Fundamentals of Predictive Analytics with JMP, 3rd Edition

About This Book
    About These Authors
    Acknowledgments
    Chapter 1: Introduction
    Historical Perspective
    Two Questions Organizations Need to Ask
        Return on Investment
        Cultural Change
    Business Intelligence and Business Analytics
    Introductory Statistics Courses
        The Problem of Dirty Data
        Added Complexities in Multivariate Analysis
    Practical Statistical Study
        Obtaining and Cleaning the Data
        Understanding the Statistical Study as a Story
        The Plan-Perform-Analyze-Reflect Cycle
        Using Powerful Software
    Framework and Chapter Sequence
    Chapter 2: Statistics Review
    Introduction
    Fundamental Concepts 1 and 2
        FC1: Always Take a Random and Representative Sample
        FC2: Remember That Statistics Is Not an Exact Science
    Fundamental Concept 3: Understand a Z-Score
    Fundamental Concept 4
        FC4: Understand the Central Limit Theorem
        Learn from an Example
    Fundamental Concept 5
        Understand One-Sample Hypothesis Testing
        Consider p-Values
    Fundamental Concept 6:
        Understand That Few Approaches/Techniques Are Correct—Many Are Wrong
        Three Possible Outcomes When You Choose a Technique
    Chapter 3: Dirty Data
    Introduction
    Data Set
    Error Detection
    Outlier Detection
        Approach 1
        Approach 2
        Missing Values
        Statistical Assumptions of Patterns of Missing
        Conventional Correction Methods
        The JMP Approach
        Example Using JMP
    General First Steps on Receipt of a Data Set
    Exercises
    Chapter 4: Data Discovery with Multivariate Data
    Introduction
    Use Tables to Explore Multivariate Data
        PivotTables
        Tabulate in JMP
    Use Graphs to Explore Multivariate Data
        Graph Builder
        Scatterplot
    Explore a Larger Data Set
        Trellis Chart
        Bubble Plot
    Explore a Real-World Data Set
        Use Graph Builder to Examine Results of Analyses
        Generate a Trellis Chart and Examine Results
        Use Dynamic Linking to Explore Comparisons in a Small Data Subset
        Return to Graph Builder to Sort and Visualize a Larger Data Set
    Chapter 5: Regression and ANOVA
    Introduction
    Regression
        Perform a Simple Regression and Examine Results
        Understand and Perform Multiple Regression
        Understand and Perform Regression with Categorical Data
    Analysis of Variance
        Perform a One-Way ANOVA
        Evaluate the Model
        Perform a Two-Way ANOVA
    Exercises
    Chapter 6: Logistic Regression
    Introduction
        Dependence Technique
        The Linear Probability Model
        The Logistic Function
    A Straightforward Example Using JMP
        Create a Dummy Variable
        Use a Contingency Table to Determine the Odds Ratio
        Calculate the Odds Ratio
    A Realistic Logistic Regression Statistical Study
        Understand the Model-Building Approach
        Run Bivariate Analyses
        Run the Initial Regression and Examine the Results
        Convert a Continuous Variable to Discrete Variables
        Produce Interaction Variables
        Validate and Use the Model
    Exercises
    Chapter 7: Principal Components Analysis
    Introduction
    Basic Steps in JMP
        Produce the Correlations and Scatterplot Matrix
        Create the Principal Components
        Run a Regression of y on Prin1 and Excluding Prin2
        Understand Eigenvalue Analysis
        Conduct the Eigenvalue Analysis and the Bartlett Test
        Verify Lack of Correlation
    Dimension Reduction
        Produce the Correlations and Scatterplot Matrix
        Conduct the Principal Component Analysis
        Determine the Number of Principal Components to Select
        Compare Methods for Determining the Number of Components
    Discovery of Structure in the Data
        A Straightforward Example
        An Example with Less Well Defined Data
    Exercises
    Chapter 8: Least Absolute Shrinkage and Selection Operator and Elastic Net
    Introduction
        The Importance of the Bias-Variance Tradeoff
        Ridge Regression
    Least Absolute Shrinkage and Selection Operator
        Perform the Technique
        Examine the Results
        Refine the Results
    Elastic Net
        Perform the Technique
        Examine the Results
        Compare with LASSO
    Exercises
    Chapter 9: Cluster Analysis
    Introduction
        Example Applications
        An Example from the Credit Card Industry
        The Need to Understand Statistics and the Business Problem
    Hierarchical Clustering
        Understand the Dendrogram
        Understand the Methods for Calculating Distance between Clusters
        Perform a Hierarchal Clustering with Complete Linkage
        Examine the Results
        Consider a Scree Plot to Discern the Best Number of Clusters
        Apply the Principles to a Small but Rich Data Set
        Consider Adding Clusters in a Regression Analysis
    K-Means Clustering
        Understand the Benefits and Drawbacks of the Method
        Choose k and Determine the Clusters
        Perform k-Means Clustering
        Change the Number of Clusters
        Create a Profile of the Clusters with Parallel Coordinate Plots
        Perform Iterative Clustering
        Score New Observations
    K-Means Clustering versus Hierarchical Clustering
    Exercises
    Chapter 10: Decision Trees
    Introduction
        Benefits and Drawbacks
