phacking (Q80326): Difference between revisions
From MaRDI portal
Removed claim: imports (P585): metabias (Q76914) |
Added link to MaRDI item. |
||||||||||||||
(16 intermediate revisions by one other user not shown) | |||||||||||||||
Property / last update | |||||||||||||||
| |||||||||||||||
Property / last update: 20 January 2023 / rank | |||||||||||||||
Property / maintained by | |||||||||||||||
Property / maintained by: Mika Braginsky / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: methods / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: stats / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: stats4 / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: dplyr / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: metafor / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: purrr / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: rlang / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: truncnorm / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: Rcpp / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: RcppParallel / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: Rdpack / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: rstan / rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: rstantools / rank | |||||||||||||||
Property / cites work | |||||||||||||||
Property / cites work: Sensitivity analysis for p-hacking in meta-analyses / rank | |||||||||||||||
Property / software version identifier | |||||||||||||||
0.0.1 | |||||||||||||||
Property / software version identifier: 0.0.1 / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / software version identifier: 0.0.1 / qualifier | |||||||||||||||
publication date: 21 June 2022
| |||||||||||||||
Property / software version identifier | |||||||||||||||
0.2.1 | |||||||||||||||
Property / software version identifier: 0.2.1 / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / software version identifier: 0.2.1 / qualifier | |||||||||||||||
publication date: 17 July 2023
| |||||||||||||||
Property / last update | |||||||||||||||
17 July 2023
| |||||||||||||||
Property / last update: 17 July 2023 / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / maintained by | |||||||||||||||
Property / maintained by: Peter Solymos / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / description | |||||||||||||||
Fits right-truncated meta-analysis (RTMA), a bias correction for the joint effects of p-hacking (i.e., manipulation of results within studies to obtain significant, positive estimates) and traditional publication bias (i.e., the selective publication of studies with significant, positive results) in meta-analyses [see Mathur MB (2022). "Sensitivity analysis for p-hacking in meta-analyses." <doi:10.31219/osf.io/ezjsx>.]. Unlike publication bias alone, p-hacking that favors significant, positive results (termed "affirmative") can distort the distribution of affirmative results. To bias-correct results from affirmative studies would require strong assumptions on the exact nature of p-hacking. In contrast, joint p-hacking and publication bias do not distort the distribution of published nonaffirmative results when there is stringent p-hacking (e.g., investigators who hack always eventually obtain an affirmative result) or when there is stringent publication bias (e.g., nonaffirmative results from hacked studies are never published). This means that any published nonaffirmative results are from unhacked studies. Under these assumptions, RTMA involves analyzing only the published nonaffirmative results to essentially impute the full underlying distribution of all results prior to selection due to p-hacking and/or publication bias. The package also provides diagnostic plots described in Mathur (2022). | |||||||||||||||
Property / description: Fits right-truncated meta-analysis (RTMA), a bias correction for the joint effects of p-hacking (i.e., manipulation of results within studies to obtain significant, positive estimates) and traditional publication bias (i.e., the selective publication of studies with significant, positive results) in meta-analyses [see Mathur MB (2022). "Sensitivity analysis for p-hacking in meta-analyses." <doi:10.31219/osf.io/ezjsx>.]. Unlike publication bias alone, p-hacking that favors significant, positive results (termed "affirmative") can distort the distribution of affirmative results. To bias-correct results from affirmative studies would require strong assumptions on the exact nature of p-hacking. In contrast, joint p-hacking and publication bias do not distort the distribution of published nonaffirmative results when there is stringent p-hacking (e.g., investigators who hack always eventually obtain an affirmative result) or when there is stringent publication bias (e.g., nonaffirmative results from hacked studies are never published). This means that any published nonaffirmative results are from unhacked studies. Under these assumptions, RTMA involves analyzing only the published nonaffirmative results to essentially impute the full underlying distribution of all results prior to selection due to p-hacking and/or publication bias. The package also provides diagnostic plots described in Mathur (2022). / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / author | |||||||||||||||
Property / author: Maya Mathur / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / author | |||||||||||||||
Property / author: Mika Braginsky / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / copyright license | |||||||||||||||
Property / copyright license: MIT license / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / copyright license | |||||||||||||||
Property / copyright license: File License / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / copyright license: File License / qualifier | |||||||||||||||
Property / depends on software | |||||||||||||||
Property / depends on software: R / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / depends on software: R / qualifier | |||||||||||||||
software version identifier: ≥ 4.1.0 | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: dplyr / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: ggplot2 / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: metabias / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: metafor / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: methods / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: purrr / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: rlang / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: stats / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: stats4 / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: truncnorm / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: Rcpp / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports: Rcpp / qualifier | |||||||||||||||
software version identifier: ≥ 0.12.0 | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: RcppParallel / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports: RcppParallel / qualifier | |||||||||||||||
software version identifier: ≥ 5.0.1 | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: Rdpack / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: rstan / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports: rstan / qualifier | |||||||||||||||
software version identifier: ≥ 2.18.1 | |||||||||||||||
Property / imports | |||||||||||||||
Property / imports: rstantools / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / imports: rstantools / qualifier | |||||||||||||||
software version identifier: ≥ 2.2.0 | |||||||||||||||
Property / cites work | |||||||||||||||
Property / cites work: Sensitivity analysis for p-hacking in meta-analyses / rank | |||||||||||||||
Normal rank | |||||||||||||||
Property / MaRDI profile type | |||||||||||||||
Property / MaRDI profile type: MaRDI software profile / rank | |||||||||||||||
Normal rank | |||||||||||||||
links / mardi / name | links / mardi / name | ||||||||||||||
Latest revision as of 19:55, 12 March 2024
Sensitivity Analysis for p-Hacking in Meta-Analyses
Language | Label | Description | Also known as |
---|---|---|---|
English | phacking |
Sensitivity Analysis for p-Hacking in Meta-Analyses |
Statements
17 July 2023
0 references
Fits right-truncated meta-analysis (RTMA), a bias correction for the joint effects of p-hacking (i.e., manipulation of results within studies to obtain significant, positive estimates) and traditional publication bias (i.e., the selective publication of studies with significant, positive results) in meta-analyses [see Mathur MB (2022). "Sensitivity analysis for p-hacking in meta-analyses." <doi:10.31219/osf.io/ezjsx>.]. Unlike publication bias alone, p-hacking that favors significant, positive results (termed "affirmative") can distort the distribution of affirmative results. To bias-correct results from affirmative studies would require strong assumptions on the exact nature of p-hacking. In contrast, joint p-hacking and publication bias do not distort the distribution of published nonaffirmative results when there is stringent p-hacking (e.g., investigators who hack always eventually obtain an affirmative result) or when there is stringent publication bias (e.g., nonaffirmative results from hacked studies are never published). This means that any published nonaffirmative results are from unhacked studies. Under these assumptions, RTMA involves analyzing only the published nonaffirmative results to essentially impute the full underlying distribution of all results prior to selection due to p-hacking and/or publication bias. The package also provides diagnostic plots described in Mathur (2022).
0 references