The 95% interval included zero for extra MMN voltage disagreement between early and late halves in 15 NEMAR 250 Hz ds005429 records

We tested early and late fixed MMN voltage scores in all 15 healthy participants in the Optimum1 task of ds005429. We used the public NEMAR 250 Hz serving copy. The random reference kept physical sound counts fixed and used an exact finite-pool expectation. Mean extra squared disagreement was 0.5034 µV²; its whole-person bootstrap 95% interval was [-0.1860, 1.2629] µV². The primary 95% interval included zero. This test did not establish extra disagreement between the early and late scores. It also did not establish that the two split methods are equivalent. All six fixed check intervals included zero. The package preserves source records, code, 22,080 post-initial epochs with two references, trial membership, bootstrap draws, and independent checks. Corrected event samples and eye-channel scale were checked. This test concerns one contrast within a recording. It does not establish clinical validity or between-visit reliability. Full native EEG bytes were not verified.

mismatch negativity · EEG · within-person reliability · finite-population sampling · bootstrap · auditory oddball · split-half comparison