Foundations of Data Analysis for Product and Process Improvement
Cy Wegman, Course Author
Senior Analyst and Statistical Consultant at Predictum Inc.
3 days
On-premises or virtual
Available on request
About This Course
It’s essential that you not only master core data analysis skills, but that you quickly apply them to your work.
That’s why Foundations of Data Analysis for Product and Process Improvement provides you with the hands-on skills you need to get ahead.
During the course, you will master basic to advanced analytical methods, you will solve problems that arise in real-world scenarios, and most importantly, you will improve the effectiveness of your work.
- Identify and apply key data analyses, graphics and modeling techniques to more accurately describe your products and processes.
- Leverage those descriptions to improve the performance of those products and processes more effectively and efficiently.
Training Outcomes:
- Apply a general priority framework for improvement.
- Perform data preparation for analyses.
- Identify and explain key statistical concepts and metrics.
- Determine if observed measures are statistically different.
- Assess if a process is in statistical control.
- Prioritize improvement efforts:
- Which results? Shift mean or reduce variation?
- Define special and common causes.
- Estimate the capability of a process.
- Derive specifications for product performance measures.
- Perform simple linear and multilinear regression.
- Explore sources of variation using variation analysis.
- Evaluate the suitability of data for modeling.
- Use linear regression to build predictive continuous response models from continuous and categorical factors.
- Evaluate the statistical significance and confidence intervals of the model prediction.
- Recite strengths and weaknesses of various analysis techniques.
- Optimize a process.
Session 1
Introduction & Course Objectives
Introduction Problem
Navigating JMP
Key Features & Characteristics
Importing Data
Table Arrangements
Saving Scripts
Formula Editor
Session 2
Improvement Process
System Thinking
Analysis versus Synthesis
Foundational Statistics
Descriptive Statistics
Testing Assumptions
Comparing Differences – Hypothesis Tests
One Sample Means Test
Sample Size and Power
Equivalence Tests
Session 3
Multiple Comparisons
One Way ANOVA
Multiple Comparisons
Process Stability
Moving Range & X Charts
XBar and Range Charts
Common versus Special Causes
Session 4
Process Capability
Estimating Sources of Variation
Capability Indices
Variation Reduction
Estimating Specification Limits
Goal Plots
Quality Prioritization
Session 5
Cleaning Data
Basic Cleaning & Graphing
Robust PCA Outlier Platform
Missing Value Code
Multivariate k-Nearest Neighbor
Explore Missing Values
Data Imputation
Session 6
Model Building
N-Way ANOVA
Simple Linear Regression
Multi-Linear Regression
Continuous & Nominal Factor Regression
Extra Addendum Material
Multiple Comparisons
Converting Nonnormal distributions to Normal
Nonparametric Comparison Tests
Process Stability
Attribute Control Charts
p-charts, fraction defective
u-charts, average defects per item
Instructors
Before joining Predictum, he worked for 38 years at Procter & Gamble, where his last assignment was the Empirical Modeling leader for the company. Cy is a member of the P&G Prism Society, which represents the top 1% of P&G engineers, for profitably applying his technical mastery. His contributions have resulted in hundreds of millions of dollars in annual savings. His cross-industry work in manufacturing, engineering, and R&D has spanned molecular-scale to full-scale technologies, as well as material, formulation, process, packaging, and consumer models.
Cy holds a B.S. in Civil Engineering from Rose-Hulman Institute of Technology.
Who Should Attend
Engineers, scientists and technicians responsible for product and process development
Duration
3 days
Delivery Methods
On premises or virtual
Prerequisites
Familiarity with computers and spreadsheet software, such as Microsoft Excel.
JMP is required if you want to actively participate in the course. If you do not have JMP you can get a free trial version to install on your work or personal computer.
Pricing
Individual and group pricing available on request
