[2022] Minitab: Master Minitab From A-Z | Minitab 19

Define data and explore its two main types: categorical data and numeric data. Explore examples of categorical data, continuous data, and count data to see how data informs decisions.

Learn to use a bar chart to compare defect frequencies across production lines, with defect types on the horizontal axis and counts on the vertical axis.

Learn how to create a bar chart in Minitab using the values from a table option, selecting a cluster chart for two production lines to compare defects.

Pareto chart theory helps identify the most frequent defects by ranking categories in decreasing frequency and plotting a cumulative frequency line, guiding targeted 85 percent defect elimination.

Learn to generate a pareto chart in Minitab 19 by navigating to stat > quality tools > chart, selecting defect type and frequency, and clicking ok.

Explore how pie charts visualize the percentage contribution of each defect to total defects for two production lines, highlighting the most impactful defects.

Learn to build a pie chart in Minitab from crosstab data to display the percentage contribution of each defect type across production lines, label slices, and compare lines.

Explore histogram theory by visualizing numerical data with equal-size intervals, reading bar heights as frequencies, and recognizing right or left skewness and symmetry; note sample size guidelines for reliable interpretation.

Learn to plot a histogram in Minitab, choose from four histogram types, and assess whether height data fit a normal distribution curve.

Explore dot plots for small to medium data, compare with histograms, and learn how bin width and data points reveal distribution and outer layers in real data.

learn to create a dot plot in minitab 19 for a single data group, choosing graph options, selecting the data column, and interpreting how the data distributes across small units.

Visualize data with an individual value plot, where every measurement is a dot without bins, enabling outlier detection and easy comparison of populations.

Create and interpret individual value plots in Minitab to compare two production lines, entering two columns and selecting multiple, white and simple blocks, with means around 30 and 25.

Explore box plot theory using a plastic bottle height example, visualizing data with the box, whiskers, median, Q1, Q3, and outliers for group comparisons.

Learn how to create a box plot in Minitab 19, select box plot, input height data, and interpret the median, quartiles, and whiskers to visualize data spread.

Explore how to visualize production data with a time series plot, showing horizontal time axis and vertical measurements, to identify variability, trends, patterns, and stability against control limits.

Create a simple time series plot in Minitab by selecting the simple time series block, entering the height data column, and viewing dates on the x-axis.

Compare mean and median as central-tendency measures using a plastic board data example, calculating from samples and noting how left or right skew shifts their values.

Compare data spread between two plastic bottle production lines using range and standard deviation. Compute deviations from the mean, square them, and divide by n-1 to obtain variance.

Calculate descriptive statistics in Minitab by selecting height in centimeters and displaying mean, standard deviation, minimum, maximum, median, and quartiles.

Learn inferential statistics by surveying a sample to infer population parameters, using population and sample concepts, and applying mean and standard deviation to compare experiments.

Examine random sampling and its role in inferential statistics, showing how equal chances of selection help samples represent the population and support unbiased experiments with resin and process variables.

Explore random sampling in minitab by selecting a hundred samples from ten thousand customer ideas, using random data in columns and storing results to generate representative samples.

Explore the concept of sampling distribution, using a customer interest example to show how sample percentages center on the true population proportion and assign probabilities to outcomes.

Explore the central limit theorem by comparing means from multiple samples, show that the sampling distribution of means becomes normal as sample size grows, regardless of population shape.

Explore the normal distribution, its histogram and curve, learn that total probability is one, with 68.264% within one standard deviation, and use z-scores in Minitab.

Learn to calculate the probability between two points on a normal distribution using Minitab, by selecting normal distribution, entering x values, and reading the shaded area result.

Explore the t-distribution for unknown population standard deviation and small samples, and compare it to the normal distribution. Understand degrees of freedom, sample means, and p values.

Use point estimates like the sample mean and standard deviation to form confidence intervals, inferring population parameters. Example: 95% CI for mean 28–32 cm; 99% CI 27–33 cm.

Master hypothesis testing with Minitab: define null and alternative hypotheses, analyze sample data, and decide to reject or fail to reject using p-value and alpha.

Define null and alternative hypotheses for a one-sample t-test. Verify data are random, numeric, and from a normal distribution, then compare the p-value to alpha to draw conclusions.

Learn to perform a one-sample t-test in Minitab, set the population mean to 30 cm, apply 95% confidence, and use histograms and box plots to interpret p-values.

Explain type i and ii errors, when to reject or fail to reject the null, and how alpha, beta, and power relate to test decisions.

Conduct a two-sample t-test in Minitab by selecting each sample in its own column and setting the null difference to zero; interpret the p-value to assess if population means differ.

Perform a two-variance test to compare production line variances, with null hypothesis sigma1^2 = sigma2^2; a p-value of 0.000 with alpha 0.05 rejects equal variances.

Demonstrates performing a variance test in Minitab by selecting two samples in separate columns, setting 95% confidence, and rejecting the null hypothesis that the two production line variances are equal.

Learn how to perform a paired t-test in Minitab by testing before-and-after data, setting null and alternate hypotheses, evaluating p-values and confidence intervals to decide whether to reject the null.

Define a one-proportion test with random binary data and independent observations to test p=0.05 using 1000 samples and 46 defects, yielding p-value 0.564 and 95% ci 0.033–0.0608; fail to reject.

