Uri Simonsohn
Ramon Llull University
Hindsight biasStatisticsBehavioral economicsPositive psychologyReplication (statistics)EconometricsPsychologyActuarial scienceEconomicsCommon value auctionSet (psychology)MicroeconomicsCognitive psychologyCognitive scienceData scienceValue (mathematics)P-hackingSimilarity (psychology)EgotismPublication biasZero (linguistics)ReplicateCurve analysisExperimental researchMathematicsComputer sciencePublicationSocial psychologyStatistical hypothesis testingSpurious relationship
99Publications
38H-index
9,456Citations
Publications 75
Newest
#1Joseph P. Simmons (UPenn: University of Pennsylvania)H-Index: 31
#2Leif D. Nelson (University of California, Berkeley)H-Index: 38
Last. Uri Simonsohn (Ramon Llull University)H-Index: 38
view all 3 authors...
2 CitationsSource
#1Joseph P. Simmons (UPenn: University of Pennsylvania)H-Index: 31
#2Leif D. Nelson (University of California, Berkeley)H-Index: 38
Last. Uri Simonsohn (Ramon Llull University)H-Index: 38
view all 3 authors...
Source
#1Robert Mislavsky (Johns Hopkins University)H-Index: 3
#2Berkeley J. Dietvorst (U of C: University of Chicago)H-Index: 7
Last. Uri Simonsohn (Ramon Llull University)H-Index: 38
view all 3 authors...
Recent public backlash to corporate experimentation was likely caused by the policies the experiments contained rather than a more general “experiment aversion.”
4 CitationsSource
#1Uri Simonsohn (Ramon Llull University)H-Index: 38
#2Joseph P. Simmons (UPenn: University of Pennsylvania)H-Index: 31
Last. Leif D. Nelson (University of California, Berkeley)H-Index: 38
view all 3 authors...
1 CitationsSource
#1Uri Simonsohn (Ramon Llull University)H-Index: 38
#2Joseph P. Simmons (UPenn: University of Pennsylvania)H-Index: 31
Last. Leif D. Nelson (University of California, Berkeley)H-Index: 38
view all 3 authors...
Empirical results hinge on analytical decisions that are defensible, arbitrary and motivated. These decisions probably introduce bias (towards the narrative put forward by the authors), and they certainly involve variability not reflected by standard errors. To address this source of noise and bias, we introduce specification curve analysis, which consists of three steps: (1) identifying the set of theoretically justified, statistically valid and non-redundant specifications; (2) displaying the ...
10 CitationsSource
#1Robert Mislavsky (Johns Hopkins University)H-Index: 3
#2Berkeley J. Dietvorst (U of C: University of Chicago)H-Index: 7
Last. Uri Simonsohn (Ramon Llull University)H-Index: 38
view all 3 authors...
Meyer et al. (1) propose that people object to “experiments that compare two unobjectionable policies” (their title). In our own work (2), we arrive at the opposite conclusion: People “don’t dislike a corporate experiment more than they dislike its worst condition” (our title). In this letter we reanalyze the 7 studies in table 1 of ref. 1, for they most closely resemble ours. We conclude that the evidence for experiment aversion is caused by a statistical artifact. In those studies, 3 separate ...
2 CitationsSource
#1Uri SimonsohnH-Index: 38
Last. Robert MislavskyH-Index: 3
view all 3 authors...
Source
#1Joachim Vosgerau (Bocconi University)H-Index: 15
#2Uri Simonsohn (Ramon Llull University)H-Index: 38
Last. Joseph P. Simmons (UPenn: University of Pennsylvania)H-Index: 31
view all 4 authors...
: Several researchers have relied on, or advocated for, internal meta-analysis, which involves statistically aggregating multiple studies in a paper to assess their overall evidential value. Advocates of internal meta-analysis argue that it provides an efficient approach to increasing statistical power and solving the file-drawer problem. Here we show that the validity of internal meta-analysis rests on the assumption that no studies or analyses were selectively reported. That is, the technique ...
15 CitationsSource
#1Berkeley J. Dietvorst (U of C: University of Chicago)H-Index: 7
#2Uri Simonsohn (Ramon Llull University)H-Index: 38
: Abundant research has shown that people fail to disregard to-be-ignored information (e.g., hindsight bias, curse of knowledge), which has contributed to the popular notion that people are unwillingly and unconsciously affected by information. Here we provide evidence that, instead, people simply do not want to ignore such information. The findings: In Studies 1 and 2, the majority of participants explicitly indicated a desire to use to-be-ignored information in classic paradigms. In Study 3, t...
4 CitationsSource
#1Uri Simonsohn (Ramon Llull University)H-Index: 38
#2Leif D. Nelson (University of California, Berkeley)H-Index: 38
Last. Joseph P. Simmons (UPenn: University of Pennsylvania)H-Index: 31
view all 3 authors...
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 confou...
8 CitationsSource