Tempered Thompson Algorithm

In Simple Words

Imagine a doctor testing four different medical treatments on arriving patients. Instead of flipping a fair four-sided coin for every single patient throughout the entire study, the doctor tracks which treatment is working best. For each new patient, the doctor flips a biased coin: 80% of the time, the patient receives whichever treatment currently looks best based on historical data, while 20% of the time, the patient is completely randomized among all four options. This guarantees that every treatment maintains a minimum chance of being tested (e.g., 5%), allowing researchers to reliably gather data while still giving most patients the top treatment.

Research question

Standard randomized controlled trials allocate subjects equally across treatment arms to maximize statistical precision, but this can assign many vulnerable individuals to inferior interventions. Pure bandit algorithms assign subjects to high-performing arms to maximize participant welfare, but vanishing allocation probabilities for suboptimal arms cause severe inferential bias and high variance.

Participants

N = 3,770 individuals (1,663 Syrian refugees and 2,107 Jordanian jobseekers) in urban Jordan.

Study Design

Adaptive targeted field experiment using a Tempered Thompson Algorithm with mixing parameter gamma = 0.2 and 16 demographic strata, evaluating rapid 6-week employment as well as 2-month and 4-month follow-up outcomes.

Results

At gamma = 0.2, the minimum allocation probability for any of the 4 treatment arms is bounded below at 5%. In counterfactual simulations using 2-month employment outcomes, the algorithm doubled the employment gains compared to a standard randomized controlled trial.

Takeaway

Set the mixing parameter gamma in a multi-armed bandit algorithm to enforce a lower bound gamma/k on assignment probabilities for all k treatment arms to balance participant welfare and frequentist inference bounds.

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.

Follow-up

Collecting more information about participants later in a study to see what has happened to them. The term can also mean the length of time researchers keep track of them.

ExampleResearchers interview the same workers three months after a programme ends. That later interview is a follow-up.

GET-IT glossary · Follow-up ↗Read more about follow-up →

Randomized controlled trial

A study that uses chance, like drawing lots, to decide who receives each option being compared. Researchers compare the groups’ outcomes to estimate the effect of those options.

ExampleA lottery assigns volunteers to a training programme or a comparison group. Researchers then compare their outcomes.

GET-IT glossary · Randomized study ↗Read more about randomized controlled trial →

Related findings

• Counterfactual Re-Randomization Inference →Economics (general)

  Imagine evaluating whether a coin is biased during a game where the referee alters the flipping rules every time someone scores. To test fairly if players had any real effect on the game, you replay the exact sequence of changing referee rules thousands of times assuming player actions mattered zero percent, creating a true benchmark to see how rare the real game result actually was.

• Frequentist Variance Bounding in Adaptive Trials →Economics (general)

  Imagine an adaptive slot machine experiment where the casino wants to stop players from using losing machines. If the casino completely turns off losing machines after a few bad spins, researchers can never prove mathematically how bad those machines actually were.

• Myopic Stopping Rules for Adaptive Field Experiments →Economics (general)

  Imagine a company testing new advertisements online. Every day, the company measures how much extra revenue it earns by showing the top ad compared to the daily cost of keeping the test running.

• Statistical Surrogacy in Sequential Policy Trials →Economics (general)

  Imagine a school testing three teaching methods to improve student graduation rates ten years later. Waiting a decade to update the teaching strategy makes adaptive learning impossible.