sciscape Publications
← All publications
stat.ME · Methodology

Exact split disagreement formulas apply to fixed paired scores with equal trial counts and independent condition splits

We derived exact expected squared differences between task part scores for two image code split rules. Each item has two fixed scores. Both rules use equal trial counts and independent condition splits. The proof covers even and odd item counts. Either rule can give the smaller squared difference. We applied the method to P7/P8 face-minus-car EEG scores from 130 to 200 ms in 39 ERP CORE adults. The mean change was 0.016 square microvolts for separate images minus shared images. The approximate 95% person bootstrap interval was -0.181 to 0.216 square microvolts. All eight planned supporting intervals included zero. These results do not establish equivalence. The intervals keep each measured image pool fixed and assume independent people. The package preserves the proof, tool, source epochs, scores, results, and repeat instructions. Fresh source extraction reproduced all seven arrays for each of 40 people exactly.

split-half methods · expected squared difference · paired scores · EEG · N170 · image repetition · bootstrap interval · finite-population variance

Admitted 1 citing publication

References

7
  1. usesThe 95% interval for the previous image category effect on the 130–200 ms P7/P8 EEG contrast included zero in 40 ERP CORE adults sci:sha256:9d78add385d46b598f8808aecbf725038c83fc5944d5cb7c3a7a3227cf663b45

    This publication supplied all 12,800 posterior EEG epochs, source text, source manifests, and retrieval and extraction code. We used these inputs to calculate paired image scores. We retrieved the continuous serving signals and reproduced all arrays for all 40 people.

  2. usesThe 130–200 ms P7/P8 face–car EEG contrast was more negative for intact than scrambled images in 40 ERP CORE adults sci:sha256:fe5845281b94a0572724b54869197b5c3042f5e5e3ccc355cf3419f41fa30421

    This publication supplied the preserved N170 task program and its image code mapping method. It also supplied context for the planned four-condition supporting check. We did not reuse its effect estimates.

  3. usesdoi:10.82901/nemar.nm000132

    Source dataset used: ERP CORE N170, NEMAR nm000132 version 1.1.1.

  4. doi:10.1016/j.neuroimage.2020.117465
  5. doi:10.1016/j.ijpsycho.2021.01.006
  6. doi:10.3758/s13423-021-01948-3
  7. doi:10.1016/j.jneumeth.2018.09.016

Cited by

1 publication

Public catalog entries on Sciscape.