book

JMP 12 Design of Experiments Guide

Name: JMP 12 Design of Experiments Guide
Author: SAS Institute
ISBN: 9781629594446

by SAS Institute

March 2015

Intermediate to advanced

616 pages

14h 55m

English

SAS Institute

Read now

Unlock full access

Contents
Learn about JMP
Documentation and Additional Resources
Formatting Conventions
JMP DocumentationJMP Documentation LibraryDiscovering JMPUsing JMPBasic AnalysisEssential GraphingProfilersDesign of Experiments GuideFitting Linear ModelsSpecialized ModelsMultivariate MethodsQuality and Process MethodsReliability and Survival MethodsConsumer ResearchScripting GuideJSL Syntax ReferenceJMP HelpAdditional Resources for Learning JMPTutorialsSample Data TablesLearn about Statistical and JSL TermsLearn JMP Tips and TricksTooltipsJMP User CommunityJMPer CableJMP Books by UsersThe JMP Starter Window
Introduction to DOE
Overview of Design of Experiment Platforms
Starting Out with DOE
Example and Key Concepts
Overview of Experimental Design and the DOE Workflow
The Coffee Strength ExperimentDefine the Study and GoalsCreate the DesignDefine Responses and FactorsSpecify the ModelSteps to Duplicate Results (Optional)Generate the DesignEvaluate the DesignMake the TableRun the ExperimentAnalyze the DataThe DOE Workflow: Describe, Specify, DesignDefine Responses and FactorsSpecify the ModelGenerate the DesignEvaluate the DesignMake the TablePrinciples and Guidelines for Experimental DesignEffect HierarchyEffect HeredityEffect SparsityCenter Points, Replicate Runs, and Testing
Custom Designs
Construct Designs That Meet Your Needs
Overview of Custom Design
Example of a Custom DesignCreate the DesignResponsesFactorsModelAlias TermsSteps to Duplicate Results (Optional)Design GenerationDesignDesign EvaluationOutput OptionsAnalyze the DataInterpret the Full Model ResultsReduce the ModelInterpret the Reduced Model ResultsOptimize Factor SettingsLock a Factor LevelCustom Design WindowResponsesResponse Limits Column PropertyFactorsFactors OutlineFactor TypesChanges and Random BlocksFactor Column PropertiesDefine Factor ConstraintsSpecify Linear ConstraintsUse Disallowed Combinations FilterUse Disallowed Combinations ScriptModelAlias TermsDesign GenerationDesignDesign EvaluationOutput OptionsCustom Design OptionsSave X MatrixNumber of StartsDesign Search TimeSet Delta for PowerTechnical DetailsDesigns with Randomization RestrictionsRandom Block DesignsSplit-Plot DesignsSplit-Split-Plot DesignsTwo-Way Split-Plot DesignsCovariates with Hard-to-Change LevelsNumbers of Whole Plots and SubplotsOptimality CriteriaD-OptimalityBayesian D-OptimalityI-OptimalityBayesian I-OptimalityAlias OptimalityD-EfficiencyCoordinate-Exchange Algorithm
Examples of Custom Designs
Perform Experiments That Meet Your Needs
Screening Experiments
Design That Estimates Main Effects OnlyDesign That Estimates All Two-Factor InteractionsDesign That Avoids Aliasing of Main Effects and Two-Factor InteractionsSupersaturated Screening DesignsGenerating a Supersaturated DesignAnalyzing a Supersaturated Design Using the Screening PlatformAnalyzing a Supersaturated Design Using Stepwise RegressionDesign for Fixed BlocksResponse Surface ExperimentsResponse Surface DesignConstructing a Response Surface DesignAnalyzing the Experimental ResultsResponse Surface Design with Flexible BlockingComparison of a D-Optimal and an I-Optimal Response Surface DesignI-Optimal DesignD-Optimal DesignMixture ExperimentsMixture Design with Nonmixture FactorsMixture of Mixtures DesignExperiments with CovariatesDesign with Fixed CovariatesDesign with Hard-to-Change CovariatesDesign with a Linear Time TrendExperiments with Randomization RestrictionsSplit-Plot ExperimentTwo-Way Split-Plot Experiment

