Statistical Thinking

for Industrial Problem Solving

Course outline
Statistical Thinking for Industrial Problem Solving is a free, online course available to anyone interested in building practical skills
in using data to solve problems better. The course is comprised of seven modules, totaling about 30 hours of self-paced learning.
Each module includes short instructional videos, JMP demonstrations, questions and exercises. Learn more and enroll
at jmp.com/statisticalthinking.

The topics covered in each module are outlined below.

Module 1: Statistical Thinking and Problem Solving

Learn how to map a process, define and scope your project,
and determine the data you need to solve your problem.

Statistical Thinking Identifying Potential Root Causes

• What Is Statistical Thinking • Tools for Identifying Potential Causes
• Brainstorming
Problem Solving • Multi-Voting
• Using Affinity Diagrams
• Overview of Problem Solving
• Cause-and-Effect Diagrams
• Statistical Problem Solving
• The 5 Whys
• Types of Problems
• Cause-and-Effect Matrices
Defining the Problem
Compiling and Collecting Data
• Defining the Problem
• Data Collection for Problem Solving
• Goals and Key Process Indicators
• Types of Data
• The White Polymer Case Study
• Operational Definitions
• Data Collection Strategies
Defining the Process • Importing Data for Analysis
• What Is a Process?
• Developing a SIPOC Map
• Developing an Input/Output Process Map
• Top-Down and Deployment Flowcharts

Module 2: Exploratory Data Analysis

Learn how to describe data with graphics and use interactive visualizations
to find and communicate the story in your data.

Describing Data • Understanding the Normal Distribution

• Introduction to Descriptive Statistics • Checking for Normality
• Types of Data • The Central Limit Theorem
• Histograms
• Measures of Central Tendency and Location Exploratory Data Analysis for Problem Solving
• Measures of Spread — Range and Interquartile Range • Introduction to Exploratory Data Analysis
• Measures of Spread — Variance and Standard • Exploring Continuous Data: Enhanced Tools
Deviation • Pareto Plots
• Visualizing Continuous Data • Packed Bar Charts and Data Filtering
• Describing Categorical Data • Tree Maps and Mosaic Plots
• Using Trellis Plots and Overlay Variables
Probability Concepts • Bubble Plots and Heat Maps
• Introduction to Probability Concepts • Summary of Exploratory Data Analysis Tools
• Samples and Populations
Module 2: Exploratory Data Analysis (continued)

Communicating With Data Data Preparation for Analysis

• Introduction to Communicating With Data • Data Tables Essentials
• Creating Effective Visualizations • Common Data Quality Issues
• Evaluating the Effectiveness of a Visualization • Identifying Issues in the Data Table
• Designing an Effective Visualization • Identifying Issues One Variable at a Time
• Communicating Visually With Animation • Restructuring Data for Analysis
• Designing for Your Audience • Combining Data
• Understanding Your Target Audience • Deriving New Variables
• Designing Visualizations for Communication • Working With Dates
• Designing Visualizations: The Do’s and Don’ts

Saving and Sharing Results

• Introduction to Saving and Sharing Results
• Saving and Sharing Results in JMP
• Saving and Sharing Results Outside of JMP
• Deciding Which Format to Use

Module 3: Quality Methods

Learn about tools to quantify, control and reduce variation in your product,
service or process.

Statistical Process Control • Estimating Process Capability: An Example

• Introduction to Control Charts • Calculating Capability for Nonnormal Data
• Individual and Moving Range Charts • Estimating Process Capability for Many Variables
• Common Cause Versus Special Cause Variation • Identifying Poorly Performing Processes
• Testing for Special Causes • A View From Industry
• X-bar and R, and X-bar and S Charts
• Rational Subgrouping Measurement System Studies
• 3-Way Control Charts • What Is a Measurement Systems Analysis (MSA)?
• Control Charts With Phases • Language and Terminology
• Designing a Measurement System Study
Process Capability • Designing and Conducting an MSA
• The Voice of the Customer • Analyzing an MSA
• Process Capability Indices • Studying Measurement System Accuracy
• Short- and Long-Term Estimates of Capability • Improving the Measurement Process
• Understanding Capability for Process Improvement

Module 4: Decision Making With Data

Learn to draw inferences from data, construct statistical intervals, perform hypothesis
tests, and understand the relationship between sample size and power.

