Minitab Training

Lesson 1 • Fundamental Statistical Concepts

Introduces population vs. sample, variables, and measurement scales. These concepts frame every analytical decision made throughout the course.

Lesson 2 • Data Entry and File Management

Teaches manual entry, copy-paste, and import of external data files. Proper file management prevents data loss and ensures reproducibility across projects.

Lesson 3 • Basic Data Visualization

Creates histograms, dotplots, and boxplots to reveal data distribution and outliers. Visual tools complement numerical summaries for complete data understanding.

Lesson 4 • Minitab Interface and Workspace

Covers the Session window, worksheet, toolbars, and menu structure. Establishes navigation habits that support all subsequent data entry and analysis tasks.

Lesson 1 • Coding and Recoding Variables

Recodes numeric and text values to create categorical groupings or correct data errors. Accurate coding ensures group comparisons are meaningful and unbiased.

Lesson 2 • Sorting, Ranking, and Subsetting Data

Applies sort, rank, and subset commands to isolate relevant data segments. These operations prepare targeted datasets for focused statistical analysis.

Lesson 3 • Stacking, Unstacking, and Merging Data

Restructures data between wide and long formats and merges separate worksheets. Proper data structure is required for most Minitab statistical procedures.

Lesson 4 • Data Validation and Auditing

Identifies outliers, duplicates, and inconsistencies before analysis begins. Auditing data quality prevents misleading results and wasted analytical effort.

Lesson 1 • Normal Distribution Fundamentals

Explains the normal curve, z-scores, and probability areas. The normal distribution is the basis for most parametric tests covered in later chapters.

Lesson 2 • Central Limit Theorem in Practice

Demonstrates how sample means distribute normally regardless of population shape. This theorem justifies parametric inference on non-normal populations with sufficient sample size.

Lesson 3 • Sampling Methods and Sample Size

Compares random, stratified, and systematic sampling and calculates required sample sizes. Adequate sample size controls error rates and ensures reliable conclusions.

Lesson 4 • Normality Testing in Minitab

Runs Anderson-Darling and Ryan-Joiner tests and interprets probability plots. Normality test results determine whether parametric or nonparametric methods apply.

Lesson 1 • One-Sample Tests for Means

Performs one-sample t-tests and z-tests to compare a sample mean to a target value. Results guide decisions about whether a process meets a specified standard.

Lesson 2 • Nonparametric Alternatives

Uses Mann-Whitney, Wilcoxon, and Kruskal-Wallis tests when normality assumptions fail. Nonparametric methods provide valid inference on skewed or ordinal data.

Lesson 3 • Tests for Proportions and Variances

Applies 1-proportion, 2-proportion, and variance tests to attribute and spread data. Proportion and variance tests extend hypothesis testing beyond continuous means.

Lesson 4 • Hypothesis Testing Logic and Structure

Defines null and alternative hypotheses, Type I and Type II errors, and significance levels. This framework governs every inferential test performed in Minitab.

Lesson 1 • General Linear Model in Minitab

Extends ANOVA to unbalanced designs and mixed factor types using the General Linear Model. GLM handles complex experimental structures beyond standard two-way ANOVA.

Lesson 2 • One-Way ANOVA Concepts and Execution

Partitions total variation into between-group and within-group components using Minitab. One-way ANOVA determines whether at least one group mean differs significantly.

Lesson 3 • Post-Hoc Multiple Comparison Tests

Applies Tukey, Fisher, and Dunnett comparisons to identify which group pairs differ. Post-hoc tests control family-wise error after a significant ANOVA result.

Lesson 4 • ANOVA Residual Diagnostics

Evaluates residual plots for normality, constant variance, and independence assumptions. Residual analysis validates ANOVA conclusions and reveals model inadequacies.

Lesson 1 • Regression Diagnostics and Remedies

Examines residual plots, leverage, Cook's distance, and influential points. Diagnostics confirm that regression assumptions hold and results are trustworthy.

Lesson 2 • Logistic and Nonlinear Regression

Applies binary logistic regression for categorical outcomes and fits nonlinear curves. These models extend regression capability to non-continuous and curved relationships.

Lesson 3 • Multiple Linear Regression

Extends regression to two or more predictors and interprets partial coefficients. Multiple regression controls for confounding variables and improves predictive accuracy.

Lesson 4 • Regression Model Selection

Uses stepwise, best subsets, and Mallows Cp to identify the most parsimonious model. Model selection balances predictive power against overfitting and complexity.

Lesson 1 • Advanced SPC Techniques

Applies CUSUM, EWMA, and multivariate T-squared charts for detecting small or correlated shifts. Advanced charts complement standard Shewhart charts in high-precision environments.

Lesson 2 • Control Chart Fundamentals

Explains common-cause vs. special-cause variation and control chart structure. Understanding variation types is essential for correctly interpreting all control chart signals.

Lesson 3 • Variable Control Charts

Creates and interprets Xbar-R, Xbar-S, and I-MR charts for continuous measurement data. Variable charts provide the most sensitive detection of process mean and spread shifts.

Lesson 4 • Attribute Control Charts

Builds p, np, c, and u charts for defective and defect count data. Attribute charts monitor quality when measurement is binary or count-based rather than continuous.

Lesson 1 • Fractional Factorial Designs

Reduces run count by confounding higher-order interactions using fractional factorial designs. Resolution levels guide the trade-off between run economy and information completeness.

Lesson 2 • Full Factorial Experiments

Creates and analyzes two-level full factorial designs to estimate all main effects and interactions. Full factorials provide complete information but require more experimental runs.

Lesson 3 • Fundamentals of Experimental Design

Introduces randomization, replication, blocking, and factor-level selection principles. Sound design principles prevent confounding and ensure valid causal conclusions.

Lesson 4 • Mixture and Taguchi Designs

Applies mixture designs for formulation problems and Taguchi arrays for robust parameter design. These specialized designs address constrained factor spaces and noise factor control.