Samuel Pawel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Samuel Pawel has a total of 869 co-authors. Here are the top co-authors by number of shared publications:
- Leonhard Held
Epidemiology Biostatistics and Prevention Institute (EBPI) Center for Reproducible Science and Research Synthesis (CRS University of Zurich
23 shared publications - František Bartoš
University of Amsterdam
10 shared publications - Eric-Jan Wagenmakers
Department of Psychology, University of Amsterdam, Amsterdam, Netherlands
8 shared publications - Rachel Heyard
Center for Reproducible Science and Research Synthesis, Epidemiology, Biostatistics and Prevention Institute, University of Zurich
8 shared publications - Kimberley Elaine Wever
Department of Anesthesiology, Pain and Palliative Medicine, Radboud university medical center
7 shared publications Leonhard Held
Epidemiology, Biostatistics and Prevention Institute, Center for Reproducible Science, University of Zurich
6 shared publications
Latest Publications
- Open Access
- 22 October 2026
- Published by Center for Open Science in PsyArXiv
The Prevalence of Bayesian Inference, Preregistration, and Open Data in Psychology, 2004-2024
Psychology has undergone substantial methodological changes in the past two decades. We tracked the adoption of Bayesian inference and two open science practices across 28,738 articles from six ‘top-tier’ (15,634 articles) and six ‘mid-tier’ (13,104 articles) psychology journals in 2004–2024. In ‘top-tier’ journals, human (50%) and LLM-assisted (50%) full-text coding revealed that in 2024, 26% of articles reported a Bayesian analysis, 41% included a preregistration, and 73% provided open data. In ‘mid-tier’ journals, LLM coding showed corresponding rates of 16%, 18%, and 40%. From 2004 to 2012, these practices were virtually nonexistent. Bayesian logistic growth modeling suggests further increases, although their extent remains uncertain. Mixed-effects models became more prevalent, software reporting improved, with greater use of R and less reliance on SPSS, but estimation-focused (vs. hypothesis-testing-focused) reporting showed only modest gains. Despite heterogeneity across journals, psychology articles published in 2024 differ markedly from those published only a decade earlier.
- 22 October 2026
- Published by Center for Open Science in PsyArXiv
Open AccessThe Prevalence of Bayesian Inference, Preregistration, and Open Data in Psychology, 2004-2024
Psychology has undergone substantial methodological changes in the past two decades. We tracked the adoption of Bayesian inference and two open science practices across 28,738 articles from six ‘top-tier’ (15,634 articles) and six ‘mid-tier’ (13,104 articles) psychology journals in 2004–2024. In ‘top-tier’ journals, human (50%) and LLM-assisted (50%) full-text coding revealed that in 2024, 26% of articles reported a Bayesian analysis, 41% included a preregistration, and 73% provided open data. In ‘mid-tier’ journals, LLM coding showed corresponding rates of 16%, 18%, and 40%. From 2004 to 2012, these practices were virtually nonexistent. Bayesian logistic growth modeling suggests further increases, although their extent remains uncertain. Mixed-effects models became more prevalent, software reporting improved, with greater use of R and less reliance on SPSS, but estimation-focused (vs. hypothesis-testing-focused) reporting showed only modest gains. Despite heterogeneity across journals, psychology articles published in 2024 differ markedly from those published only a decade earlier.
- Open Access
- 13 September 2026
- Published by Center for Open Science in PsyArXiv
On Power and Sample Size Calculation for Bayes Factors: A Tutorial on the BayesPower Package
Power analyses and sample size justifications are increasingly encouraged and required by funding agencies across disciplines such as psychology and the biomedical sciences, highlighting the growing need for accessible sample size determination tools. The present article introduces BayesPower, an R package for conducting sample size determination, power calculation, and Bayes factor calculation in Bayesian hypothesis testing without simulation. The package supports a wide range of statistical tests commonly encountered in the social, behavioral, and biomedical sciences, including standardized mean differences, correlations, linear regression and analysis of variance, and tests for one and two proportions. In addition to the traditional comparison of a point-null hypothesis with acomposite alternative hypothesis, BayesPower supports sample size planning for interval-hypothesis Bayes factors (i.e., equivalence testing). For most testing problems, sample size and power are returned almost instantly, enabling researchers to design informative and efficient studies rapidly. To reach a broader audience, the package provides a user-friendly Shiny application for researchers with little or no experience coding in R, in addition to command-line functions for more experienced users. The use of the software is illustrated through five empirical examples.
