Caste-Stratified Market Penetration Randomization

In Simple Words

Imagine testing how a new vaccine affects an entire town's economy depending on what percentage of the population gets vaccinated. Instead of picking some towns to receive 10% vaccination and others 90% (which might accidentally pick wealthier or healthier towns), researchers select specific local community clubs in every town and offer vaccines to members of those chosen clubs. Because some towns happen to have larger memberships in those selected clubs, the total percentage of vaccinated people in each town varies naturally across towns without introducing biased town selection.

Research question

Measuring general equilibrium spillover effects requires cross-market variation in intervention coverage, but directly randomizing coverage rates at the village level can introduce selection bias or correlate with unobserved market characteristics. Stratifying individual-level randomization by naturally varying sub-groups (such as social castes) generates exogenous cross-market coverage variation while maintaining experimental control.

Participants

118 unique castes (jatis) across 63 sample villages in Andhra Pradesh, Uttar Pradesh, and Tamil Nadu, India.

Study Design

Two-step experimental design randomizing 93 treatment castes and random sub-samples of households within castes to create market-level coverage variation.

Results

Generated exogenous cross-village coverage variation ranging from 0% to 53% for cultivators and 0% to 100% for landless laborers, with zero statistically significant correlation to village size, caste concentration, or number of castes after conditioning on eligibility shares.

Takeaway

Use sub-group or caste stratification when designing large-scale randomized evaluations to generate exogenous market-level treatment intensity without confounding market-level characteristics.

Read alongside the research

Plain-English glossary

Original explanations, informed by the references below. Examples are illustrations, not data from the studies above. The research text stays unchanged.

Statistically significant

A label used when a result passes a chosen statistical threshold, often p < 0.05. It does not show how large or useful an effect is. A result that is not statistically significant does not prove there is no effect.

ExampleA study reports p = 0.03 against a 0.05 threshold. It passes that test, but the effect could still be too small to matter.

American Statistical Association · Statement on p-values ↗Read more about statistically significant →

Related findings

• Tangible Goods Simulation for Field BDM Auctions →Methods & evidence

  Before asking someone to place real cash bids on a complex multi-page financial contract, you let them play a practice round bidding 5 cents on a candy bar so they visually see how higher and lower bids win or lose the prize.

• Birthdate-Based Randomization Design →Methods & evidence

  Assigning people based on their birthdate works like splitting a crowd into two equal groups based on whether their ticket number is odd or even. Because birthdays are evenly distributed across the population, everyone born in the first half of the month gets one treatment and those born in the second half get another, creating two balanced groups without bias.

• Evaluation Time Horizon Bias →Methods & evidence

  Evaluating a policy right after it starts is like testing a person's diet on day one when they have not had time to buy snacks or change their routine. True long-term policy impacts can only be measured after people have had enough time to notice the change, adjust their habits, and settle into a new equilibrium.

• Exogenous Failure Assignment →Methods & evidence

  Imagine testing how drivers handle an unexpected patch of black ice on a road. If drivers only go onto the icy road voluntarily, only risk-tolerant drivers are tested; but if a road detour forces a random selection of drivers onto the ice patch, researchers can measure true handling ability and recovery without selection bias.