# Difference plot

A difference plot shows the differences between two observations on the same sampling unit.

The difference plot shows the difference between two observations on the vertical axis against the average of the two observations on the horizontal axis. A gray identity line represents equality; no difference.

If the second observation is always greater than the first the points lie above the line of equality, or vice-versa. If differences are not related to the magnitude the points will form a horizontal band. If the points form an increasing, decreasing, or non-constant width band, then the variance is not constant.

It is common to combine the difference plot with a histogram and a normality plot of the differences to check if the differences are normally distributed, which is an assumption of some statistical tests and estimators.

- What is Analyse-it?
- Administrator's Guide
- User's Guide
- Statistical Reference Guide
- Distribution
- Compare groups
- Compare pairs
- Difference plot
- Creating a Tukey mean-difference plot
- Equality of means/medians hypothesis test
- Tests for equality of means/medians
- Testing equality of means/medians
- Difference between means/medians effect size
- Estimators for the difference in means/medians
- Estimating the difference between means/medians
- Study design
- Contingency tables
- Correlation and association
- Principal component analysis (PCA)
- Factor analysis (FA)
- Item reliability
- Fit model
- Method comparison
- Measurement systems analysis (MSA)
- Reference interval
- Diagnostic performance
- Control charts
- Process capability
- Pareto analysis
- Bibliography

Published 8-Jan-2017

Version 4.90