Reading the evidence
Effect size describes the magnitude of a difference or relationship in meaningful or standardised units. It complements uncertainty and helps distinguish detectable effects from useful ones.
Make it click
Two jumps both clear a qualifying line, but one clears it by a millimetre and one by a metre. The label matches while the practical magnitude does not.
Now put that into markets
Market effects can be expressed as percentage-point differences, returns, odds ratios or standardised measures. Costs and context determine usefulness.
Absolute and relative effects can tell different stories. Standardisation aids comparison but can hide the natural unit.
Report the estimate with an interval and a pre-defined smallest meaningful effect. Prefer units users can interpret.
Large estimated effects from small samples are often unstable, and a statistically precise tiny effect may be economically irrelevant.
Takeaway
