期刊论文详细信息
PLoS One | |
P-curve wonât do your laundry, but it will distinguish replicable from non-replicable findings in observational research: Comment on Bruns & Ioannidis (2016) | |
Uri Simonsohn1  Leif D. Nelson2  Joseph P. Simmons3  | |
[1]Behavioral Science, ESADE Business School, Ramon Llull University, Barcelona, Spain | |
[2]Marketing Department, Haas School of Business, University of California-Berkeley, Berkeley, California, United States of America | |
[3]Operations, Information and Decisions department, The Wharton School, University of Pennsylvania, Pennsylvania, United States of America | |
[4]Public Library of Science, UNITED KINGDOM | |
DOI : 10.1371/journal.pone.0213454 | |
学科分类:医学(综合) | |
来源: Public Library of Science | |
【 摘 要 】
p-curve, the distribution of significant p-values, can be analyzed to assess if the findings have evidential value, whether p-hacking and file-drawering can be ruled out as the sole explanations for them. Bruns and Ioannidis (2016) have proposed p-curve cannot examine evidential value with observational data. Their discussion confuses false-positive findings with confounded ones, failing to distinguish correlation from causation. We demonstrate this important distinction by showing that a confounded but real, hence replicable association, gun ownership and number of sexual partners, leads to a right-skewed p-curve, while a false-positive one, respondent ID number and trust in the supreme court, leads to a flat p-curve. P-curve can distinguish between replicable and non-replicable findings. The observational nature of the data is not consequential.【 授权许可】
CC BY
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO201910252970238ZK.pdf | 570KB | download |