🔒 Please log in to use tool features (fill sample / analyze / AI interpretation / export document)
🧲 Scatter Plot
Are two variables related? Correlation r, significance p, and regression line at a glance
Paste one (x, y) pair per line: two variables, one as X and one as Y, separated by space / comma / Tab (copy two columns from Excel and paste directly). You may type text at the start of a line as a sample label (auto-stripped). The tool plots a scatter + regression line and outputs Pearson r (strength of linear correlation), p (statistical significance), Spearman ρ, the regression equation and slope 95% CI; red dots flag residual outlier candidates. Typical uses: hardness vs. tensile strength, bake temperature vs. adhesion, RPM vs. surface roughness, setpoint vs. measured value. At least 3 pairs required.
Variable names (optional, used in chart and conclusions)
Paste data (one x and y pair per line)
What is the scatter plot telling you?
· The scatter plot is one of the seven basic quality tools, answering one question: do two continuous variables move together? (hardness↔strength, temperature↔dimension, RPM↔roughness, setpoint↔measured value)
· Read the conclusion in three steps: ① check the sign of r for direction—positive means both rise together, negative means one rises as the other falls; ② check |r| magnitude for strength—≥0.8 strong, 0.5~0.8 moderate, 0.3~0.5 weak, <0.3 essentially no linear relation; ③ check p—only p<0.05 is statistically significant (note: with large samples even very weak correlation becomes significant; in that case r matters more than p)
· Red dots = outlier candidates (residual > 2.5σ)—first verify whether they are data entry errors, measurement anomalies, or a special batch; don't let one point alone pull the correlation coefficient up or down
· Look at the chart before trusting the numbers: r≈0 may hide a curved relationship (U-shape / arch); a few extreme points can drag r toward 1 or 0. The gray dashed lines (x̄, ȳ) split the chart into four quadrants—points in the upper-right / lower-left support positive correlation, the other two quadrants suggest negative direction
· Correlation ≠ causation: two variables rising and falling together does not mean one causes the other; there may be a third hidden variable behind them. To confirm causation, use DOE (Design of Experiments)
· To compare between-group differences → "One-Way ANOVA" / "Box Plot"; to keep monitoring whether a key X is stable → "Control Chart SPC"
· Read the conclusion in three steps: ① check the sign of r for direction—positive means both rise together, negative means one rises as the other falls; ② check |r| magnitude for strength—≥0.8 strong, 0.5~0.8 moderate, 0.3~0.5 weak, <0.3 essentially no linear relation; ③ check p—only p<0.05 is statistically significant (note: with large samples even very weak correlation becomes significant; in that case r matters more than p)
· Red dots = outlier candidates (residual > 2.5σ)—first verify whether they are data entry errors, measurement anomalies, or a special batch; don't let one point alone pull the correlation coefficient up or down
· Look at the chart before trusting the numbers: r≈0 may hide a curved relationship (U-shape / arch); a few extreme points can drag r toward 1 or 0. The gray dashed lines (x̄, ȳ) split the chart into four quadrants—points in the upper-right / lower-left support positive correlation, the other two quadrants suggest negative direction
· Correlation ≠ causation: two variables rising and falling together does not mean one causes the other; there may be a third hidden variable behind them. To confirm causation, use DOE (Design of Experiments)
· To compare between-group differences → "One-Way ANOVA" / "Box Plot"; to keep monitoring whether a key X is stable → "Control Chart SPC"
About Scatter Plot
Scatter plot generator: plot X-Y data, compute Pearson correlation coefficient and overlay a fitted line to judge relationship direction and strength.
Learn more about this tool → ← Back to all quality tools