JMP 13 Multivariate Methods, Second Edition, 2nd Edition

Book description

JMP 13 Multivariate Methods describes techniques for analyzing several variables simultaneously. The book covers descriptive measures, such as correlations. It also describes methods that give insight into the structure of the multivariate data, such as clustering, latent class analysis, principal components, discriminant analysis, and partial least squares.

Table of contents

  1. Contents
  2. Learn about JMP
    1. Documentation and Additional Resources
    2. Formatting Conventions
    3. JMP Documentation
      1. JMP Documentation Library
      2. JMP Help
    4. Additional Resources for Learning JMP
      1. Tutorials
      2. Sample Data Tables
      3. Learn about Statistical and JSL Terms
      4. Learn JMP Tips and Tricks
      5. Tooltips
      6. JMP User Community
      7. JMPer Cable
      8. JMP Books by Users
      9. The JMP Starter Window
    5. Technical Support
  3. Introduction to Multivariate Analysis
    1. Overview of Multivariate Techniques
  4. Correlations and Multivariate Techniques
    1. Explore the Multidimensional Behavior of Variables
    2. Launch the Multivariate Platform
    3. The Multivariate Report
    4. Multivariate Platform Options
      1. Nonparametric Correlations
      2. Scatterplot Matrix
      3. Outlier Analysis
        1. Mahalanobis Distance
        2. Jackknife Distances
        3. T2 Statistic
        4. Saving Distances and Values
      4. Item Reliability
      5. Impute Missing Data
    5. Example of Item Reliability
    6. Computations and Statistical Details
      1. Estimation Methods
        1. REML
        2. Robust
      2. Pearson Product-Moment Correlation
      3. Nonparametric Measures of Association
        1. Spearman’s ρ (rho) Coefficients
        2. Kendall’s τb Coefficients
        3. Hoeffding’s D Statistic
      4. Inverse Correlation Matrix
      5. Distance Measures
        1. Mahalanobis Distance Measures
        2. Jackknife Distance Measures
        3. T2 Distance Measures
      6. Cronbach’s Alpha
  5. Principal Components
    1. Reduce the Dimensionality of Your Data
    2. Overview of Principal Component Analysis
    3. Example of Principal Component Analysis
    4. Launch the Principal Components Platform
      1. Missing Data
    5. Principal Components Report
    6. Principal Components Report Options
    7. Statistical Details
      1. Estimation Methods
        1. REML
        2. Wide
        3. Sparse
      2. DModX Calculation
  6. Discriminant Analysis
    1. Predict Classifications Based on Continuous Variables
    2. Discriminant Analysis Overview
    3. Example of Discriminant Analysis
    4. Discriminant Launch Window
      1. Stepwise Variable Selection
        1. Updating the F Ratio and Prob>F
        2. Statistics
        3. Buttons
        4. Columns
        5. Stepwise Example
      2. Discriminant Methods
        1. Regularized, Compromise Method
      3. Shrink Covariances
    5. The Discriminant Analysis Report
      1. Principal Components
      2. Canonical Plot and Canonical Structure
        1. Canonical Structure
        2. Canonical Plot
        3. Modifying the Canonical Plot
        4. Classification into Three or More Categories
        5. Classification into Two Categories
      3. Discriminant Scores
      4. Score Summaries
        1. Entropy RSquare
    6. Discriminant Analysis Options
      1. Score Options
      2. Canonical Options
        1. Show Canonical Details
        2. Show Canonical Structure
      3. Example of a Canonical 3D Plot
      4. Specify Priors
      5. Consider New Levels
      6. Save Discrim Matrices
      7. Scatterplot Matrix
    7. Validation in JMP and JMP Pro
    8. Technical Details
      1. Description of the Wide Linear Algorithm
      2. Saved Formulas
        1. Linear Discriminant Method
        2. Quadratic Discriminant Method
        3. Regularized Discriminant Method
        4. Wide Linear Discriminant Method
      3. Multivariate Tests
      4. Approximate F-Tests
      5. Between Groups Covariance Matrix
  7. Partial Least Squares Models
    1. Develop Models Using Correlations between Ys and Xs
    2. Overview of the Partial Least Squares Platform
    3. Example of Partial Least Squares
    4. Launch the Partial Least Squares Platform
      1. Centering and Scaling
      2. Standardize X
    5. Model Launch Control Panel
    6. Partial Least Squares Report
      1. Model Comparison Summary
      2. <Cross Validation Method> and Method = <Method Specification>
        1. Root Mean PRESS Plot
        2. Root Mean PRESS
        3. Calculation of Q2
        4. Calculation of R2X and R2Y When Validation Is Used
      3. Model Fit Report
    7. Partial Least Squares Options
    8. Model Fit Options
      1. Variable Importance Plot
      2. VIP vs Coefficients Plots
      3. Save Columns
