Statistical Methods for Product and Process
Course "Statistical Methods for Product and Process Development" has been
pre-approved by RAPS as eligible for up to 12 credits towards a participant's
RAC recertification upon full completion.
This course is designed to help scientists and engineers apply statistical
methods used assist decision making in process and product development.
Variability must be considered when utilizing data to arrive at conclusions.
This course will cover Basic Statistics and Graphical Methods used to summarize
data. You will learn how to apply Hypothesis Testing methods to determine
whether groups are statistically equivalent or not with respect to key process
characteristics such as process averages and variability.
The use of confidence intervals when estimating key parameters will be covered.
When planning studies, sample size determination is critical to ensure that
study results will be meaningful. Methods to determine appropriate sample sizes
for various types of problems will be covered.
Finally, an introduction to Design of Experiments (DOE) is provided. DOE is an
extremely efficient method to understand which variables (and interactions)
affect key outcomes and allows the development of mathematical models used to
optimize process and product performance. The concepts behind DOE are covered
along with some effective types of screening experiments. Case studies will also
be presented to illustrate the use of the methods.
This highly interactive course will allow participants the opportunity to
practice applying statistical methods with various data sets. The objective is
to provide participants with the key tools and knowledge to be able to apply the
methods effectively in their process and product development efforts.
Why should you attend?
• Effectively summarize data and communicate results with basic statistics and
• Apply Hypothesis Testing to test whether two or more groups of data are
statistically equivalent or not.
• Estimate key process parameters with associated confidence intervals to
express estimate uncertainty
• Determine appropriate sample sizes for estimation and hypothesis testing
• Understand key Design of Experiments concepts and methods
• Apply experiments to determine cause and effect relationships and model
Day 1 Schedule:
Lecture 1: Basic Statistics & Distributions
• Data Types
• Populations & Samples
• Central Tendency and Variation
• Probability Distributions
• The Normal Distribution
Lecture 2: Graphical Analysis
• Boxplots and Individual Value Plots
• Scatter Plots
Lecture 3: Hypothesis Testing Concepts
• Test Statistics, Crit. Values, p-values
• One and Two Sided Tests
• Type I and Type II Errors
• Estimation and Confidence Intervals
Lecture 4: Hypothesis Tests for One and Two Groups
• Testing Means (1 sample t ,2 sample t and paired t tests)
• Testing Variances (Chi-Square, F test)
Lecture 5: Hypothesis Tests for one and Two Groups (cont'd)
• Testing Proportions (overview)
• Equivalence Tests
Lecture 6: Hypothesis Tests for Multiple (>2) Groups
• Testing Means (ANOVA)
• Multiple Comparisons
• Testing Variances (Bartletts and Levenes Test)
Day 2 Schedule:
Lecture 1: Power & Sample Size
• Type II Errors and Power
• Factors affecting Power
• Computing Sample Sizes
• Power Curves
Lecture 2: Introduction to Experimental Design
• What is DOE?
• Sequential Experimentation
• When to use DOE
• Common Pitfalls in DOE
• DOE Guide to Experimentation
Lecture 3: Two Level Factorial Designs
• Design Matrix and Calculation Matrix
• Calculation of Main & Interaction Effects
• Interpreting Effects
• Fractional Factorials (Introduction)
Lecture 4: Identifying Significant Effects
• Determining which effects are statistically significant
• Analyzing Replicated and Non-replicated Designs
Lecture 5: Developing Mathematical Models
• Developing First Order Models
• Residuals/Model Validation
• Optimizing Responses
Principal Statistician, Integral Concepts, Inc
Steven Wachs has 25 years of wide-ranging industry experience in both technical
and management positions. Steve has worked as a statistician at Ford Motor
Company where he has extensive experience in the development of statistical
models, reliability analysis, designed experimentation, and statistical process
Steve is currently a Principal Statistician at Integral Concepts, Inc. where he
assists manufacturers in the application of statistical methods to reduce
variation and improve quality and productivity. He also possesses expertise in
the application of reliability methods to achieve robust and reliable products
as well as estimate and reduce warranty.
M.A., Applied Statistics, University of Michigan, 2002
M.B.A, Katz Graduate School of Business, University of Pittsburgh, 1992
B.S., Mechanical Engineering, University of Michigan, 1986