--- title: Difference-in-Differences — RGM® Glossary url: https://realgrowthmatters.com/glossary/difference-in-differences/ updated: 2026-06-10 source_html: https://realgrowthmatters.com/glossary/difference-in-differences/ --- # Difference-in-Differences D·i·Dnoun Subtract the trend, keep the effect — compare changes, not levels, and what opened beyond the shared path is yours. Term : Difference-in-Differences Compares : Changes in treated vs untreated groups Cancels : Shared trends and seasonality Rests on : The parallel-trends assumption ## Forms & parts of speech DiD · noun Change-vs-change comparison. "Sales rose 14% in launch markets - but **difference-in-differences** showed control markets rose 9% anyway. The campaign owns 5." ## Definition in plain terms Difference-in-differences (DiD) is the quasi-experimental method for measuring an intervention's effect when you cannot randomize: compare the change over time in treated units (markets where the campaign ran) against the change in untreated ones (markets where it didn't), and the difference of those differences is the effect. The genius is in what cancels — seasonality, macro trends, anything moving both groups alike subtracts itself out, leaving only the gap that opened beyond the shared path. ## The mechanics The setup needs treated and control units observed before and after: launch the campaign in some regions, hold others out, measure both periods in both groups. Treated markets up 14% while controls rose 9% means the intervention owns five points, not fourteen — the naive before-after read overstates by exactly the trend the controls reveal (the CAUSAL-INFERENCE discipline operationalized). Everything rests on one assumption with a name worth memorizing: parallel trends — absent the intervention, treated and control groups would have moved alike. It is checkable in the rear-view (did the groups track each other before the launch?) and breakable in practice (treated markets chosen because they were already accelerating poisons the comparison — selection's revenge). The marketing habitats: geo-split campaign launches (DiD is the analysis engine of geo-experiments and CONVERSION-LIFT's regional cousin), pricing and policy changes rolled to some markets first, retail-distribution gains, and any natural experiment where something changed for some units and not others. The craft extensions handle real-world mess: matched controls chosen for pre-period similarity, synthetic controls built as weighted blends when no single market parallels the treated one, and event-study plots showing the gap period by period — flat before, opening after is the picture that convinces. ## When it matters DiD matters whenever a clean A/B is impossible but a control group exists in space or time — regional launches, market-by-market rollouts, platform changes that hit some accounts first. It matters most as the antidote to before-after storytelling, which credits campaigns with whatever the season was doing anyway. The discipline is parallel-trends verification in the pre-period, controls chosen before results are known, and the event-study plot shown with every claim — the method is one subtraction; the credibility is all in the setup. **Worked example.** A beverage brand launches a regional TV-and-DOOH push in five metros and headquarters celebrates the result: sales up 14% versus the prior quarter. The analyst runs DiD before the deck ships: eight matched control metros - chosen for parallel pre-period trends over the prior 18 months - rose 9% in the same window, riding the category's summer wave. The campaign's honest effect is five points, not fourteen, and the event-study plot makes the story legible: treated and control lines braided together for six quarters, separating only after launch week. Five points still clears the hurdle - the campaign scales to twelve more metros, with the next wave's controls locked before launch. The before-after version would have set expectations the summer owned; the difference of differences set ones the campaign could keep. **Failure modes to watch.** Before-after reads crediting campaigns with the season; treated markets chosen because they were already accelerating, breaking parallel trends; controls picked after results are known; no pre-period plot, so the assumption rides on hope; and effects claimed at granularity the regional data cannot support. ## Synonyms & antonyms ### Synonyms difference-in-differencesDiDdiff-in-diff ### Antonyms before-after comparisonuncontrolled rollout read ## Origin & history Difference-in-differences traces to John Snow's 1850s cholera work — comparing changes between London water districts — and became econometrics' workhorse quasi-experiment (Card and Krueger's 1994 minimum-wage study its modern landmark) before marketing adopted it as the analysis engine of geo-experiments. Etymology: [source](https://en.wikipedia.org/wiki/Difference_in_differences). ## Usage trends Search interest for this term over the last five years: [View interest-over-time on Google Trends →](https://trends.google.com/trends/explore?q=difference%20in%20differences&date=today%205-y) ## Common questions What is difference-in-differences? : A quasi-experimental method comparing the change in treated units against the change in untreated ones — shared trends cancel, and the remaining gap is the intervention's effect. What is the parallel-trends assumption? : That treated and control groups would have moved alike absent the intervention — checkable in pre-period data, and the method's credibility rests entirely on it. When do marketers use DiD? : Geo-split campaign launches, staged rollouts of pricing or policy, distribution gains — anywhere randomization is impossible but some markets got the change and comparable ones didn't. ## Related tools & calculators - tool[A/B test sample size](/tools/a-b-test-sample-size/) ## Resources & people to follow - reference[Wikipedia — Difference in differences](https://en.wikipedia.org/wiki/Difference_in_differences) - referenceQuasi-experimental methods literature (event studies, synthetic controls) - referenceRGM analysis — lock the controls before launch and show the pre-period plot with every claim Curated, non-competitor resources verified per term. ## Related training - module[Performance marketing](/training/performance-marketing-foundations/) ## Disciplines Areas of marketing where difference-in-differences is a core concern: [Performance marketing](/training/performance-marketing-foundations/)[Growth strategy](/training/growth-marketing-foundations/) ## Read next ## Related terms [Causal inference](/glossary/causal-inference/)[Incrementality testing](/glossary/incrementality-testing/)[Conversion lift](/glossary/conversion-lift/)[Confounding variable](/glossary/confounding-variable/)[AB test](/glossary/ab-test/) ## Sources 1. trends[Google Trends — "difference in differences"](https://trends.google.com/trends/explore?q=difference%20in%20differences&date=today%205-y)