Definitive Screening Designs
Overview of Definitive Screening Design
Examples of Definitive Screening DesignsDefinitive Screening DesignCreate the DesignAnalyze the Experimental DataComparison with a Fractional Factorial DesignDefinitive Screening Design with BlockingCreate the DesignAnalyze the Experimental DataComparison of a Definitive Screening Design with a Plackett-Burman DesignDefinitive Screening Design WindowResponsesResponse Limits Column PropertyFactorsFactor TypesFactor Column PropertiesOrthogonal Blocking OptionsBlocking in Definitive Screening DesignsAdd Blocks with Center Runs to Estimate Quadratic EffectsAdd Blocks without Extra Center RunsDesignDesign EvaluationOutput OptionsDefinitive Screening Design OptionsTechnical DetailsStructure of Definitive Screening DesignsConference Matrices and the Number of RunsDefinitive Screening Designs for Four or Fewer FactorsAnalysis of Experimental Data
Screening Designs
Overview of Screening Designs
Screening Design ExamplesA Standard Design with Two Continuous Factors and One Categorical FactorA Standard Design for Five Continuous FactorsCreating a Screening DesignEnter ResponsesSpecifying Goal Types and Lower and Upper LimitsUnderstanding Importance WeightsEnter FactorsTypes of FactorsChoose Screening TypeChoose from a List of Fractional Factorial DesignsDesign ListDisplay and Modify DesignAliasing of EffectsLook at the Confounding PatternUnderstanding Design CodesChanging the Coded DesignDesign GenerationNear-Orthogonal DesignsRelated OptionsChi2 EfficiencyDesign EvaluationSpecify Output OptionsView the Design TableCreating a Plackett-Burman DesignCreating a Main Effects Screening Design
The Screening Platform
Analyze Data from Screening Experiments
Overview of the Screening Platform
An Example Comparing Screening and Fit ModelLaunch the Screening PlatformThe Screening ReportContrastsHalf Normal PlotUsing the Fit Model PlatformThe Actual-by-Predicted PlotThe Scaled Estimates ReportA Power AnalysisAdditional Screening Analysis ExamplesAnalyzing a Plackett-Burman DesignAnalyzing a Supersaturated DesignTechnical DetailsOrder of Effect EntryScreening as an Orthogonal RotationLenth’s Pseudo-Standard Error
Response Surface Designs
A Box-Behnken Design: The Tennis Ball Example
The Prediction ProfilerA Response Surface Plot (Contour Profiler)Geometry of a Box-Behnken DesignCreating a Response Surface DesignEnter Responses and FactorsChoose a DesignBox-Behnken DesignsCentral Composite DesignsSpecify Axial Value (Central Composite Designs Only)Specify Output OptionsView the Design Table
Full Factorial Designs
The Five-Factor Reactor Example
Analyze the Reactor DataCreating a Factorial DesignEnter Responses and FactorsSelect Output OptionsMake the Table
Mixture Designs
Mixture Design Types
The Optimal Mixture DesignAdding Effects to the ModelThe Simplex Centroid DesignCreating the DesignSimplex Centroid Design ExamplesThe Simplex Lattice DesignThe Extreme Vertices DesignCreating the DesignAn Extreme Vertices Example with Range ConstraintsAn Extreme Vertices Example with Linear ConstraintsExtreme Vertices Method: How It WorksThe ABCD DesignThe Space Filling DesignFFF Optimality CriterionSet Average Cluster SizeLinear ConstraintsA Space Filling ExampleA Space Filling Example with a Linear ConstraintCreating Ternary PlotsFitting Mixture DesignsWhole Model Tests and Analysis of Variance ReportsUnderstanding Response Surface ReportsA Chemical Mixture ExampleCreate the DesignAnalyze the Mixture ModelThe Prediction ProfilerThe Mixture ProfilerA Ternary Plot of the Mixture Response Surface
Covering Arrays
Detecting Component Interaction Failures
Overview of Covering Arrays
Covering Arrays and StrengthExample of a Covering Array with No Factor Level RestrictionsCreate the DesignAnalyze the Experimental DataExample of a Covering Array with Factor Level RestrictionsCreate the DesignLoad FactorsRestrict Factor Level CombinationsSpecify Disallowed Combinations Using the FilterSpecify Disallowed Combinations Using a ScriptConstruct the Design TableAnalyze the Experimental DataCovering Array WindowFactorsFactors TableEditing the Factors TableFactor Column PropertiesRestrict Factor Level CombinationsUse Disallowed Combinations FilterUse Disallowed Combinations ScriptDesignUnsatisfiable ConstraintsMetricsOutput OptionsThe Covering Array Data TableAnalysis ScriptCovering Array OptionsTechnical DetailsAlgorithm for OptimizeFormulas for MetricsUnconstrained DesignConstrained Design
Discrete Choice Designs
Create a Choice Design with No Prior Information
Create an Example Choice ExperimentCreate a Choice Design and Analyze the DataCreate a Choice Experiment for a Pilot StudyAnalyze the Pilot Study DataDesign a Choice Experiment Using Prior InformationAdminister the Survey and Analyze ResultsInitial Choice Platform AnalysisFind Unit Cost and Trade Off Costs with the ProfilerChoice Design Options
Space-Filling Designs
Overview of Space-Filling Designs
