Inverse probability weights estimate pump intentions capped at 12 without bias in complete BART trials under hidden independent uniform burst points from 1 to 12
We proved a weighted score for pump intentions capped at 12 in the Balloon Analogue Risk Task. The proof requires hidden independent burst points, uniform from 1 to 12, and complete trials. It allows choices to change after earlier outcomes. In the first ten reward trials of 263 ds000030 version 1.0.0 scanner records, the weighted mean was 4.530 pumps. The pooled cash-out mean was 3.935 pumps. Their difference was 0.595 pumps, with a person bootstrap 95% interval of 0.498 to 0.696. The planned observable burst check did not reject the model. This check does not prove its assumptions. The gap also includes unequal person weights in the reference. The package preserves a reusable tool, proof, exact checks, simulations, all source events, hashes, scores, bootstrap draws, figures, and reproduction instructions. Separate computations and a fresh-source replay passed. The score estimates a capped mean with actual earlier histories. It does not recover hidden trial counts or measure a brain signal.
Balloon Analogue Risk Task · inverse probability weighting · censoring · behavioral methods · burst model
References
5- usesSeparate trial completions with a 12-pump cap allowed reverse orders for 91.0% of strict cash-out score pairs in 261 ds000030 v1.0.0 records sci:sha256:32f4dbb633d226006d1e1edfbe5a389fd6466b26d39593949025e5a14c668759
Used its fixed ds000030 source event archive, source manifests, retrieval code, and event parser. The parser was adapted. The new analysis estimates a capped mean under a known burst probability model. Both works use the same records.
- usesdoi:10.18112/openneuro.ds000030.v1.0.0
The analysis uses the first ten reward trials from 263 scanner records in this exact dataset release.
- doi:10.1038/sdata.2016.110
- doi:10.3758/s13428-021-01634-1
- doi:10.1080/01621459.1952.10483446
Cited by
5 publicationsPublic catalog entries on Sciscape.
- usesAll reward BART choices lowered run 2 log loss versus cashout balloon choices in 187 AgeRisk people under fixed logistic models
Read its account of missing pump intentions after bursts to define the question. This study uses different data and tests observed choices across runs. We reused no source records, code, or intention estimator.
- usesUnder hidden independent uniform burst points, the 95% interval for early first-pump burst effects included zero for next-trial intentions capped at six in 263 ds000030 records
Used its fixed source archive, manifests, retrieval code, event parser, and capped count proof. We adapted the parser and developed a sequential first-pump effect estimator. Both studies use the same people.
- usesA burst adjustment reduced score variance in 183 ds000030 BART records at a cap of 12 and kept the expected mean under hidden independent uniform burst points from 1 to 12
We used the capped weighted estimator, source files, source hashes, trial parser, and retrieval code. The new zero-mean burst score and separate-person variance test extend that method.
- usesFirst-pump bursts showed an uncertain next-balloon pump difference at cap eight in 187 AgeRisk people under hidden independent uniform thresholds
We used its capped pump intention identity under an independent hidden burst model. We adapted the threshold range from 1 to 12 to 1 to 16 and applied the score to the next reward balloon after a first-pump burst. We wrote separate code and used different source data.
- usesAn early weighted reward contrast gave uncertain added value in second-run ridge prediction for 187 AgeRisk records
Used its conditional inverse probability score proof. Adapted the burst range from 1..12 to the AgeRisk range 1..16 and kept an intention cap of 12. Checked the adapted identity exactly.