- 13 September 2026
- Published by Center for Open Science in PsyArXiv
Open AccessOn Power and Sample Size Calculation for Bayes Factors: A Tutorial on the BayesPower Package
Power analyses and sample size justifications are increasingly encouraged and required by funding agencies across disciplines such as psychology and the biomedical sciences, highlighting the growing need for accessible sample size determination tools. The present article introduces BayesPower, an R package for conducting sample size determination, power calculation, and Bayes factor calculation in Bayesian hypothesis testing without simulation. The package supports a wide range of statistical tests commonly encountered in the social, behavioral, and biomedical sciences, including standardized mean differences, correlations, linear regression and analysis of variance, and tests for one and two proportions. In addition to the traditional comparison of a point-null hypothesis with acomposite alternative hypothesis, BayesPower supports sample size planning for interval-hypothesis Bayes factors (i.e., equivalence testing). For most testing problems, sample size and power are returned almost instantly, enabling researchers to design informative and efficient studies rapidly. To reach a broader audience, the package provides a user-friendly Shiny application for researchers with little or no experience coding in R, in addition to command-line functions for more experienced users. The use of the software is illustrated through five empirical examples.
- Open Access
- 22 August 2026
- Published by Elsevier in Clinical Radiology
- Vol. 102, 107461
Single-slice quantitative magnetic resonance imaging (MRI) of the thigh for differential assessment of fasting-related body composition changes
- 22 August 2026
- Published by Elsevier in Clinical Radiology
- Vol. 102, 107461
Open AccessSingle-slice quantitative magnetic resonance imaging (MRI) of the thigh for differential assessment of fasting-related body composition changes
- Open Access
- 7 August 2026
- Published by eLife Sciences Publications, Ltd in eLife
- Vol. 15
Evaluating the applicability of replication success metrics in animal-to-human translation: A simulation study
Translation failure, in which promising animal study results cannot be reproduced in human trials, is a challenge in biomedical research. Metrics for replication success are widely used to evaluate reproducibility, that is the extent to which the results of a study agree with those of replication studies. The relevance of these metrics in assessing animal-to-human translation success (or failure) is unclear. We conducted a simulation study to examine whether these metrics can quantify translation success, and how their performance varies under different conditions. Using parameters from a meta-analysis on prenatal amino acid supplementation and maternal blood pressure, we simulated animal and human studies under 648 scenarios, varying effect sizes, heterogeneity, animal sample sizes, and number of pooled animal studies. Nine metrics were assessed, namely the two-trials rule, meta-analysis, replication Bayes factor, unweighted and weighted Edgington’s methods, golden skeptical p-value, and three versions of controlled skeptical p-value. Most metrics, except meta-analysis and replication Bayes factor, controlled false positive rates under no heterogeneity, but became liberal as heterogeneity increased, particularly between human studies. Translation power (i.e. the probability of true positive translation success) was constrained by the weaker evidence of the two findings; for example, small sample size in the animal studies resulted in lower translation power. The metric based on meta-analysis frequently indicated success when either of the species found strong evidence, while skeptical p-values were more conservative. The skeptical p-value that controls overall type-one error and the weighted version of Edgington’s method performed relatively consistently across scenarios. However, no metric was uniformly optimal. Metrics developed for replication studies can inform assessments of translation, but their utility depends on the underlying evidence and assumptions. Using multiple metrics in combination, with attention to their strengths and limitations, is recommended for evaluating the translation of animal findings to human outcomes.
