Statistical quality control with MS Excel

Demonstrate central tendency and dispersion using MySQL, explaining mean, median, and mode, and standard deviation, variance, and range, including sample versus population and Bessel's correction.

Explore central tendency in Excel by calculating mean (average), median, and mode from a dataset, using formulas, selecting data ranges, and understanding single or multiple modes.

Explore dispersion in data by computing population and sample standard deviations, variances, and the range in Excel, illustrating Bessel correction and related formulas.

Learn to visualize age variation with an Excel histogram, outlining bin size creation via pivot tables, computing frequencies, and formatting axes for clear interpretation.

Showcases variation of data using MS Excel by building stem-and-leaf plots of student ages, explaining stems and leaves, ordering data, and deriving a histogram from the plot.

Explore box and whisker plots in MS Excel using a five-number summary—minimum, Q1, median, Q3, and maximum—to visualize variation in student ages (in months).

Apply the central limit theorem to obtain a normal sampling distribution of the mean as sample size grows, regardless of population distribution, given finite variance and independent, identically distributed observations.

Explore the normal distribution, its bell-shaped curve, and how mean and standard deviation determine position and spread, with practical 68-95-99.7 percent rules.

Construct a normal distribution curve in Excel by calculating values from -3 sigma to +3 sigma, computing the pdf with Excel's normal distribution function, and plotting a smooth, symmetric curve.

Explore how the central limit theorem explains the transition from a uniform to a normal distribution when sampling single dice values, using histograms and frequency analysis of 100 throws.

Demonstrate the central limit theorem with two dice by building a histogram in Excel, illustrating how sums from 2 to 12 form an approximate normal distribution as sample size grows.

Demonstrate the central limit theorem by simulating five dice rolled 100 times, then create a normal distribution curve in Excel from the resulting frequency data.

Explore the difference between variables (continuous data) and attributes (discrete data), and learn how control charts apply these concepts to monitor quality with measurements and conformance.

Dive into the classification of control charts, including mean, range, and proportion charts, with central lines, standard error, and three-sigma limits for x-bar, r, s, p, and c charts.

Construct an x-bar mean control chart in Excel by calculating x-bar, x-bar-bar, r-bar, and A2, then determine upper and lower control limits and plot the chart to identify out-of-control samples.

Construct a range control chart in excel using D4 and D3, plot with a line chart, and note the mean chart breach indicating the process is out of control.

Compute the proportion defective p = d/n and build a p-chart in MS Excel by calculating p-bar and n-bar, then determine UCL and LCL and identify out-of-control points.

Learn to construct a np-chart in Excel for 15 lots of 400 items, calculating the center line and control limits, and distinguish it from proportion defective charts.

Construct a defect control chart (c-chart) in Excel using the center line C-bar, and compute UCL and LCL with 3 sqrt(C-bar) to identify out-of-control samples.

Learn how to assess process capability against design specifications, using nominal value, tolerance, and USL/LSL, and relate Six Sigma to in control production for quality control.

Explore process capability ratio and process capability index (Cp and Cpk) and how six sigma, design specification width, and process centering determine whether a process meets specifications.

Explore how to perform process capability analysis in MS Excel, including calculating mu and sigma, plotting histograms with three-sigma limits, and computing CP and CPK to assess process capability.

Estimate defective product rate with the Z score. Use a standard normal distribution with mean and standard deviation to convert x-values to Z and read areas for defective products.

Design a single sampling plan using the Larson nomogram, a graphical tool that links sample size, acceptance number, and lot fraction defective to approximate binomial probabilities.

Design a single sampling plan using the Larson nomogram to determine the sample size and acceptance number. Learn producer and consumer risks and construct the operating characteristic curve.

Design a double sampling plan using military standard 105e to determine lot acceptance or rejection based on two samples and standard acceptance and rejection numbers.