    9. Statistical Details
      1. Partial Least Squares
        1. NIPALS
        2. SIMPLS
      2. van der Voet T2
      3. T2 Plot
      4. Confidence Ellipses for X Score Scatterplot Matrix
      5. Standard Error of Prediction and Confidence Limits
        1. Standard Error of Prediction Formula
        2. Mean Confidence Limit Formula
        3. Indiv Confidence Limit Formula
      6. Standardized Scores and Loadings
        1. Standardized Scores
        2. Standardized Loadings
      7. PLS Discriminant Analysis (PLS-DA)
  8. Hierarchical Cluster
    1. Group Observations Using a Tree of Clusters
    2. Hierarchical Cluster Overview
      1. Overview of Platforms for Clustering Observations
    3. Example of Clustering
    4. Launch the Hierarchical Cluster Platform
      1. Clustering Method
      2. Method for Distance Calculation
      3. Data Structure
        1. Not Enough Nonmissing Data Alert
      4. Transformations to Y, Columns Variables
    5. Hierarchical Cluster Report
      1. Dendrogram Report
        1. Distance Graph
      2. Illustration of Dendrogram and Distance Graph
      3. Clustering History Report
      4. Hierarchical Cluster Options
    6. Additional Examples of the Hierarchical Clustering Platform
      1. Example of a Distance Matrix
      2. Example of Wafer Defect Classification Using Spatial Measures
    7. Statistical Details
      1. Spatial Measures
        1. Choose Spatial Components Window
        2. Spatial Measures Reports
      2. Distance Method Formulas
  9. K Means Cluster
    1. Group Observations Using Distances
    2. K Means Cluster Platform Overview
      1. Overview of Platforms for Clustering Observations
    3. Example of K Means Cluster
    4. Launch the K Means Cluster Platform
    5. Iterative Clustering Report
      1. Iterative Clustering Options
    6. Iterative Clustering Control Panel
    7. K Means NCluster=<k> Report
      1. Cluster Comparison Report
      2. K Means NCluster=<k> Report
      3. K Means NCluster=<k> Report Options
    8. Self Organizing Map
      1. Self Organizing Map Control Panel
      2. Self Organizing Map Report
      3. Description of SOM Algorithm
  10. Normal Mixtures
    1. Group Observations Using Probabilities
    2. Normal Mixtures Clustering Platform Overview
      1. Overview of Platforms for Clustering Observations
    3. Example of Normal Mixtures Clustering
    4. Launch the Normal Mixtures Clustering Platform
      1. Options
    5. Iterative Clustering Report
      1. Iterative Clustering Options
    6. Iterative Clustering Control Panel
    7. Normal Mixtures NCluster=<k> Report
      1. Cluster Comparison Report
      2. Normal Mixtures NCluster=<k> Report
      3. Normal Mixtures NCluster=<k> Report Options
    8. Robust Normal Mixtures
      1. Robust Normal Mixtures Control Panel
      2. Robust Normal Mixture Reports
    9. Statistical Details for the Normal Mixtures Method
      1. Additional Details for Robust Normal Mixtures
  11. Latent Class Analysis
    1. Group Observations of Categorical Variables
    2. Latent Class Analysis Platform Overview
    3. Example of Latent Class Analysis
    4. Launch the Latent Class Analysis Platform
    5. The Latent Class Analysis Report
      1. Latent Class Model for <k> Clusters Report
    6. Latent Class Analysis Platform Options
      1. Latent Class Analysis Options
      2. Latent Class Model Options
    7. Additional Example of the Latent Class Analysis Platform
      1. Plot Probabilities of Cluster Membership
    8. Statistical Details for the Latent Class Analysis Platform
  12. Cluster Variables
    1. Group Similar Variables into Representative Groups
    2. Cluster Variables Platform Overview
    3. Example of the Cluster Variables Platform
    4. Launch the Cluster Variables Platform
    5. The Cluster Variables Report
      1. Color Map on Correlations
      2. Cluster Summary
      3. Cluster Members
      4. Standardized Components
    6. Cluster Variables Platform Options
    7. Additional Examples of the Cluster Variables Platform
      1. Example of Color Map on Correlations
      2. Example of Cluster Variables Platform for Dimension Reduction
        1. Cluster Variables
        2. Fit Models
    8. Statistical Details for the Cluster Variables Platform
      1. Variable Clustering Algorithm
  13. Statistical Details
    1. Multivariate Methods
    2. Wide Linear Methods and the Singular Value Decomposition
      1. The Singular Value Decomposition
      2. The SVD and the Covariance Matrix
      3. The SVD and the Inverse Covariance Matrix
      4. Calculating the SVD
  14. References
  15. Index
    1. Multivariate Methods

Product information

  • Title: JMP 13 Multivariate Methods, Second Edition, 2nd Edition
  • Author(s): SAS Institute
  • Release date: February 2017
  • Publisher(s): SAS Institute
  • ISBN: 9781629609577