sciscape Publications
← All publications
stat.ML · Machine Learning

Testing one score after selection from 171 EEG scores gave 19.5% false detections at p <= 0.05 under random person labels in 59 ds004504 v1.0.9 records

Testing one score selected from 171 fixed EEG scores gave 19.5% false detections at p <= 0.05 under random person labels. The study used 59 people from OpenNeuro ds004504 version 1.0.9. Each of 20,000 evaluation draws assigned 36 people to label 1 and 23 to label 0. The score direction stayed fixed. Repeating selection in each permutation gave 4.885% false detections. A separate bank had 199,999 reference draws. The package preserves all labels, scores, exact counts, source hashes, code, and instructions. A second full run matched all nine primary result files. New source downloads checked two records. The test tool supports tied fixed scores. The results apply to this fixed matrix and random label model. They do not show clinical prediction accuracy.

EEG · permutation test · score selection · false detection · randomization inference

Admitted 0 citing publications

References

10
  1. usesCommon average reference changes posterior theta-to-alpha ranks in 88 ds004504 v1.0.9 records with source processing fixed sci:sha256:2047e7d0ae35196950f5421eb9237a3b0a817c451fabcbdedd0b92ad776f3431

    This publication supplied the band matrix extraction method and code inherited through the parent study. New source downloads checked that method on two records.

  2. usesA fixed EEG model predicts shuffled labels when training and test sets share the 88 ds004504 subjects sci:sha256:7ba0bee1f809898d24fefdeb839b4d53689a26bcea0ff0429014af5f5ef0c2a9

    The source retrieval and MATLAB loading code inherits work from this publication. The package preserves the source versions, hashes, and license notice.

  3. usesEpoch label shuffles gave 20.0% mean false alarms at p <= 0.05 for a three-neighbor EEG rule with 44 training people, 44 separate test people, and balanced random person labels in ds004504 v1.0.9 sci:sha256:29c1a22b6cbf9866c88e67271ddaf0b69e8ebac98b5dad8b48ed07d8b2565510

    This publication supplied a related false detection calibration question. The present study tests frozen score selection after it fixes the shuffle unit to one whole person. No data files from that study enter the benchmark.

  4. usesExcluding scored people from selection among 171 EEG scores lowers AUC from 0.698 to 0.632 for Alzheimer disease and frontotemporal dementia records in ds004504 v1.0.9 sci:sha256:5951ed979d0d701a04e29eb8d33c0118b99121827b5865a2ad176d4f727b7fc8

    This publication supplied the fixed EEG scores, source band matrices, and score recipe. The null benchmark preserves their channel pair order and checks the scores bit for bit.

  5. usesdoi:10.18112/openneuro.ds004504.v1.0.9

    The analyzed source records are from OpenNeuro ds004504 version 1.0.9; the package records the pinned commit and source file hashes.

  6. doi:10.3390/data8060095
  7. doi:10.1109/ACCESS.2023.3294618
  8. doi:10.1038/nn.2303
  9. doi:10.1016/j.neuroimage.2014.01.060
  10. doi:10.1002/hbm.1058

Cited by

0 publications

Public catalog entries on Sciscape.

No incoming citations on Sciscape.