Six Sigma Statistics using Minitab 19 with practice examples

Explore descriptive and inferential statistics, where descriptive statistics organize data with graphs and measure central tendency and variability, and inferential statistics infer populations from samples using probability.

Apply row statistics in calc to compute mean, sum, and other metrics across physics, chemistry, biology, mathematics, and english; verify the mean with the calc function.

Learn two methods to perform column statistics in Minitab 19: use calc column statistics to compute means and other metrics, or use display descriptive statistics for multiple subjects.

Develop six sigma statistics using minitab 19 with practice examples by applying lean, business, quality management and improvement tools to add value and solve problems.

Discover how to choose graphs in minitab by objective, including histogram, box plot, pareto chart, bar chart, pie chart, scatter plots, and control charts for time and relationships.

Learn to create pie charts in Minitab 19, using categorical variables like sex and sales location to compare proportions and percentages, and customize slices and chart options.

Explore creating simple, cluster, and stacked bar charts in Minitab 19, using counts and percentages to compare subjects by grades 10 and 11.

Create a simple box plot in Minitab 19 to visualize the center, spread, whiskers, median, and quartiles of GPA data for twenty students.

Compare sales performance of two agents using a multiple box plot in Minitab, analyze medians, quartiles, outliers, adjust the title, and interpret whisker ranges.

Draw box plots with groups in Minitab to compare GPA across study hours, using the with groups option. Interpret whiskers, outliers, and n per category.

Explore the pareto principle and pareto charts for root cause analysis in Six Sigma and Lean projects, showing how 20 percent of causes drive 80 percent of outcomes.

Learn to create a pareto chart in Minitab 19 to identify key process inputs affecting retail checking time, using defects and total score data and options for combining remaining defects.

Use scatter plots to explore the relationship between two variables and identify correlation. Assess positive or negative correlations, no correlation, and strength with a line of best fit.

Learn to create a simple scatter plot in Minitab 19 (and 2018) to study the relationship between sales and advertisement in thousand dollars, with options for groups and regression lines.

Compare before and after maintenance using an individual value plot in Minitab 19, showing how defects drop across multiple data batches.

Plot a time series scatterplot of defects versus time in minutes with a connect line to show how defects progress over time in six sigma statistics using Minitab 19.

Explore the relationship between sales and advertising with a scatterplot with regression in Minitab, interpret the regression equation and the R-squared value of 95.8%.

Discover six sigma statistics using minitab 19 with practice examples, guided by a responsive instructor who adds practical value through general, real-world case studies for professionals across fields.

Analyze descriptive statistics to determine central tendency and distribution using mean, median, mode, standard deviation, and variation in yield percentage data, using Minitab.

Generate a simple histogram in Minitab 19 to visualize defects per 10000 items, adjust binning and interval counts, and interpret the data shape and spread.

Compare defect counts for machines A and B with a grouped histogram, noting A's higher mean and greater standard deviation, and B's lower mean with left-skewed distribution.

Use the with fit tab to generate a normal curve for defects per 10,000 items; note mean 59.6, standard deviation 17.5, positive skew, and an outlier at item 16.

Check normality before hypothesis testing in Minitab 19 using graphical summary and normality tests. Interpret p-values, skewness, and kurtosis; a p-value above 0.05 suggests normal data for further tests.

Check normality in Minitab using graphical summary and normality test; p-values below 0.05 lead to rejecting the null, indicating non-normal data and suggesting non-parametric tests.

Explore binomial distribution with minitab by analyzing two-outcome scenarios, using a 0.91 success rate across 10 trials to find P(X=7), P(X=10), and P≥8.

Explore Poisson distribution in Minitab 19, using a mean of 2 crashes per year to compute the probability of exactly four crashes and the 90 percent maximum with left-tail shading.

Explore how control charts monitor a process over time, identify stability with center lines and control limits, and distinguish common from special causes using Minitab.

Explore how run charts reveal data stability and identify special causes of variation, such as process bias, data clustering, and systematic sampling, through patterns like trends and shifts.

Explore the control chart selection pathway for continuous data, distinguishing continuous and attribute data, and choose I-MR for ungrouped data, R for subgroups ≤ eight, and S for larger groups.

Follow the pathway for attribute control charts, distinguishing between P, NP, U, and C charts and when to use each for defects per unit or defective items.

Explore the i chart in Minitab 19 by building pre-phase and post-phase control charts for continuous time data and verify all points stay within control limits.

Learn how to construct and interpret an x-bar r control chart for subgroups of five bottles, identify time-based patterns, and investigate a high 11:30 am reading within control limits.

Using a p control chart in Minitab 19, this lecture analyzes varying subgroup sizes over 20 days of calls to monitor the proportion of unanswered calls and detect special causes.

Study the np chart, counting defectives in a fixed subgroup size. Use Minitab's np option to compute mean, lower control limit, and upper control limit, and identify special causes.

Explore the u chart, a u-type control chart for defects per unit with varying subgroup sizes, using Minitab 19, and compare it with p-type and B-type attribute charts.

Use a c chart to monitor defects per unit in a batch of 10,000, with mean 33.2 and limits 15.91 to 50.49; point at 65 defects indicates a special cause.

Draw an I chart for individual data to compare before and after improvement, using stages to show faster cycle time and narrower control limits.

Explain hypothesis testing by identifying the null hypothesis and alternative hypothesis, review type I and II errors, and apply alpha and p-value to make rejection decisions.

Perform a one-sample t test in Minitab to test if the mean pizza delivery time equals 25 minutes; with a p-value of 0.38, accept the null hypothesis.

perform a two-sample t test in Minitab 19 to compare mean packaging times between machine A and machine B, including data setup, null and alternative hypotheses, and interpreting the p-value.

Analyze yield with a two-way anova using a general linear model to test operator, machine, and their interaction. Tukey comparisons reveal machine B and raw material AA maximize yield.

Assess a product's material mix using chi square goodness of fit in Minitab 19, comparing observed counts to expected proportions and testing the null hypothesis with p-values.

Explore correlation as a statistical measure of how two variables relate, using the Pearson correlation coefficient from -1 to +1. Interpret strong positive, negative, and zero relationships with scatter plots.

Select the regression pathway by the number of X variables: single X for simple regression, two to five X for multiple regression, then optimize the response for target profit.

Learn how to plan screening experiments to identify the most influential factors among 6–15, then optimize 2–5 factors to maximize a response such as viscosity in a syrup.

Master measurement system analysis to quantify variation in data, addressing bias, linearity, stability, repeatability, reproducibility, and the impact of gages, fixtures, calibration, and environmental factors.

Explore selection criteria for measurement system analysis by data type, performing gage R and R for continuous data and attribute agreement analysis for attribute data, using the respective worksheets.

Learn to perform gage R and R studies to quantify measurement system variation. Determine whether variation comes from the instrument or the operators and apply thresholds for repeatability and reproducibility.

Assess process capability using Cp and Cpk to determine if a production process meets specifications, considering USL, LSL, sigma, and potential centering issues.