Tag

experimental_design

30 findings

Methods & evidenceTangible Goods Simulation for Field BDM AuctionsPractice rounds enabled successful implementation of 4-contract BDM elicitations across 1,978 rural subjects, resulting in zero instances of participants refusing to complete winning transactions.RCT DevelopmentBecker-DeGroot-Marschak Wage Elicitation MechanismOver 60% of participants accepted low piece rates (10 MWK/unit, yielding ~70 MWK daily earnings plus 50 MWK participation fee). Ex-post refusal rates were under 3% and declined over time, confirming that workers learned and adhered to truthful wage revelation.RCT EducationBetween-School Generalizability Limit of Within-School RCTsRandom assignment was strictly bounded within individual schools, grade levels, and subjects, preventing statistical evaluation of whether teacher value-added metrics hold predictive validity for cross-school teacher transfers or district-wide comparisons.RCT Methods & evidenceBirthdate-Based Randomization DesignProduced balanced baseline demographic distributions across treatment and control groups while enabling evaluation of policy regime shifts.RCT Methods & evidenceCaste-Stratified Market Penetration RandomizationGenerated 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.RCT DevelopmentCaste-Stratified Village Identification StrategyConditioning on eligibility population shares eliminates endogeneity bias, reducing correlations between insurance marketing proportions and village characteristics (such as caste concentration and total households) to statistically insignificant levels (p-values > 0.33).RCT Labour & employmentCasual-Labor Field-Laboratory Screening ProxyReplicated real-world day-labor market conditions where 91 percent of participants were active labor force participants and 45 percent had made real job referrals, achieving a 72 percent return rate (N = 407 referrals) with robust experimental control over financial and screening incentives.RCT Behaviour & psychologyCovert Market Choice Experiment FramingCovert framing successfully measured baseline discrimination where control group participants sacrificed goods worth nearly twice the median daily per capita food expenditure to avoid selecting transgender workers, while eliminating experimenter demand bias.RCT Economics (general)Cross-Community Audit Methodology for Bias DetectionStandardized multi-community audit visits successfully isolated seller pricing differences (-12% for Marwari sellers vs. +5% for Andhra sellers) and buyer-seller match effects independently of product quality or negotiation script variations.RCT Labour & employmentDouble-Sided Randomization DesignPlacing 1.398 formal apprentices per firm displaced only 0.318 traditional apprentices, creating a net gain of 1.080 total apprentices per firm (p < 0.0001); net job creation was bounded between 74.1% and 77.3% of formal positions placed.RCT Labour & employmentEffective Wage Differential Bundle MechanismThe logit intercept divided by the slope directly identifies the marginal value of time, proving that effective wage variation cleanly isolates willingness to supply incremental work hours without income effects.RCT Methods & evidenceEvaluation Time Horizon BiasThe estimated intervention effect was 0.085 SD (p < 0.05) after 1 year (before household reoptimization), but fell to a statistically insignificant 0.053 SD (p = 0.611) after 2 years once households adjusted private spending.RCT Methods & evidenceExogenous Failure AssignmentAmong the subset forced into the difficult task who failed in Round 1 (N = 558 in Sample A, N = 522 in Sample B), treated students re-attempted the difficult task in Round 2 at rates 17.6 percentage points higher in Sample A (p = 0.002) and 13.9 percentage points higher in Sample B (p = 0.064) than control group baseline rates of 36% and 51%.RCT Methods & evidenceExperimental Self-Selection Verification and External ValidityProject firms showed no statistically significant differences from nonproject firms in pre-intervention assets ($12.8M vs $13.9M, p = 0.841), employees (204 vs 221, p = 0.552), total borrowings ($4.9M vs $5.5M, p = 0.756), or baseline BVR management scores (2.52 vs 2.55, p = 0.859).Observational Study Economics (general)Hawthorne Effect Control via Diagnostic-Only Counterfactual DesignControl plants achieved only a 12 percentage point increase in management practice adoption (versus 37.8 percentage points in treatment plants) and exhibited no significant reduction in quality defects or major