Advanced Lean Six Sigma: Practical Data Analysis with Excel

Apply the scientific method within Lean Six Sigma to reduce variation, using DMAIC, PDCA, SIPOC, and flow diagrams to observe, hypothesize, test, analyze, and act.

Apply the pdca cycle to solve problems by planning, doing, checking, and acting, then identify issues, test small-scale solutions, and measure results for improvement.

Master the Dmaic framework by defining, measuring, analyzing, improving, and controlling to drive data-driven problem solving, identify root causes, and stabilize complex business processes within Six Sigma.

Master the Sipoc tool to map a high-level process by defining suppliers, inputs, process steps, outputs, and customers, clarifying boundaries and establishing a shared understanding among stakeholders to improve efficiency.

Learn how process flow diagrams map steps, decisions, and data using simple symbols, label branches, and arrows to identify bottlenecks and drive improvement in teams.

Master statistics foundations for lean six sigma by studying descriptive and inferential concepts, measures of central tendency and dispersion, distributions, and hypothesis testing, with Excel handling calculations.

Probability and distribution types drive data-driven decisions in Lean Six Sigma, highlighting the normal and binomial distributions for continuous and discrete outcomes, to predict performance and improve quality.

Explore the normal distribution and its key measures—mean, median, mode, standard deviation, skewness, and kurtosis—and learn to interpret data with Excel in Lean Six Sigma contexts.

Define population and sample; explain practical sampling and methods: random, stratified, cluster, and systematic; and outline how to estimate sample size for 95% confidence.

Learn to perform descriptive statistics in Excel with the analysis toolpak, create histograms and box plots, and apply sampling to interpret mean, standard deviation, skewness, and outliers.

Advanced lean six sigma teaches measurement system analysis for data accuracy. Measurement system analysis evaluates bias, accuracy, precision, linearity, and variability, and involves SMEs to reduce measurement variation before analysis.

Understand the components of a measurement system in Lean Six Sigma, including discrimination, resolution, tolerance, bias, accuracy, precision, and stability, to ensure reliable data for decision making.

Explore MSA with Excel by applying the rule of ten to divide tolerance into ten steps and assess resolution, bias, drift, linearity (R-squared), and precision through repeatability and reproducibility analyses.

Attribute agreement analysis measures inspection accuracy and consistency in pass/fail parts, exposing bias, false rejects, and false accepts, and guides training and tool improvements, operator consistency and agreement between operators.

Examine how baseline measurements establish a starting point for Lean Six Sigma by tracking defects, cycle time, mean time between failures, and yield with a baseline matrix.

Understand yield metrics—classical yield, first pass yield, and rolled throughput yield—and how they expose rework and true process efficiency across steps, illustrated by form approvals and factory examples.

Learn how dpu measures defects per unit and how dpmo quantifies defects per million opportunities. See how dpo, yield, and sigma relate, with practical examples.

Apply statistical process control (SPC) and control charts to monitor process stability, differentiating random common cause variation from assignable special cause variation using rational subgroups, mean, range, and standard deviation.

Learn how IMR charts track performance using individual observations, compute x bar and moving range with Excel, set control limits, interpret signals, and apply to cases where subgroups aren't possible.

Explore x bar and r charts to monitor process stability over time, compute subgroups' averages and ranges, determine control limits, and interpret signals of out-of-control conditions.

Master x bar and s control charts to monitor mean and variation, calculating subgroup means, standard deviations, and control limits with a3, B3, and B4 for eight or more samples.

Learn to read control charts to monitor processes over time, detect violations and instability using Western Electric rules, center line, and sigma limits, and investigate root causes.

Master descriptive statistics for continuous data, including central tendency, spread, and distribution shape, to support data-driven decisions in Lean Six Sigma.

Standardize data to the standard normal distribution to compute z-scores, compare datasets, and estimate probabilities under the bell curve, enabling better decision making and variation reduction in lean six sigma.

