This course is an introduction to Minitab, the statistical software utilized by Six Sigma practitioners, quality leaders and statisticians to help them analyze data.

The ability to understand and use statistical data is crucial to the success of any Lean Six Sigma project. This module introduces basic statistical concepts including populations and sampling, measures of central tendency, and measures of variation.

Proper data collection is critical to the correct analysis and reporting of key business metrics. The fundamental topics covered in this course include discrete vs. continuous data types, scales of measurement, specific data collection principles, converting attribute data to variable data, sample size considerations, sampling strategies and data gathering strategies.

This module explains how to assess the capability of a measurement system and why this task is critical to measurement success. Participants learn about Attribute R&R and Gage R&R. This course is ideal for introducing measurement system concepts to all levels of your organization or as a refresher course for Lean Six Sigma and Six Sigma practitioners.

A probability distribution is a statistical concept that enables us to estimate the chance of a particular value occurring over a range of values. This module introduces this topic, using Minitab software to help visualize the normal distribution and some common patterns associated with non-normal data such as natural limits, artificial limits, multiple modes and mixtures. For practitioners, a working knowledge of probability distributions helps guide your day-to-day process improvement. (This is the first in a set of three lectures on Common Probability Distributions).

A probability distribution is a statistical concept that enables us to estimate the chance of a particular value occurring over a range of values. This module uses Minitab software to help visualize two frequently utilized discrete distributions – binomial and Poisson – and provides process examples of each distribution. For practitioners, a working knowledge of probability distributions helps guide your day-to-day process improvement. (This is the third in a set of three lectures on Common Probability Distributions).

Graphing data is the best way to communicate results. This course explains how to understand data and convert it into useful, visual information. Individuals responsible for collecting, presenting, and/or analyzing data will find this module of great value.

This course reviews the ways of quantifying the statistical uncertainty of sampling. It describes how to use sample statistics to calculate and interpret confidence intervals for the population mean, the population standard deviation and the population proportion. Confidence Intervals is recommended to anyone who is involved in data analysis activities.

Using Hypothesis Testing, practitioners learn how to prove and disprove theories, leading to more sound and statistically-based decisions.

This module introduces the concept of statistical hypothesis testing, defines the null and alternate hypotheses, provides a general method for constructing a hypothesis test, and demonstrates how to use MINITAB for hypothesis testing.

This module presents the concept of sample size for estimation for discrete and variable data. The course demonstrates how to calculate sample sizes for estimation purposed both manually and via Minitab.

This module introduces the concept of sample size for hypothesis testing. The course reviews the types of hypothesis testing errors, and alpha and beta risk. It also defines sample size terminology, including Power, Critical Difference, Delta, and Specific Hypothesis.

Hypothesis testing is an important process improvement tool. This course demonstrates how to calculate the appropriate sample size for 1-Sample t-Tests, 1 Proportion Tests, and 1 Variance Tests. The concepts presented in this module can be applied to other statistical tests including 2-sample T-tests, 2-proportion tests, 2-variance tests, and One way ANOVA tests.

Concepts covered in this course include ANOVA, or Analysis of Variance, sum of squares and mean square error. A detailed process for executing a successful ANOVA is demonstrated and calculations are practiced using Minitab. This course is intended for Six Sigma practitioners, team members, and process owners.

Chi-Square Analysis is a key tool to help us analyze discrete or attribute data from our processes. This module will walk you through how to use Chi-Square Analysis in your improvement project for assessing the independence of two discrete sets of data. It will also demonstrate how to conduct a Chi-Square Goodness-of-Fit Analysis for determining if your discrete data deviates from a specified distribution. A manual method for completing the analysis will be explained, before step by step instructions are provided for the analysis in Minitab.

This module introduces simple Linear Regression and how it can be used to study the relationship between a continuous Y and continuous X variable. It discusses how the regression line can be used to predict the value of Y for a given value of X.

Multiple Linear Regression is an advanced tool that can be used to build a robust prediction model. In this first of two modules on the topic, the focus is on using a single continuous predictor to build a multi term, or higher order model, such as a quadratic and cubic model. Minitab is used to conduct the analysis as well as providing support for verifying the validity of the model through Residual Analysis.

This course on multiple linear regression discusses how to use continuous and discrete predictors to build a robust regression model. It presents a general method for conducting the multiple regression analysis beginning with the practical problem and ending with the practical solution. It also discusses multicollinearity and residual analysis, two key elements for assessing the validity of the regression model. Minitab is used to generate the models through a manual iteration method and best subsets.

This module introduces the basic concepts behind Design of Experiments (DOE). It covers strategies for determining the critical inputs to drive the important outputs, the DOE method, and possible barriers to applying DOE in the real world.

This course covers Full Factorials and introduces 2K Factorials. General factorial experiment design and analysis are demonstrated, and several concepts are introduced including main effects and interactions, as well as key DOE terms. In addition, this course shows how to derive Y as a function of X. This module is intended for Six Sigma practitioners, team members, and process owners.

This course introduces the concept of fractional factorial designs and defines the terminology associated with these designs. The concepts of aliasing, design resolution and sparsity of effects are discussed.

In this module, the practical analysis of fractional factorial experiments is presented. In addition, the course demonstrates the Response Optimizer and how to determine sample size for DOE.

Binary Logistic Regression is a powerful technique that is used with binomial response data in order to identify which Xs are driving it. In this module we provide details on the terminology used in this type of analysis such as event, odds and odds ratio. We then walk through an example using a single continuous predictor and then move onto a second case where we examine the outcomes for a single categorical predictor. In each situation graphical representations of the analysis in Minitab are shown to help with practical interpretation of the analysis.

Binary Logistic Regression is a powerful technique that is used with binomial response data in order to identify which Xs are driving it. In this module we provide a general method for conducting Binary Logistic Regression with multiple predictors. Focus is also given to the impact of multicollinearity and how the presence of this can be identified through Minitab. We then walk through an example using continuous and categorical predictors, including how to verify assumptions using goodness of Fits tests.