Estimation Foundations in Statistical Testing

• Introduction to Statistical Inference • Introduction to Statistical Testing
• What Is a Confidence Interval? • Statistical Decision Making
• Estimating a Mean • Understanding the Null and Alternative Hypotheses
• Visualizing Sampling Variation • Sampling Distribution Under the Null
• Constructing Confidence Intervals • The p-Value and Statistical Significance
• Understanding the Confidence Level and Alpha Risk
• Prediction Intervals
• Tolerance Intervals
• Comparing Interval Estimates
Module 4: Decision Making with Data (continued)

Hypothesis Testing for Continuous Data Sample Size and Power

• Conducting a One-Sample t Test • Introduction to Sample Size and Power
• Understanding p-Values and t Ratios • Sample Size for a Confidence Interval for the Mean
• Equivalence Testing • Outcomes of Statistical Tests
• Comparing Two Means • Statistical Power
• Unequal Variances Tests • Exploring Sample Size and Power
• Paired Observations • Calculating the Sample Size for One-Sample t Tests
• One-Way ANOVA (Analysis of Variance) • Calculating the Sample Size for Two-Sample t Tests
• Multiple Comparisons and ANOVA
• Statistical Versus Practical Significance

Module 5: Correlation and Regression

Learn how to study the linear association between pairs of variables,
and how to fit and interpret linear and logistic regression models.

Correlation • Interpreting Results in Explanatory Modeling

• What Is Correlation? • Residual Analysis and Outliers
• Interpreting Correlation • Multiple Linear Regression With Categorical Predictors
• Multiple Linear Regression With Interactions
• Variable Selection
Simple Linear Regression
• Multicollinearity
• Introduction to Regression Analysis
• The Simple Linear Regression Model
Introduction to Logistic Regression
• The Method of Least Squares
• Visualizing the Method of Least Squares • What Is Logistic Regression?
• Regression Model Assumptions • The Simple Logistic Model
• Interpreting Regression Results • Simple Logistic Regression Example
• Fitting a Model With Curvature • Interpreting Logistic Regression Results
• Multiple Logistic Regression
• Logistic Regression With Interactions
Multiple Linear Regression
• Common Issues
• What Is Multiple Linear Regression?
• Fitting the Multiple Linear Regression Model

Module 6: Design of Experiments

Learn the language of design of experiments (DOE) and see
how to design, conduct and analyze an experiment in JMP.

Introduction to DOE Response Surface Experiments

• What Is DOE? • Introduction to Response Surface Designs
• Conducting Ad Hoc and One-Factor-at-a-Time (OFAT) • Analyzing Response Surface Experiments
Experiments • Creating Custom Response Surface Designs
• Why Use DOE? • Sequential Experimentation
• Terminology of DOE
• Types of Experimental Designs DOE Guidelines
• Introduction to DOE Guidelines
Factorial Experiments • Defining the Problem and the Objectives
• Designing Factorial Experiments • Identifying the Responses
• Analyzing a Replicated Full Factorial • Identifying the Factors and Factor Levels
• Analyzing an Unreplicated Full Factorial • Identifying Restrictions and Constraints
• Preparing to Conduct the Experiment
Screening Experiments • Case Study
• Screening for Important Effects
• A Look at Fractional Factorial Designs
• Custom Screening Designs (Module 7 on back)
 Module 7: Predictive Modeling and Text Mining
Learn how to identify possible relationships, build predictive models
and derive value from free-form text.

Essentials of Predictive Modeling Generalized Regression

• Introduction to Predictive Modeling • Introduction to Generalized Regression
• Overfitting and Model Validation • Fitting Models Using Maximum Likelihood
• Assessing Model Performance: Prediction Models • Introduction to Penalized Regression
• Assessing Model Performance: Classification Models
• Receiver-Operating Characteristic (ROC) Curves Model Comparison and Selection
• Comparing Predictive Models
Decision Trees
• Introduction to Decision Trees Introduction to Text Mining
• Classification Trees
• Introduction to Text Mining
• Regression Trees
• Processing Text Data
• Decision Trees With Validation
• Curating the Term List
• Random (Bootstrap) Forests
• Visualizing and Exploring Text Data
• Analyzing (Mining) Text Data
Neural Networks
• What Is a Neural Network?
• Interpreting Neural Networks
• Predictive Modeling With Neural Networks

jmp.com/statisticalthinking

Copyright © 2019 SAS Institute Inc. Cary, NC, USA. All rights reserved. 110935_G115959US.1019