Explore z scores, standard scores that show how far a value lies from the mean in standard deviations, and connect them to the standard normal distribution and alpha.

Apply z-scores to calculate probabilities and yield, illustrated by Jenny's test score and parts meeting a 105-inch upper specification limit.

Explore how a confidence interval uses sample data to estimate a population mean, with a chosen confidence level and calculated lower and upper limits.

Explore the central limit theorem, which shows that the average of many random, independent samples forms a normal distribution from non-normal data, enabling normal-distribution tools in Lean Six Sigma.

Master hypothesis testing to decide if sample evidence reflects the population, using null hypothesis H0, alternative hypothesis Ha, p values, alpha, and two-tailed, left-tailed, or right-tailed tests to compare means.

Learn to perform a one sample z test against a mean of 30 with variance 5, using a sample of 100 with mean 24.25 to decide if performance is better.

Explore the t distribution and its use in Excel hypothesis testing, performing two-sample t tests with equal or unequal variances, guided by F tests, p-values, and alpha levels.

See how hypothesis testing uses a null hypothesis and a t test to decide if a sample mean, like 170 from 30 people, differs from 150, guided by p values.

Learn how to interpret type I and type II errors in hypothesis testing within lean six sigma, using alpha and beta to minimize false positives and false negatives.

Explore ANOVA, the analysis of variance, to compare means across multiple groups and identify factors driving variation in Lean Six Sigma processes.

Compare three text support groups using one-way ANOVA in Excel to determine if performance differs significantly, using p-value and F statistic to guide data-driven Lean Six Sigma improvements.

Explore how a two-factor anova with replication assesses machine type and operator skill effects on task performance, including interaction and hypothesis testing through an example.

Perform a two-factor ANOVA without replication using Excel data to evaluate performance differences by vehicle type and driver experience, interpret f and p values, and note interactions cannot be tested.

Examine how sum of squares, degrees of freedom, and mean square reveal variation sources in ANOVA. Interpret SS rows, SS columns, and SS error for a small non-replicated data set.

Compute the mean square by dividing the sum of squares by degrees of freedom. Use mean squares to compare variation and form the F statistic for significance.

Understand how degrees of freedom in ANOVA shape variance estimates and the F statistic, via a two-factor, no-replication example that shows how limited df reduces power and blocks interaction tests.

Analyze covariance and correlation as metrics of how variables move together, with real estate size and price, and temperature and ice cream sales. Understand that correlation does not imply causation.

Apply linear regression to predict a dependent variable from an independent variable, distinguish correlation from causation, account for outliers, and evaluate model fit with r squared using Excel.

Learn to perform linear regression in Excel by creating scatter plots, adding trend lines, and interpreting r squared and the equation to assess model fit and predictive power.

Review essential Lean Six Sigma concepts, including central tendency, data spread, distribution shape, sampling and hypothesis testing, and control charts used for the project.

Apply the Dmaic framework to a Lean Six Sigma project on a 500ml bottle line. Define, measure, analyze, improve, and control quality with SIPOC, control charts, and hypothesis testing.

Calculate production activity by summing the monetary value of all items produced in a given time frame, revealing the production value KPI and the financial health of the manufacturing process.

Explore cycle time as a key manufacturing KPI that sums process time, inspection time, move time, and queue time to improve lean production.

Explore first pass yield, a KPI measuring how many products come out perfect on the first try, calculated by dividing perfect by started, and used to gauge quality and efficiency.

Set takt time as the production tempo that aligns output with customer demand by dividing available production time by demand; use a two-minute per product example to balance flow.

Calculate inventory turnover by dividing cost of goods sold by average inventory to show how fast products move from warehouse to customers, with 10,000/2,000 = five turns per year.

Measure how efficiently assets like machinery and inventory generate profit. Compute ROA by dividing net income by total assets, highlighting a 20% return on assets.

Calculate overall equipment effectiveness by multiplying availability, performance, and quality to measure equipment performance against its full potential.