Home / Lean Six Sigma / ANOVA, regression & simulation
Find out which process variables move together, how strongly and how surely, before building a regression model or changing a machine setting.
Pre-sizing and estimating tool: results do not replace design, calculations or reports signed by a licensed professional, nor verification against the applicable codes and standards.
Each point is a table row. Direct labels show the slope and the most influential point; tap a point to exclude it from this chart only and watch r and R² change.
A −1 to +1 ruler with the usual bands (Evans, 1996), r and ρ with their confidence intervals, and R² as 100 squares.
Below the diagonal, scatterplots with a line; on the diagonal, histograms; above, the coefficient and p-value in color.
Variables clustered by correlation. Bold: p-value below 0.05.
Coefficient and confidence interval for each pair, strongest to weakest.
Pearson with Fisher z CI; Spearman with Bonett–Wright CI; p-value from the t test with N − 2 degrees of freedom.
The same pair computed separately within each group of the chosen column.
Take this page’s results to another calculator with the fields already filled in.
The calculation report gathers this page's inputs, results, equations, assumptions and references, with fields for project, engineer and revision. The full report also includes the charts and interpretations, in color. In the print dialog, choose Save as PDF.
That the two variables have a strong linear relationship in the same direction: when one rises, the other tends to rise. The R² of 0.64 says 64% of one’s variation moves with the other. Check the confidence interval: with 10 pairs, r = 0.8 may be anything from 0.34 to 0.95.
Pearson measures straight-line association and is the default for roughly normal continuous measurements. Spearman uses the order of the values: it suits curved relationships that always rise or fall, ratings and scores, and is barely affected by extreme values. If they differ by more than 0.1, look at the chart.
No. Both may depend on a third factor, such as weather, shift or raw material. Correlation shows where to investigate; to measure each factor’s effect, use regression with all of them or a designed experiment.
It depends on the size of r. Confirming r = 0.5 with 95% confidence and 80% power takes about 30 pairs; r = 0.3 takes about 85. The page computes that number for your r in the report card.
The observation that, on its own, changes r the most when removed. Tap it in the chart to see r and R² without it. If it is a special event, such as a cleaning, a start-up or a typo, investigate before excluding it from the data.
Select the columns with the names in the first row, copy and paste into the table field. Text columns, such as shift or supplier, become groups and can color the points. Rows with an empty cell are left out only of the pair where the value is missing.
Yes. r, rho, the p-values and the intervals follow the published formulas (Fisher for Pearson and Bonett and Wright for Spearman) and were checked against published examples and SciPy to the third decimal place.
Important notice: Indus Metrics tools produce estimates and pre-sizing results from the data you enter and from published engineering methods. They do not replace design, calculations or reports signed by a licensed professional engineer (PE), nor verification against the applicable codes, standards and regulations, such as OSHA rules and the ASME codes. Material and fuel properties vary: check manufacturer data or your own process analyses before deciding. By using this site you agree to the Terms of Use.
© 2026 Indus Metrics. Found an error? Write to contato@seudominio.com.