Statistical Process Control (SPC) Using Microsoft Excel

Discover statistical process control (SPC) to analyze and improve manufacturing and service processes using inputs, outputs, and tools like capability analysis, Pareto analysis, control charts, and regression.

Differentiate attribute data from variable data and identify discrete and continuous subtypes within variable data to apply the correct SPC methods.

Explore the four data scales: nominal, ordinal, interval, and ratio, and how their meaningfulness and zero points guide analysis in statistical process control using Microsoft Excel.

Explore probability distributions, distinguishing discrete and continuous types with examples like the uniform die and log normal call times, and learn U(a,b) and mu and variance shaping spc data.

Explore the central limit theorem, showing that the distribution of sample averages becomes normal regardless of the population distribution, and apply this insight to sampling, means, and control charting.

Explore the normal distribution as the foundation of statistical process control, and learn how the central limit theorem justifies using sample averages, along with measures of central tendency and dispersion.

Calculate the mean, median, and mode in Excel from a data column using average, median, and mode, and note how alignment signals normality.

Explore measures of dispersion, including range, variance, and standard deviation, using population and sample formulas, with practical examples and notes on degrees of freedom for statistical process control in Excel.

Calculate measures of dispersion in Excel by using max–min for range, var.s and stdev.s for samples, and var.p and stdev.p for populations, plus descriptive statistics via data analysis.

Explore histograms as a key quality tool and learn to create one in Excel using age-group bins. See how an ordered histogram maps to Pareto diagrams for SPC analysis.

Explore how to use pivot tables in Excel to summarize defect data, perform Pareto analysis, and rank part numbers by total rejects for SPC.

Apply Pareto analysis in Excel by converting pivot data to a static table and calculating percent of total rejects. Identify the vital few versus trivial many with a Pareto diagram.

Apply Pareto analysis in two directions to rank rejects by part and by defect type, build Pareto diagrams in Excel, and focus on the top defects using the 80/20 principle.

Explore Pareto analysis in Excel using pivot tables to create Pareto diagrams by percent rejected and sort data by defects, part number, and type, with the attached workbook for practice.

Explore control charting in statistical process control using excel. Learn variable charts (x-bar and r, x-bar and s) and moving range, plus attribute charts (p, c, u).

Explore control chart terminology, including X-bar, x double bar, and R and R-bar. Differentiate specification limits (USL, LSL) from control limits (UCL, LCL) in run charts.

Build x-bar and r control charts in Excel from a 75-sample data set, calculating x-bar, r-bar, and A2-based control limits for a saw-cutting process.

Demonstrate X-bar and R chart interpretation, showing that 99.7% of values fall between control limits and the process is in spec and in control.

Build x-bar and s charts in Excel using 12 samples, calculating x-bar, s, and their upper and lower control limits with A3, B3, and B4 constants.

Learn to use the individual X and moving range chart, applicable to 100% measurements or infrequent production, where each value compares to the previous one, with Excel formulas.

Learn to build an individual X and moving range chart in Excel, using x bar and r bar, E2 and D4 constants, and absolute-value moving ranges to compute control limits.

Learn the p chart, the proportion defective attribute control chart, by sorting lots into good or bad and analyzing defects as a proportion, with variable lot sizes allowed within ±20%.

Calculate the p chart in Excel by deriving the proportion defective, average lot size, and control limits, then plot and interpret common and special cause variation.

Explore the np chart, aka pn bar chart, for counting defects in fixed-size lots (e.g., 500 pieces) using a binomial framework. Uniform lot sizes and automated measuring support defective-count interpretation.

Learn to build an NP chart in Excel using uniform lot sizes, compute NP bar and P bar, set upper and lower control limits, and flag out-of-control defects for investigation.

Explore the c chart for defects per single sample, using lot size one, appearance defects on surfaces, Poisson distribution, and Excel-based control chart analysis.

Explore the c chart for defect counting with sample size one in Excel, computing c bar, three-sigma tolerance, and upper and lower control limits to distinguish special from common causes.

Explore the u chart, the fourth attribute control chart, which monitors defects per standardized unit when sample size varies using Poisson assumptions in Excel.

Explore the u chart for fabric defects per square meter, calculating u bar and Poisson-based standard deviation to set control limits, and interpret out-of-control signals.

This addendum clarifies the u chart limits with a standardized unit, showing u-bar plus three times sqrt of u-bar divided by sqrt of N for Poisson defects per square meter.

Learn to interpret control charts, identify patterns across chart types, and guide investigations in the workplace to prevent out-of-control conditions.

Interpretation tools for control charts help you read X bar charts, identify out-of-control points, jumps, and shifts, and decide when to reset upper and lower control limits.

Identify trends, truncation, and lack of discrimination on control charts, and investigate out of control; apply Western Electric rules to x-bar, s, u, p, np charts and avoid over adjustment.

Explore Excel-based control charting for SPC with a downloadable workbook, a flow-chart driven selection process, chart types, control-limit formulas, and printable cheat sheets for variable and attribute data.