- 7 August 2026
- Published by eLife Sciences Publications, Ltd in eLife
- Vol. 15
Open AccessEvaluating the applicability of replication success metrics in animal-to-human translation: A simulation study
Translation failure, in which promising animal study results cannot be reproduced in human trials, is a challenge in biomedical research. Metrics for replication success are widely used to evaluate reproducibility, that is the extent to which the results of a study agree with those of replication studies. The relevance of these metrics in assessing animal-to-human translation success (or failure) is unclear. We conducted a simulation study to examine whether these metrics can quantify translation success, and how their performance varies under different conditions. Using parameters from a meta-analysis on prenatal amino acid supplementation and maternal blood pressure, we simulated animal and human studies under 648 scenarios, varying effect sizes, heterogeneity, animal sample sizes, and number of pooled animal studies. Nine metrics were assessed, namely the two-trials rule, meta-analysis, replication Bayes factor, unweighted and weighted Edgington’s methods, golden skeptical p-value, and three versions of controlled skeptical p-value. Most metrics, except meta-analysis and replication Bayes factor, controlled false positive rates under no heterogeneity, but became liberal as heterogeneity increased, particularly between human studies. Translation power (i.e. the probability of true positive translation success) was constrained by the weaker evidence of the two findings; for example, small sample size in the animal studies resulted in lower translation power. The metric based on meta-analysis frequently indicated success when either of the species found strong evidence, while skeptical p-values were more conservative. The skeptical p-value that controls overall type-one error and the weighted version of Edgington’s method performed relatively consistently across scenarios. However, no metric was uniformly optimal. Metrics developed for replication studies can inform assessments of translation, but their utility depends on the underlying evidence and assumptions. Using multiple metrics in combination, with attention to their strengths and limitations, is recommended for evaluating the translation of animal findings to human outcomes.
- Open Access
- 23 July 2026
- Published by eLife Sciences Publications, Ltd in eLife preprints
- Vol. 15
Evaluating the applicability of replication success metrics in animal-to-human translation: A simulation study
Translation failure, in which promising animal study results can not be reproduced in human trials, is a challenge in biomedical research. Metrics for replication success are widely used to evaluate reproducibility, i.e., the extent to which the results of a study agree with those of replication studies. The relevance of these metrics in assessing animal-to-human translation success (or failure) is unclear. We conducted a simulation study to examine whether these metrics can quantify translation success and how their performance varies under different conditions. Using parameters from a meta-analysis on prenatal amino acid supplementation and maternal blood pressure, we simulated animal and human studies under 648 scenarios, varying effect sizes, heterogeneity, animal sample sizes and number of pooled animal studies. Nine metrics were assessed, namely the two-trials rule, meta-analysis, replication Bayes factor, unweighted and weighted Edgington’s methods, golden sceptical p-value and three versions of controlled sceptical p-value. Most metrics, except meta-analysis and replication Bayes factor, controlled false positive rates under no heterogeneity, but became liberal as heterogeneity increased, particularly between human studies. Translation power (i.e., the probability of true positive translation success) was constrained by the weaker evidence of the two findings; e.g., small sample size in the animal studies resulted in lower translation power. The metric based on meta-analysis frequently indicated success when either of the species found strong evidence, while sceptical p-values were more conservative. The sceptical p-value that controls overall type-one error and the weighted version of Edgington’s method performed relatively consistently across scenarios. However, no metric was uniformly optimal. Metrics developed for replication studies can inform assessments of translation, but their utility depends on the underlying evidence and assumptions. Using multiple metrics in combination, with attention to their strengths and limitations, is recommended for evaluating the translation of animal findings to human outcomes.
- 23 July 2026
- Published by eLife Sciences Publications, Ltd in eLife preprints
- Vol. 15
Open AccessEvaluating the applicability of replication success metrics in animal-to-human translation: A simulation study
Translation failure, in which promising animal study results can not be reproduced in human trials, is a challenge in biomedical research. Metrics for replication success are widely used to evaluate reproducibility, i.e., the extent to which the results of a study agree with those of replication studies. The relevance of these metrics in assessing animal-to-human translation success (or failure) is unclear. We conducted a simulation study to examine whether these metrics can quantify translation success and how their performance varies under different conditions. Using parameters from a meta-analysis on prenatal amino acid supplementation and maternal blood pressure, we simulated animal and human studies under 648 scenarios, varying effect sizes, heterogeneity, animal sample sizes and number of pooled animal studies. Nine metrics were assessed, namely the two-trials rule, meta-analysis, replication Bayes factor, unweighted and weighted Edgington’s methods, golden sceptical p-value and three versions of controlled sceptical p-value. Most metrics, except meta-analysis and replication Bayes factor, controlled false positive rates under no heterogeneity, but became liberal as heterogeneity increased, particularly between human studies. Translation power (i.e., the probability of true positive translation success) was constrained by the weaker evidence of the two findings; e.g., small sample size in the animal studies resulted in lower translation power. The metric based on meta-analysis frequently indicated success when either of the species found strong evidence, while sceptical p-values were more conservative. The sceptical p-value that controls overall type-one error and the weighted version of Edgington’s method performed relatively consistently across scenarios. However, no metric was uniformly optimal. Metrics developed for replication studies can inform assessments of translation, but their utility depends on the underlying evidence and assumptions. Using multiple metrics in combination, with attention to their strengths and limitations, is recommended for evaluating the translation of animal findings to human outcomes.
