Minitab – Basic Statistics (Manufacturing)

Minitab - Normal Probability PlotThis hands-on workshop is normally taught in 1 day (or 1.5 days with additional or custom content). Prerequisite: Introduction to Minitab and Basic Graphical Analysis, or working knowledge of Minitab.

Augment your graphical analysis skills using MINITAB’s powerful statistical tools. Develop the foundation for important statistical concepts such as hypothesis testing and confidence intervals. By analyzing a variety of real world data sets, learn how to match the appropriate statistical tool to your own applications and how to correctly interpret statistical output to quickly reveal problems with a process or to show evidence of an improvement. Learn how to explore critical features in your processes through statistical modeling tools that help to uncover and describe relationships between variables. A strong emphasis is placed on making good business decisions based upon the practical application of statistical techniques commonly found in manufacturing, engineering, and research and development endeavors.

Tools Covered Include: t-Tests, Proportion Tests, Tests for Equal Variance, Power and Sample Size, Correlation, Simple Linear and Multiple Regression, ANOVA and GLM.

Optional topics are special additions to standard Minitab training workshops, and extend the course by about 1/2 day. All Minitab training workshops use the latest, current version of Minitab, and authorized Minitab training materials.

One and Two Sample t tests

  • Minitab BoxplotMinitab Boxplot to compare 2 groups
  • testing for Normal distribution
  • Testing a null hypothesis using t-tests and confidence intervals
  • assesing power of a hypothesis test using power analysis
  • testing the difference betwen a process mean and a target value using a one-sample t test
  • testing the difference between two sample means using a two-sample t-test
  • testing the differences between paired observations using a paired t-test
  • boxplots, individual value plots

Optional: videos on Confidence Intervals, paired t-tests (from Against All Odds: Inside Statistics series); review of Truth Tables, development of Null Hypothesis; online demonstration of Confidence Intervals ; discussion of sample size n = f (alpha, beta, sigma, delta)

Proportion Tests

  • power and sample size for a one-proportion test;
  • Using one-proportion test to determine whether a defect rate is different from a target value;
  • Assumptions in a two-proportion test
  • Fisher’s exact test to determine whether two defect rates are different from one another

Optional: discussion of sample size n = f (alpha, beta, p’)

Correlation and Regression

  • Linear regression modelMinitab Linear Regression Model
  • Measuring the degree of linear association between two variables using graphs, statistics, and correlation
  • Modelling the relationship between a continuous reponse variable and one or more predictor variables;
  • Determining the strength of the relationship between a continuous response variable and one or more predictor variables.
  • polynomial regression; quadratic vs linear models
  • Adding Confidence and Prediction intervals.

Optional: testing assumptions of regression by analyzing residuals

Analysis of Variance

  • Test for Equal VariancesMinitab Test for Equal Variance Graph
  • Assesing the power of an analysis of variance using power analysis
  • Comparing group variances using a variance test
  • Comparing means for samples collected at different levels using a general linear model
  • ANOVA with more than one factor
  • Interpration of interaction plots and multiple comparisons.
  • ANOVA: General Linear Model; full and reduced models; main effects and interactions; pairwise comparisons

Optional: discussion on ANOVA using General Linear Model (GLM); clarification of terms: crossed vs nested factors; fixed vs random factors; mixed models; balanced vs unbalanced designs.

Multiple Regression (optional)

  • Matrix Plot with SmootherMinitab Matrix Plot
  • Regression analysis with more than one predictor; matrix plots; multiple correlations; fitting a multiple regression model
  • Best subsets regression
  • Handling multicollinearity in a regression analysis.

Practice Exercises

Each participant receives an official Minitab workbook and data files, as well as a certificate for Recertification Units for completion of this workshop.

See other Minitab Training Courses and comments from previous participants in Carol Kavanaugh’s workshops!