs

    Crossover and Repeated Measures Designs
    Crossover Designs (COD)
    Simple AB, BA Crossover Designs for Two Treatments
    Crossover Designs for Multiple Treatments
    Repeated Measures Designs
    Univariate Analysis of Repeated Measures Design

    Response Surface Designs
    Fundamentals of Response Surface Methodology
    Standard Designs for Second-Order Models—Completely Randomized Response Surface (CRRS) Designs
    Creating Standard Designs in SAS
    Non-Standard Response Surface Designs
    Fitting the Response Surface Model with SAS
    Determining Optimum Operating Conditions
    Response Surface Designs in Blocks (BRS)
    Response Surface Designs in Split-Plots (RSSP)

    Mixture Experiments
    Models and Designs for Mixture Experiments
    Creating Mixture Designs in SAS
    Analysis of Mixture Experiment
    Constrained Mixture Experiments
    Blocking Mixture Experiments
    Mixture Experiments with Process Variables
    Mixture Experiments in Split Plot Arrangements

    Robust Parameter Design Experiments
    Noise Sources of Functional Variation
    Product Array Parameter Design Experiments
    Analysis of Product Array Experiments
    Single Array Parameter Design Experiments
    Joint Modeling of Mean and Dispersion Effects

    Experimental Strategies for Increasing Knowledge
    Sequential Experimentation
    One-Step Screening and Optimization
    Evolutionary Operation
    Concluding Remarks



    A Review and Exercises appear at the end of each chapter.


    John Lawson is a professor in the Department of Statistics at Brigham Young University.

    This book deserves to be seriously considered as an external reference for a beginning, one semester course in experimental design. It is a handy, reference showing how to get things done quickly using SAS. …
    —Francis Giesbrecht, Biometrics, December 2011

    The scope of the material coverage is one of the strengths of this book. The author brings a wealth of industrial, consulting, and teaching experience to the book, and adds his great writing style, which keeps the reader paying attention throughout the book. … one of the biggest strengths of the book is the breadth of coverage of topics and examples relevant to different disciplines. … The level of detail with respect to SAS codes in this text is excellent. … I would say that this book fills a gap in guiding the design and analyses of experiments using SAS, and would be well suited as a text for students in applied disciplines who had some linear algebra and statistics background. This book is also an outstanding reference for design and analysis of experiments using SAS. In this book I can find SAS codes for virtually all problems I had to solve in applications, and I will be reaching for this book time and time again in the future.
    —Alla Sikorskii, The American Statistician, August 2011

    The design and analysis of experiments is a fundamental part of statistics, and this book gives a comprehensive treatment of this broad topic. … this book focuses on linking concepts to practice. … The examples are taken from a range of areas, including pharmaceutical science and industrial manufacturing. … A companion website includes SAS code and data sets.
    The book covers the basics that you would expect … . A wide variety of other topics are also covered, including split-plot designs, mixture experiments and robust-parameter design. Of particular interest to medical statisticians may be the chapter on crossover and repeated measurement studies …
    The inclusion of so many exercises makes this book ideal for teaching. …
    I think this book achieves its objectives. It is a comprehensive text on an important subject and it is sure to make designing and analysing experiments in SAS more straightforward. The inclusion of advanced topics and modern methods is a particular benefit in this regard.
    —David Woods, Statistics in Medicine, 2011

    The exposition throughout is first rate. The presentation and organization, the coverage of the topics, and the discussions of the examples are all excellent. If you are an SAS user needing help with experimental design, you will certainly profit from this text.
    International Statistical Review (2011), 79, 1

    … The book’s strongest point is its wealth of practical examples from a wide range of fields, such as agriculture, industrial production, psychology, pharmacology etc. … the examples are very helpful for grasping the ideas behind applied experimentation. … a very useful addition to the library of anyone with an already strong understanding of linear models, some familiarity with SAS, and interest or experience in applied experimentation. … [also] useful for statistically skilled readers who want to use software other than SAS for design and analysis of experiments. Applied experimenters without a strong statistical background or at least interest will benefit from individual examples…
    Journal of Statistical Software, December 2010, Volume 37