- Open Access
- 3 June 2026
- Published by The Royal Society in Royal Society Open Science
- Vol. 13 (6)
Assessing replication success: a taxonomy and systematic comparison of replication success measures for prospective replications
Replication studies are recognized as essential to the scientific process. Numerous measures have been developed to quantify replication success. Most measures were developed for post hoc replications, in which the primary study has been conducted and sometimes assumed to show a specific result (e.g. statistical significance). Consequently, methodological studies have focused on evaluating replication success measures for those replications. However, recent work emphasizes the value of prospective replications, in which primary and replication studies are planned simultaneously. Such replications allow researchers to control study characteristics and thus investigate which characteristics cause effect heterogeneity. This study provides replication success measures for prospective replications, and guidelines for choosing between them. We present a taxonomy of measures based on research questions they address and evaluate existing frequentist and Bayesian approaches for their applicability to prospective replications. We illustrate their application using an example from social psychology. In simulations, we compare the statistical properties of measures that aim at the same research question. Results indicate that there is almost always a trade-off between error types. Thus, no single measure emerged as always clearly superior. We highlight the assumptions and strengths of each measure and offer recommendations for choosing a measure based on replication goals.
- 3 June 2026
- Published by The Royal Society in Royal Society Open Science
- Vol. 13 (6)
Open AccessAssessing replication success: a taxonomy and systematic comparison of replication success measures for prospective replications
Replication studies are recognized as essential to the scientific process. Numerous measures have been developed to quantify replication success. Most measures were developed for post hoc replications, in which the primary study has been conducted and sometimes assumed to show a specific result (e.g. statistical significance). Consequently, methodological studies have focused on evaluating replication success measures for those replications. However, recent work emphasizes the value of prospective replications, in which primary and replication studies are planned simultaneously. Such replications allow researchers to control study characteristics and thus investigate which characteristics cause effect heterogeneity. This study provides replication success measures for prospective replications, and guidelines for choosing between them. We present a taxonomy of measures based on research questions they address and evaluate existing frequentist and Bayesian approaches for their applicability to prospective replications. We illustrate their application using an example from social psychology. In simulations, we compare the statistical properties of measures that aim at the same research question. Results indicate that there is almost always a trade-off between error types. Thus, no single measure emerged as always clearly superior. We highlight the assumptions and strengths of each measure and offer recommendations for choosing a measure based on replication goals.
- 20 April 2026
- Published by The R Foundation
confMeta: Confidence Curves and P-Value Functions for Meta-Analysis
Provides tools for the combination of individual study results in meta-analyses using 'p-value' functions. Implements various combination methods including those by Fisher, Stouffer, Tippett, Edgington along with weighted generalizations. Contains functionality for the visualization and calculation of confidence curves and drapery plots to summarize evidence across studies.
- 20 April 2026
- Published by The R Foundation
confMeta: Confidence Curves and P-Value Functions for Meta-Analysis
Provides tools for the combination of individual study results in meta-analyses using 'p-value' functions. Implements various combination methods including those by Fisher, Stouffer, Tippett, Edgington along with weighted generalizations. Contains functionality for the visualization and calculation of confidence curves and drapery plots to summarize evidence across studies.
- Top Cited Papers
- 1 April 2026
- Published by Springer Nature in Nature
- Vol. 652 (8108) , 135-142
Investigating the analytical robustness of the social and behavioural sciences
The same dataset can be analysed in different justifiable ways to answer the same research question, potentially challenging the robustness of empirical science1-3. In this crowd initiative, we investigated the degree to which research findings in the social and behavioural sciences are contingent on analysts' choices. We examined a stratified random sample of 100 studies published between 2009 and 2018, in which, for one claim per study, at least five reanalysts independently reanalysed the original data. The statistical appropriateness of the reanalyses was assessed in peer evaluations, and the robustness indicators were inspected along a range of research characteristics and study designs. We found that 34% of the independent reanalyses yielded the same result (within a tolerance region of ±0.05 Cohen's d) as the original report; with a four times broader tolerance region, this indicator increased to 57%. Of the reanalyses conducted, 74% reached the same conclusion as the original investigation, 24% yielded no effects or inconclusive results and 2% reported the opposite effect. This exploratory study indicates that the common single-path analyses in social and behavioural research should not be simply assumed to be robust to alternative analyses4. Therefore, we recommend the development and use of practices to explore and communicate this neglected source of uncertainty.
