Ceteris paribus
Ceteris paribus, Latin for 'other things equal', is the interpretive condition that gives a regression coefficient its meaning. Each slope in a multi-variable model shows the effect of changing one variable while holding all others fixed.
Also known asholding all else constant · all else equal
See it move
A side-by-side comparison contrasts two regression approaches. Without controls, the slope absorbs correlated effects and risks omitted variable bias — illustrated by a size coefficient that partly captures location. Under ceteris paribus, represented by a model with controls, slope β₁ isolates the effect of X₁ whilst all other variables are held at their observed values, so a size coefficient reads cleanly after controlling for neighbourhood quality.
Check yourself
A researcher fits the model: Monthly sales (€000) = 3.2 + 0.8 × Advertising spend (€000) + 1.5 × Number of outlets. She reports that the slope on advertising spend is 0.8. Which interpretation is correct under the ceteris paribus condition?