Measure how closely two methods agree on values. See concordance, correlation, and bias correction together. Download results, inspect plots, and validate paired datasets confidently.
| # | Method X | Method Y |
|---|---|---|
| 1 | 10.1 | 10.4 |
| 2 | 12.0 | 11.8 |
| 3 | 13.5 | 13.8 |
| 4 | 15.2 | 15.0 |
| 5 | 16.1 | 16.5 |
| 6 | 18.4 | 18.2 |
| 7 | 19.0 | 19.3 |
| 8 | 21.2 | 21.1 |
The calculator uses Lin’s concordance correlation coefficient:
CCC = (2 × covariance(X,Y)) / (variance(X) + variance(Y) + (meanX - meanY)²)
Pearson correlation measures precision. The bias correction factor measures closeness to the 45-degree identity line. Their product gives concordance, which captures both correlation and agreement.
Additional outputs include mean bias, mean absolute difference, root mean square error, location shift, and scale shift. These help explain whether disagreement comes from average offset, spread mismatch, or both.
It measures how closely paired values follow the identity line. It combines precision and accuracy, so it reflects both correlation strength and agreement between methods.
Pearson correlation checks linear association. CCC also penalizes bias and scale mismatch. Two methods can correlate strongly but still show lower concordance if they systematically differ.
CCC compares matched observations from two methods, instruments, or raters. Each row must represent the same item measured twice under comparable conditions.
A negative result suggests serious disagreement or opposing movement. It often signals poor reproducibility, data entry mistakes, or a relationship inconsistent with practical agreement.
Rows are ignored when they do not contain exactly two valid numbers. The calculator lists those lines so you can fix formatting and rerun the analysis.
Location shift reflects average offset between methods. Scale shift reflects spread mismatch. Together they help explain whether disagreement is caused by bias, variability differences, or both.
Yes. It is commonly used when comparing two measurement methods, duplicate assays, manual versus automated readings, or repeated measurements on the same samples.
The plot helps reveal outliers, nonlinearity, clustering, and systematic deviation from the identity line. It adds context that a single summary coefficient cannot show alone.
Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.