        Definitions and an Example
        Theoretical Questions
    Classification Trees
        Begin Tree and Observe Results
        Use JMP to Choose the Split That Maximizes the LogWorth Statistic
        Split the Root Node According to Rank of Variables
        Split Second Node According to the College Variable
        Examine Results and Predict the Variable for a Third Split
        Examine Results and Predict the Variable for a Fourth Split
        Examine Results and Continue Splitting to Gain Actionable Insights
        Prune to Simplify Overgrown Trees
        Examine Receiver Operator Characteristic and Lift Curves
    Regression Trees
        Understand How Regression Trees Work
        Restart a Regression Driven by Practical Questions
        Use Column Contributions and Leaf Reports for Large Data Sets
    Exercises
    Chapter 11: k-Nearest Neighbors
    Introduction
        Example—Age and Income as Correlates of Purchase
        The Way That JMP Resolves Ties
        The Need to Standardize Units of Measurement
    k-Nearest Neighbors Analysis
        Perform the Analysis
        Make Predictions for New Data
    k-Nearest Neighbor for Multiclass Problems
        Understand the Variables
        Perform the Analysis and Examine Results
    The k-Nearest Neighbor Regression Models
        Perform a Linear Regression as a Basis for Comparison
        Apply the k-Nearest Neighbors Technique
        Compare the Two Methods
        Make Predictions for New Data
    Limitations and Drawbacks of the Technique
    Exercises
    Chapter 12: Neural Networks
    Introduction
        Drawbacks and Benefits
        A Simplified Representation
        A More Realistic Representation
    Understand Validation Methods
        Holdback Validation
        k-fold Cross-Validation
    Understand the Hidden Layer Structure
        A Few Guidelines for Determining Number of Nodes
        Practical Strategies for Determining Number of Nodes
        The Method of Boosting
    Understand Options for Improving the Fit of a Model
    Complete the Data Preparation
    Use JMP on an Example Data Set
        Perform a Linear Regression as a Baseline
        Perform the Neural Network Ten Times to Assess Default Performance
        Boost the Default Model
        Compare Transformation of Variables and Methods of Validation
    Exercises
    Chapter 13: Bootstrap Forests and Boosted Trees
    Introduction
    Bootstrap Forests
        Understand Bagged Trees
        Perform a Bootstrap Forest
        Perform a Bootstrap Forest for Regression Trees
    Boosted Trees
        Understand Boosting
        Perform Boosting
        Perform a Boosted Tree for Regression Trees
        Use Validation and Training Samples
    Exercises
    Chapter 14: Model Comparison
    Introduction
    Perform a Model Comparison with Continuous Dependent Variable
        Understand Absolute Measures
        Understand Relative Measures
        Understand Correlation between Variable and Prediction
        Explore the Uses of the Different Measures
    Perform a Model Comparison with Binary Dependent Variable
        Understand the Confusion Matrix and Its Limitations
        Understand True Positive Rate and False Positive Rate
        Interpret Receiving Operator Characteristic Curves
        Compare Two Example Models Predicting Churn
    Perform a Model Comparison Using the Lift Chart
    Train, Validate, and Test
        Perform Stepwise Regression
        Examine the Results of Stepwise Regression
        Compute the MSE, MAE, and Correlation
        Examine the Results for MSE, MAE, and Correlation
        Understand Overfitting from a Coin-Flip Example
        Use the Model Comparison Platform
    Exercises
    Chapter 15: Text Mining
    Introduction
        Historical Perspective
        Unstructured Data
    Developing the Document Term Matrix
        Understand the Tokenizing Stage
        Understand the Phrasing Stage
        Understand the Terming Stage
        Observe the Order of Operations
    Developing the Document Term Matrix with a Larger Data Set
        Generate a Word Cloud and Examine the Text
        Examine and Group Terms
        Add Frequent Phrases to List of Terms
        Parse the List of Terms
    Using Multivariate Techniques
        Perform Latent Semantic Analysis
        Perform Topic Analysis
        Perform Cluster Analysis
    Using Predictive Techniques
        Perform Primary Analysis
        Perform Logistic Regressions
    Exercises
    Chapter 16: Market Basket Analysis
    Introduction
        Association Analyses
        Examples
    Understand Support, Confidence, and Lift
        Association Rules
        Support
        Confidence
        Lift
    Use JMP to Calculate Confidence and Lift
        Use the A Priori Algorithm for More Complex Data Sets
        Form Rules and Calculate Confidence and Lift
    Analyze a Real Data Set
        Perform Association Analysis with Default Settings
        Reduce the Number of Rules and Sort Them
        Examine Results
        Target Results to Take Business Actions
    Exercises
    Chapter 17: Statistical Storytelling
    The Path from Multivariate Data to the Modeling Process
        Early Applications of Data Mining
        Numerous JMP Customer Stories of Modern Applications
    Definitions of Data Mining
        Data Mining
        Predictive Analytics
    A Framework for Predictive Analytics Techniques
    The Goal, Tasks, and Phases of Predictive Analytics
        The Difference between Statistics and Data Mining
        SEMMA
    References
    Index