- 1 April 2026
- Published by Springer Nature in Nature
- Vol. 652 (8108) , 135-142
Top Cited PapersInvestigating the analytical robustness of the social and behavioural sciences
The same dataset can be analysed in different justifiable ways to answer the same research question, potentially challenging the robustness of empirical science1-3. In this crowd initiative, we investigated the degree to which research findings in the social and behavioural sciences are contingent on analysts' choices. We examined a stratified random sample of 100 studies published between 2009 and 2018, in which, for one claim per study, at least five reanalysts independently reanalysed the original data. The statistical appropriateness of the reanalyses was assessed in peer evaluations, and the robustness indicators were inspected along a range of research characteristics and study designs. We found that 34% of the independent reanalyses yielded the same result (within a tolerance region of ±0.05 Cohen's d) as the original report; with a four times broader tolerance region, this indicator increased to 57%. Of the reanalyses conducted, 74% reached the same conclusion as the original investigation, 24% yielded no effects or inconclusive results and 2% reported the opposite effect. This exploratory study indicates that the common single-path analyses in social and behavioural research should not be simply assumed to be robust to alternative analyses4. Therefore, we recommend the development and use of practices to explore and communicate this neglected source of uncertainty.
- Open Access
- 31 March 2026
- Published by Center for Open Science in MetaArXiv
Investigating the analytical robustness of the social and behavioural sciences
The same dataset can be analysed in different justifiable ways to answer the same research question, potentially challenging the robustness of empirical science1–3. In this crowd initiative, we investigated the degree to which research findings in the social and behavioural sciences are contingent on analysts’ choices. We examined a stratified random sample of 100 studies published between 2009 and 2018, where for one claim per study, at least five re-analysts independently re-analysed the original data. The statistical appropriateness of the re-analyses was assessed in peer evaluations, and the robustness indicators were inspected along a range of research characteristics and study designs. We found that 34% of the independent re-analyses yielded the same result (within a tolerance region of +/- 0.05 Cohen’s d) as the original report; with a four times broader tolerance region, this indicator rose to 57%. Regarding the conclusions drawn, 74% of analyses were reported to arrive at the same conclusion as in the original investigation; 24% to no effects/inconclusive result, and 2% to the opposite effect as in the original investigation. This exploratory study suggests that the common single-path analyses in social and behavioural research should not simply be assumed to be robust to alternative analyses4. Therefore, we recommend the development and use of practices to explore and communicate this neglected source of uncertainty.
- 31 March 2026
- Published by Center for Open Science in MetaArXiv
Open AccessInvestigating the analytical robustness of the social and behavioural sciences
The same dataset can be analysed in different justifiable ways to answer the same research question, potentially challenging the robustness of empirical science1–3. In this crowd initiative, we investigated the degree to which research findings in the social and behavioural sciences are contingent on analysts’ choices. We examined a stratified random sample of 100 studies published between 2009 and 2018, where for one claim per study, at least five re-analysts independently re-analysed the original data. The statistical appropriateness of the re-analyses was assessed in peer evaluations, and the robustness indicators were inspected along a range of research characteristics and study designs. We found that 34% of the independent re-analyses yielded the same result (within a tolerance region of +/- 0.05 Cohen’s d) as the original report; with a four times broader tolerance region, this indicator rose to 57%. Regarding the conclusions drawn, 74% of analyses were reported to arrive at the same conclusion as in the original investigation; 24% to no effects/inconclusive result, and 2% to the opposite effect as in the original investigation. This exploratory study suggests that the common single-path analyses in social and behavioural research should not simply be assumed to be robust to alternative analyses4. Therefore, we recommend the development and use of practices to explore and communicate this neglected source of uncertainty.
- 6 March 2026
- Published by The R Foundation
brar: Null Hypothesis Bayesian Response-Adaptive Randomization
Implements Bayesian response-adaptive randomization methods based on Bayesian hypothesis testing for multi-arm settings (Pawel and Held, 2025, ).
- 6 March 2026
- Published by The R Foundation
brar: Null Hypothesis Bayesian Response-Adaptive Randomization
Implements Bayesian response-adaptive randomization methods based on Bayesian hypothesis testing for multi-arm settings (Pawel and Held, 2025, ).