Perform a one-proportion test in Minitab by selecting Stat > basic statistics and one-proportion test; input data or summaries, set p0 to 0.05, and interpret the p-value with 95% confidence.

Perform a two-proportion test in Minitab 19 using summarized data, enter defect counts 46 and 58, set 95% confidence, compute two-sample proportions, and interpret failure to reject the null hypothesis.

Perform a two-proportion test in Minitab 19 using summarized data from two samples of defectives, set a 95% confidence level, and determine whether to reject the null hypothesis.

Learn to perform a chi-square test by defining null and alternative hypotheses of independence across production lines, using contingency tables of defect categories, bar charts, and p-values against alpha.

Run a chi-square test for association in Minitab using two data columns of defects by production line, input raw data, and interpret a near-zero p-value to reject the hypothesis.

Statistical process control uses control charts to distinguish common from assignable variation, and explains how three lines—upper and lower control limits and the center line—signal stability.

Explore how to construct and interpret R, S, and X-bar control charts for subgroups, using mean, range, and standard deviation with control limits to detect special and common causes.

Learn to plot r, s, and x-bar charts in Minitab by organizing data into subgroups, setting subgroup sizes (min eight), and interpreting variation within and between subgroups for process control.

Examine I and MR charts for variable data with one-item subgroups, using moving range and I-chart methods to assess plastic bottle length measurements and construct control limits.

Learn to create I and MR charts in Minitab by selecting variable charts for individuals, entering data in the variables box, and clicking OK to view the charts.

Explore how p and np charts monitor the proportion of interest in attribute data, handle varying and equal subgroup sizes, and identify out-of-control signals in a process.

Learn to plot p and np charts in Minitab by using Stat > control charts > attribute charts, selecting the chart, and assigning a subgroup size column to generate chart.

Explore how C charts and U charts monitor defects in production, with C charts for same sample sizes and U charts for varying sizes, showing data within control limits.

Learn to create c and u charts in Minitab 19, using control charts, by selecting variables, counts, and subgroup sizes, and adding charts to plot the data.

Explore process capability by comparing specification limits to process variability using Cp, Cpk, Pp, Ppk, and sigma level, ensuring stability and normality with control limits and Anderson Darling test.

Explore process capability indices cp and cpk, defined as ratios of specification limits to control limits, and see how they reflect mean and variation under six sigma concepts.

Explore process performance indices Pp and Ppk, defined with overall sigma to assess performance against specification limits, using Six Sigma and evaluate long-term stability against subgroup-based variation.

Learn to compute Cp, Cpk, Pp, and Ppk in Minitab by navigating to STAT, selecting a dataset and subgroup size, and reading the resulting values.

Explore the process capability index and sigma level, the distance from the mean in standard deviations, Z value via the inverse cumulative distribution function, and lower and upper specification limits.

Compute the sigma level in Minitab by selecting dataset one, setting subgroup size to five, inputting 29 and 31 as specs, and enabling confidence intervals to compare benchmarks.

Learn how to handle non-normal data in process capability analysis by transforming data to normal using Box-Cox (lambda) and Johnson transformations, and by fitting alternative distributions.

Explore how Box-Cox transformation normalizes non-normal data by varying lambda, using a plastic bottle production example. Assess normality with Anderson-Darling, choose best lambda, evaluate CPQ values before Johnson transformation.

Explore performing Box-Cox power transformations in Minitab, selecting the optimal lambda, and applying the transformation to normal data for improved analysis.

Apply the Johnson transformation to convert non-normal data into normal data, validate normality with the Anderson-Darling test, and assess process capability with PPK against 1.33.

Learn to perform a Johnson transformation in Minitab on a single column, assess normality with p-values, and interpret the transformed data.

Explore alternative distributions and automated fitting in Minitab to model non-normal data, using Box-Cox and Johnson transformations and various distribution models to find the best fit and handle outliers.

Explore fitting alternate distributions in Minitab, comparing normal, exponential, logistic, and other distributions, and evaluate goodness using P values to identify the best model.

Explore one-way anova to compare tensile strength across four suppliers, analyzing between and within-subgroup variation with factors, levels, and responses; assess null versus alternative hypotheses using p-values and f-values.

Learn to perform a one-way anova in minitab, including setting response data, selecting options for 95% confidence intervals, assuming equal variances, and interpreting results and residuals.

Explore a two-way anova using a plastic board example, examining how temperature and humidity affect tensile strength, including main effects and their interaction with Minitab results and optimization.

Perform a two-way ANOVA in Minitab to assess how temperature and humidity affect tensile strength, and use the response optimizer to identify optimal conditions at 120 and 30.

Explore how correlation reveals the relationship between two quantitative variables using scatterplots and the Pearson coefficient, and learn how p-values assess linear links and the impact of outliers.

The lecture demonstrates calculating the coefficient of correlation in Minitab and using p-values to test the null hypothesis for a linear relationship, illustrated with a plastic bottle manufacturing example.

master simple linear regression with least squares to predict revenue from marketing expenditure, interpret the regression equation, r-squared, and residuals, including hypothesis testing and p-values.

Learn to compute a regression equation in Minitab for a linear model, using revenue as the response and marketing as the predictor, and validate with ANOVA and a 99.4% R-squared.