Space Filling Design WindowResponsesResponse Limits Column PropertyFactorsFactors OutlineFactor TypesFactor Column PropertiesDefine Factor ConstraintsSpecify Linear ConstraintsUse Disallowed Combinations FilterUse Disallowed Combinations ScriptSpace Filling Design MethodsDesignDesign DiagnosticsDesign TableSpace Filling Design OptionsSphere-Packing DesignsCreating a Sphere-Packing DesignVisualizing the Sphere-Packing DesignLatin Hypercube DesignsCreating a Latin Hypercube DesignVisualizing the Latin Hypercube DesignUniform DesignsComparing Sphere-Packing, Latin Hypercube, and Uniform MethodsMinimum Potential DesignsMaximum Entropy DesignsGaussian Process IMSE Optimal DesignsFast Flexible Filling DesignsFFF Optimality CriterionSet Average Cluster SizeConstraintsCreating and Viewing a Constrained Fast Flexible Filling DesignBorehole Model: A Sphere-Packing ExampleCreate the Sphere-Packing Design for the Borehole DataGuidelines for the Analysis of Deterministic DataResults of the Borehole Experiment
Accelerated Life Test Designs
Designing Experiments for Accelerated Life Tests
Overview of Accelerated Life Test Designs
Using the ALT Design PlatformPlatform OptionsExample
Nonlinear Designs
Examples of Nonlinear Designs
Using Nonlinear Fit to Find Prior Parameter EstimatesCreating a Nonlinear Design with No Prior DataCreating a Nonlinear DesignIdentify the Response and Factor Column with FormulaSet Up Factors and Parameters in the Nonlinear Design DialogEnter the Number of Runs and Preview the DesignMake Table or Augment the TableAdvanced Options for the Nonlinear Designer
Taguchi Designs
The Taguchi Design Approach
Taguchi Design ExampleAnalyze the DataCreating a Taguchi DesignDetail the Response and Add FactorsChoose Inner and Outer Array DesignsDisplay Coded DesignMake the Design Table
Evaluate Designs
Explore Properties of Your Design
Overview of Evaluate Design
Example of Evaluate DesignAssessing the Impact of Lost RunsConstruct the Intended and Actual DesignsComparison of Intended and Actual DesignsEvaluating Power Relative to a Specified Model
Evaluate Design Launch Window
Evaluate Design WindowFactorsModelAlias TermsDesignDesign EvaluationPower AnalysisPower Analysis OverviewPower Analysis DetailsPower Analysis for Coffee ExperimentPrediction Variance ProfileFraction of Design Space PlotPrediction Variance SurfaceEstimation EfficiencyFractional Increase in CI LengthRelative Std Error of EstimateAlias MatrixAlias Matrix ExamplesColor Map on CorrelationsColor Map ExampleDesign DiagnosticsNotationD EfficiencyG EfficiencyA EfficiencyAverage Variance of PredictionDesign Creation TimeEvaluate Design OptionsTechnical DetailsPower CalculationsPower for a Single ParameterPower for a Categorical EffectRelative Prediction Variance
Augmented Designs
A D-Optimal Augmentation of the Reactor Example
Analyze the Augmented DesignAugmentation ChoicesReplicate a DesignAdd Center PointsCreating a Foldover DesignAdding Axial PointsSpace FillingAdding New Runs and TermsDefine Factor ConstraintsSpecify Linear ConstraintsUse Disallowed Combinations FilterUse Disallowed Combinations ScriptSpecial Augment Design OptionsSave the Design (X) MatrixModify the Design Criterion (D- or I- Optimality)Select the Number of Random StartsDesign Search TimeSpecify the Sphere Radius Value
Prospective Sample Size and Power
Launching the Sample Size and Power Platform
One-Sample and Two-Sample MeansSingle-Sample MeanPower versus Sample Size PlotPower versus Difference PlotSample Size and Power Animation for One MeanTwo-Sample MeansPlot of Power by Sample Sizek-Sample MeansOne Sample Standard DeviationOne Sample Standard Deviation ExampleOne-Sample and Two-Sample ProportionsActual Test SizeOne Sample ProportionOne-Sample Proportion Window SpecificationsTwo Sample ProportionsTwo Sample Proportion Window SpecificationsCounts per UnitCounts per Unit ExampleSigma Quality LevelSigma Quality Level ExampleNumber of Defects Computation ExampleReliability Test Plan and DemonstrationReliability Test PlanExampleReliability DemonstrationExample
Column Properties
Understanding Column Properties Assigned by DOE
Adding and Viewing Column Properties
Response LimitsResponse Limits ExampleEditing Response LimitsDesign RoleDesign Role ExampleCodingLow and High ValuesCoding Column Property and Center PolynomialsCoding ExampleAssigning CodingMixtureMixture ExampleFactor ChangesFactor Changes ExampleValue OrderingValue Ordering ExampleAssigning Value OrderingValue LabelsValue Labels ExampleRunsPerBlockRunsPerBlock ExampleConstraintStateConstraintState Example
Technical Details
The Model and Alias Matrices
The Model Matrix
The Alias MatrixDesigns with Hard or Very Hard Factor ChangesDesigns with If Possible Effects
References
Index
Design of Experiments GuideABCDEFGHIJKLMNOPQRSTUVW-Z

Content preview from JMP 12 Design of Experiments Guide

Chapter 13

Discrete Choice Designs

The Discrete Choice designer creates experiments with factors that are product attributes. A collection of attributes is called a product profile. Respondents choose one in each set of product profiles.

Industrial experimentation deals with the question of how to improve processes to deliver better products. Choice experiments help a company prioritize product features for their market. The purpose of a choice experiment is to define a product that people want to buy.

Choice experiments always involve people comparing prospective products and picking the one that they prefer. For example, suppose a computer ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781629594422

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

JMP 12 Design of Experiments Guide

by SAS Institute

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.