Match each study subject to the candidate intervention most likely to benefit them¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article recommends that evaluators use its Bayesian approach to consider multiple candidate interventions simultaneously within one trial, matching each study subject with the intervention most likely to benefit that individual given their subgroup. This turns evaluation from estimating a single average effect into an allocation problem that learns what works for whom as data accumulate.

Design Implications¶

Context¶

Requirements¶

• A randomized trial infrastructure with multiple candidate treatment arms and continuously accumulating outcome data

Constraints¶

• The article states the efficiency gains occur only under the right circumstances identified in its simulation study

Target Learners¶

• Students in online courses and participants in public human services programs

Target Learning Goals¶

• Selecting the intervention most likely to benefit each learner or program participant

Affordances¶

• Bayesian Adaptive Policy Evaluation Heterogeneous Effects

Related Strategies¶

Examples¶

-

Key Sources¶

• Mariel McKenzie Finucane, Ignacio Martinez, Scott Cody. (2015). What Works for Whom? A Bayesian Approach to Channeling Big Data Streams for Policy Analysis. Working Paper 40, Mathematica Policy Research. https://www.mathematica.org/publications/what-works-for-whom-a-bayesian-approach-to-channeling-big-data-streams-for-policy-analysis