Compare and rank
Regression coefficient plot
Compares regression estimates and their uncertainty on a shared effect scale.
- Plot
- Effect comparison
- Uncertainty
What it answers
Which model coefficients differ and how uncertain are they?
- Shape
- Coefficient dots and intervals
- What it shows
- Effect direction and precision.
Example
The question
Which factors most affect basket value in our model?
Model coefficients with 95% intervals (EUR change in basket value)
Illustrative data. It belongs to no company.
When to use it
Use it when
Summarising regression coefficients with uncertainty.
Avoid it when
Comparing raw coefficients across incompatible units as importance scores.
How to read it
Read term names, estimates and intervals on a common scale.
Note
Interpretation depends on variable units and model specification.
The data you need
- Layout
- Wide interval summary
- Fields
- Study or Term: text; Estimate,Lower,Upper: numbers
- One row is
- One estimate and its lower and upper interval bounds. What is the grain?
- Rules
- Keep a common effect scale and specify the no-effect reference. Log-scale ratio effects require positive bounds.
- Optional
- Weight,Group,PooledIndicator,ModelName.
- Preparation
- Extract coefficient estimates and valid uncertainty intervals, keeping effect units and transformations explicit.
- Units
- Coefficient units depend onpredictor andoutcome scales; exponentiated ratios use no-effect 1, additive effects often 0.
Worked example
TermA0.20 with 0.05-0.35; TermB0.10 with-0.08-0.28. A's supplied interval excludeszero; B's does not.
| Study | Estimate | Lower | Upper |
|---|---|---|---|
| A | 0.20 | 0.05 | 0.35 |
| B | 0.10 | -0.08 | 0.28 |