productivity gains, confirming that observer presence alone did not drive performance improvements.RCT Economics (general)Community Incentive and Distance Instrumental Variable MethodThe first-stage regression predicting the proportion of village members learning HIV results yields a strong F-statistic of 23.98 without controls, with an average of 72.3% of village members learning test results (SD = 0.186).RCT EducationIntent-to-Treat (ITT) Reduced-Form Effect EstimationThe intent-to-treat reduced-form estimate yielded a coefficient of ~0.280 to 0.326, which reflected the true treatment impact (~0.955) diluted by an overall compliance rate of approximately 29.3%.RCT Methods & evidenceModular Unbundling of Financial Education ComponentsHighlights that traditional aggregate training evaluations obscure underlying mechanisms, recommending cross-randomization of sub-modules to isolate distinct cognitive and behavioral channels.Expert Theory Methods & evidenceMulti-Trait Intervention DecouplingPatience training alone produced no significant effect on gritty task choices or perseverance after failure, whereas standalone grit training in Sample B replicated the full magnitude of treatment effects observed in Sample A's combined intervention (+19.1 vs +14.3 percentage point increase in week-ahead task commitment).RCT Economics (general)Non-Reallocation Resource IsolationZero observed instances of teacher or student reassignment across standards occurred because automatic promotion rules and fixed classroom counts removed principal discretion, ensuring control grades remained valid comparison groups.Observational Study EducationWithin-School Exchangeable Rosters and Randomization Blocks668 randomization blocks were successfully formed across 284 schools. Standard deviation of baseline student sorting across classrooms within these blocks was 0.382 to 0.520 prior to randomization, demonstrating that blocked randomization successfully eliminated substantial pre-existing within-school student sorting.RCT Policy & public sectorRegional Administrative Enforcement VarianceMeeting intensity reached ~0.4 (once every 2.5 weeks) in Storstrøm compared to ~0.3 (once every 3 weeks) in Southern Jutland against a weekly protocol target, yielding distinct meeting risk coefficients (0.47 in Storstrøm vs 2.30 in Southern Jutland).RCT Economics (general)Side-Payment Neutralization ProtocolGuaranteed pre-task bonus disbursement successfully decoupled referral task motivation from referrer incentives, isolating pure peer screening from candidate effort responses.RCT Methods & evidenceSingle-Industry Sectoral Standardisation in Enterprise RCTsConcentrating on a single trade allowed four business consultants to deliver 1,200 hours of sector-specific coaching (averaging 10 hours per tailor), eliminating cross-sector noise and permitting precise tracking of 35 tailoring-specific operational practices over eight survey rounds.RCT Economics (general)Small-Sample Large-T Econometric Experimental DesignIntention-To-Treat (ITT) permutation tests demonstrated statistically significant reductions in quality defects (p = 0.001) and output increases (p = 0.026), proving that high-frequency weekly panel data compensates for small cross-sectional sample size.RCT Methods & evidenceStaggered Treatment Activation ProtocolEstablished a uniform 5-week pre-treatment baseline window per respondent, enabling precise subsample categorization between low and high pre-treatment remitters.RCT Methods & evidenceStratified Cluster Randomization DesignStratification achieved complete baseline balance across treatment and comparison groups, keeping all initial pretest score differences below 0.10 standard deviations.RCT Methods & evidenceWithin-Firm Spillover Dilution ControlRemoving multi-establishment corporate branches prevented internal information spillovers, maintaining orthogonal treatment variation across 7,438 independent establishments.RCT Methods & evidenceWorkplace Batching and Peer Isolation ProtocolControl group workers showed zero output decline on Day 9 after witnessing Wave A treatment workers receive early cash payouts, confirming the absence of relative fairness spillover.RCT Methods & evidenceWorst-Case Variance Bounded SamplingSetting lambda = 0.00125 guarantees a worst-case standard error of 0.05 for treatment contrasts and a statistical power >= 0.80 for detecting effect sizes of 0.124 across N = 4,000 participants, enforcing a minimum assignment probability floor of 0.05 per treatment arm.Expert Theory