Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

Effect 1709: ML5 Risen RP:P replication p = .02, not p > .05

Aperta
  • Qualcosa non va?
#145 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
2/5
Tempo stimato
1-3 ore
Idoneità per principianti
50/100
Tipo di issue
Bug
Chiarezza
Abbastanza chiara
Stato di attività
Attiva
Ambito
data

Direzione di ricerca

Find the record with fred_id ManyLabs5_1g (effect 1709) in the FReD data and check its pval_type_r and pval_value_r fields against Table 4 of Ebersole et al. (2020). The proposed change is to set the type to e (=) and the value to 0.02 while keeping r = −.04. Done means the record matches the cited table, and the maintainers confirm the inequality-versus-equality coding convention first, since the thread has no reply yet.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

Effect 1709 (fred_id = ManyLabs5_1g) records pval_type_r = g (>), pval_value_r = 0.05, despite a published replication p-value of .02 for this arm.

The record identifies the ML5 RP:P-protocol replication of Risen & Gilovich (2008), original Study 6: study_r = 7_RPP, n_r = 2811, replication DOI 10.1177/2515245920958687. Its recorded es_type_r = r, es_value_r = -0.04 agrees with the overview's tables.

Source evidence in Ebersole et al. (2020):

  • Table 3, p. 11: ML5 RP:P-protocol arm, N = 2,811, r = −.04, 95% CI [−.08, −.01]. The original effect is r = +.19.
  • Table 4, p. 14: Risen & Gilovich → RP:P protocol, k = 1, r = −.04 [−.08, −.01], p = .02 in the p-value column. The adjacent P_orig column also has .02 but represents a different metric.
  • The all-protocols and revised-protocol results have p = .20 and .87, respectively; neither is the endpoint for effect 1709.

Two independent source coders (Opus and a blind Codex agent) agreed on N, estimate, CI, p-value, and direction. I also checked the Table 4 image. The printed p-value is rounded to two decimal places; sidedness is inferred from the estimate and zero-excluding 95% CI rather than explicitly labelled in the table.

Please change the replication p-value to pval_type_r = e (=), pval_value_r = 0.02, retaining r = −.04. This makes significance against zero true under a two-sided p < .05 endpoint. It remains unsuccessful in reproducing the original direction, so reported_success = failed need not change.

The overview's narrative on pp. 10–11 says none of the RP:P-protocol replications were significant, which conflicts with this negative significant numerical result if read as significance against zero. The paper defines successful replication using significance in the original direction on p. 8. That may explain the narrative, but the reason for FReD's inequality coding is unconfirmed. Footnote 5 also distinguishes individual-report estimators from the overview meta-analyses; the recommendation here is specific to the cited overview and the matching N and effect estimate.

Lingua principale
HTML
Stelle
1
Fork
0
Nessuna PR unita negli ultimi 30g

Preparare l'ambiente

Questo progetto non fornisce container di sviluppo, Dockerfile né guida per i contributori, quindi l'ambiente è a tuo carico: parti dal suo README e consulta la nostra guida al primo contributo per i passaggi generali.

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di forrtproject/fred-data

Tutte le issue di forrtproject/fred-data

Issue simili

Altre issue su Data Engineering

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.