Learn how product design, working drawings, and tolerances drive manufacturing from concept to full production, including nominal dimensions, spec limits, key characteristics, and the role of process capability analysis.

Design manufacturing processes by selecting custom tooling and processing parameters for forging, stamping, plastic injection molding, and cnc operations. Prototype and small batches verify compatibility and enable customer evaluation.

Apply the six steps of the manufacturing development process, and perform capability studies after small batches and in full production using time-based or sequential sampling for statistical process control.

Explore process capability analysis as a computational method that compares the donut process's variable outputs to specification limits in Excel, including product and process variables.

Assess measurement methods for process outputs, from tape measures to coordinate measuring machines, noting accuracy and context. Compare cost, setup, and errors, including calipers, digital indicators, gauge blocks, and fixtures.

Learn how sampling frequency supports process capability analysis by sampling from a population, comparing 100% measurement, random sampling, and repeated samples to guide statistical process control with run and control charts.

Explore 100% measurement during prototyping and production with chart recorders and dimensional layouts. Review sampling options, histograms, descriptive statistics, and PK and P for capability analysis and control charts.

Explore the normal distribution, the bell curve, and how sample size influences the mean and dispersion, including the minimum 30 piece sample.

Explore the arithmetic mean, distinguishing population mu from sample x-bar, and learn to compute it in Excel using sum, count, and average.

Learn how standard deviation measures data spread, distinguishing population and sample versions (sigma and s), and apply calculations in Excel with stdev.p and stdev.s.

Enable the data analysis add-in in Excel 2016 to access the analysis toolpak from the data tab and learn to add and manage add-ins through Excel options.

Start with seven bins when plotting histograms to reveal underlying probability distributions, then identify normal distribution by its bell curve and middle peak, contrasting with exponential or uniform patterns.

Learn to assess normality in SPC data using Excel by examining distribution shape, skewness, and kurtosis, performing descriptive statistics, and applying the minus two to plus two range.

Build a histogram, assess normal distribution, and compute descriptive statistics (mu and sigma) to begin capability analysis, and introduce the P and Pk indices.

Learn to compute Pp and Ppk, two process performance indices, using mu, sigma, and the upper and lower specification limits with the formulas, as demonstrated in Excel.

Explain Pp and Ppk for a sample, contrasting with population indices, using x-bar and s instead of mu and sigma, and show how spec limits affect center and capability.

Analyze systematic sampling data to build a run chart by plotting x-bar and range over time. Compute x-bar, r, x double bar, and r bar to assess cp and cpk.

Learn to calculate cp and cpk from time-based sample data in Excel using x-bar and r-bar, estimate sigma with sigma hat, and apply control chart constants (D2) for SPC.

Interpret capability indices by comparing the data to specification limits, and see how pp, pp upper, pp lower, cp, cpk, and ppk change as the spec range shifts.

Explain how CPK estimates standard deviation from the average range and ignores within subgroup variation. Contrast this with PPK, which accounts for total variation across time.

Compare SPC and PCA, detailing core SPC tools—Pareto analysis, control charts, process capability and regression—plus advanced PCA topics like one-sided tolerances, Taguchi loss, CPM, and using Excel.

Learn capability analysis in excel with mu, x-bar, ppk, cpk, histograms, and run charts. Use the included cheat sheets and control chart constants to map sigma to defects.

Discover how regression analysis defines relationships between variables, build simple linear and multiple regression models, and use Excel's regression tool to make predictions with confidence intervals.

Explore regression analysis to estimate relationships between variables and make predictions, using simple linear regression with a dependent and an independent variable as starting point, then expand to multiple regression.

Learn to use a scatter plot in Excel to visualize the relationship between independent and dependent variables, and calculate the correlation coefficient to identify strong negative or positive correlations.

Explore how to use Excel's trendline for linear regression on a scatter plot, calculating the correlation and the best-fitting line, and interpreting interpolation versus extrapolation.

Interpret how Excel's trend line expresses a regression with y = -0.1219 x + 7.4688, linking pressure to nail depth and clarifying the y-intercept and slope. Emphasize validity between points.

Learn how the regression line is formed using ordinary least squares, with B0 and B1, from simple and multiple regression, and how residuals are minimized by squared errors.

Learn to build a linear regression model in Excel from a scatter plot and trendline, and use goal seek to back-calculate input values for a desired output.

Use regression with confidence intervals to estimate the upper and lower bounds of a dependent variable from intercept and coefficients, and learn how larger samples narrow the interval in Excel.

Apply a multiple regression case study in Excel to predict flexor strength from temperature and density, two independent variables, interpreting coefficients, R-squared, p-values, and confidence intervals.

Celebrate finishing this SPC using Excel course, with lifetime access to materials, and invite you to share feedback, download Excel workbooks, and refresh control charting anytime.

Discover a catalog of manufacturing and quality courses, including statistical process control with Excel, Lean Six Sigma, root cause analysis, reliability engineering, and career development.