Statistical analysis is error prone. A best practice for researchers using statistics would therefore be to share data among co-authors, allowing double-checking of executed tasks just as co-pilots do in aviation. To document the extent to which this ‘co-piloting’ currently occurs in psychology, we surveyed the authors of 697 articles published in six top psychology journals and asked them whether they had collaborated on four aspects of analyzing data and reporting results, and whether the described data had been shared between the authors. We acquired responses for 49.6% of the articles and found that co-piloting on statistical analysis and reporting results is quite uncommon among psychologists, while data sharing among co-authors seems reasonably but not completely standard. We then used an automated procedure to study the prevalence of statistical reporting errors in the articles in our sample and examined the relationship between reporting errors and co-piloting. Overall, 63% of the articles contained at least one p-value that was inconsistent with the reported test statistic and the accompanying degrees of freedom, and 20% of the articles contained at least one p-value that was inconsistent to such a degree that it may have affected decisions about statistical significance. Overall, the probability that a given p-value was inconsistent was over 10%. Co-piloting was not found to be associated with reporting errors.

Research data is increasingly viewed as an important scholarly output. While a growing body of studies have investigated researcher practices and perceptions related to data sharing, information about data-related practices throughout the research process (including data collection and analysis) remains largely anecdotal. Building on our previous study of data practices in neuroimaging research, we conducted a survey of data management practices in the field of psychology. Our survey included questions about the type(s) of data collected, the tools used for data analysis, practices related to data organization, maintaining documentation, backup procedures, and long-term archiving of research materials. Our results demonstrate the complexity of managing and sharing data in psychology. Data is collected in multifarious forms from human participants, analyzed using a range of software tools, and archived in formats that may become obsolete. As individuals, our participants demonstrated relatively good data management practices, however they also indicated that there was little standardization within their research group. Participants generally indicated that they were willing to change their current practices in light of new technologies, opportunities, or requirements.

Methods To investigate the data-related practices of psychology researchers, we adapted a survey developed as part of our previous study of neuroimaging researchers. The survey was distributed via Qualtrics (http://www.qualtrics.com) from January 25 to March 25, 2019. Before beginning the survey, participants were required to verify that they were at least 18 years old and gave their informed consent to participate. Participants who did not meet these inclusion criteria or who did not complete at least the first section of the survey were not included in the final data analysis. After filtering, 274 psychology researchers from 31 countries participated in our survey.

All code for data collection and visualization is included in the Jupyter notebooks included here.

This dataset contains several files related to our research paper titled "Attention Allocation to Projection Level Alleviates Overconfidence in Situation Awareness". These files are intended to provide a comprehensive overview of the data analysis process and the presentation of results. Below is a list of the files included and a brief description of each:

R Scripts: These are scripts written in the R programming language for data processing and analysis. The scripts detail the steps for data cleaning, transformation, statistical analysis, and the visualization of results. To replicate the study findings or to conduct further analyses on the dataset, users should run these scripts.

R Markdown File: Offers a dynamic document that combines R code with rich text elements such as paragraphs, headings, and lists. This file is designed to explain the logic and steps of the analysis in detail, embedding R code chunks and the outcomes of code execution. It serves as a comprehensive guide to understanding the analytical process behind the study.

HTML File: Generated from the R Markdown file, this file provides an interactive report of the results that can be viewed in any standard web browser. For those interested in browsing the study's findings without delving into the specifics of the analysis, this HTML file is the most convenient option. It presents the final analysis outcomes in an intuitive and easily understandable manner. For optimal viewing, we recommend opening the HTML file with the latest version of Google Chrome or any other modern web browser. This approach ensures that all interactive functionalities are fully operational.

Together, these files form a complete framework for the research analysis, aimed at enhancing the transparency and reproducibility of the study.

These files contain all scripts used for analyzing the data of the norms of the Dutch Oxford Cognitive Screen.

Behavioral data organized in wide format for analysis with JASP software.

Traffic analytics, rankings, and competitive metrics for psychology.org as of September 2025

This research data is one of psychometric properties of measurement tool of marital quality of Javanese people and it was analyzed using Rasch model. There were 840 subjects (or 420 husband-wife couples) in this research coming from Java Island, Indonesia represented by 4 regions: Special District of Yogyakarta, Solo, Banyumas, and Pekalongan. The estimation of item parameter was conducted using QUEST program. The Threshold parameter and fit model in each item was presented in the appendix. The data of the results of the research furthermore could be practically used to measure the marital quality of Javanese people.

Zip file containing all data and analysis files for Experiment 1 in:Weiers, H., Inglis, M., & Gilmore, C. (under review). Learning artificial number symbols with ordinal and magnitude information.Article abstractThe question of how numerical symbols gain semantic meaning is a key focus of mathematical cognition research. Some have suggested that symbols gain meaning from magnitude information, by being mapped onto the approximate number system, whereas others have suggested symbols gain meaning from their ordinal relations to other symbols. Here we used an artificial symbol learning paradigm to investigate the effects of magnitude and ordinal information on number symbol learning. Across two experiments, we found that after either magnitude or ordinal training, adults successfully learned novel symbols and were able to infer their ordinal and magnitude meanings. Furthermore, adults were able to make relatively accurate judgements about, and map between, the novel symbols and non-symbolic quantities (dot arrays). Although both ordinal and magnitude training was sufficient to attach meaning to the symbols, we found beneficial effects on the ability to learn and make numerical judgements about novel symbols when combining small amounts of magnitude information for a symbol subset with ordinal information about the whole set. These results suggest that a combination of magnitude and ordinal information is a plausible account of the symbol learning process.© The Authors

This dataset contains the bibliographic records of 449 documents on early childhood creativity (ECC), retrieved from the Scopus database for the period of 1962 to January 2024. The collection represents the empirical foundation for the bibliometric analysis, "From Psychometrics to Playful Pixels: A Bibliometric Cartography of Early Childhood Creativity Research (1962–2024)." This dataset provides a structured overview of the field, allowing for detailed analysis of publication trends, collaboration networks, and the underlying intellectual structure of ECC research.

Data collection was performed on January 26, 2024, using a targeted search query in the 'Article Title' field to increase thematic relevance. The query was constructed around two main concepts. The first, 'early childhood,' included the terms "early childhood," "young child*," "early years," "preschool*," "kindergarten*," and "nursery school." The second concept, 'creativity,' used the terms "creativ*" and "divergent thinking." Terms within each conceptual group were combined with the 'OR' operator, and the two groups were linked using the 'AND' operator.

The initial search returned 455 records. These were screened for inclusion based on three criteria: a direct relevance to creativity, a focus on the early childhood period (0–6 years), and publication as a journal article or review. The search was restricted to documents in English. This screening process resulted in a final corpus of 449 documents. All bibliographic data, including author names and institutional affiliations, were subsequently reviewed for accuracy.

The dataset is available in CSV format and includes extensive bibliographic metadata, such as author names, institutional affiliations, publication years, citation counts, and author keywords. It is structured for direct use with bibliometric software, including VOSviewer and the Bibliometrix R package (via Biblioshiny), to support the replication or extension of the original study’s performance analysis and science mapping. The data present a valuable resource for scholars investigating the development of ECC research.

Happiness and life satisfaction The relationship between life satisfaction and happiness is an important area within the field of positive psychology. Most researchers assert a positive link between life satisfaction and happiness [17,32,35,36,37], while seeing happiness as being more emotional and life satisfaction more cognitive in nature. The relationship between life satisfaction and happiness is an important area within the field of positive psychology. Most researchers see happiness as being more emotional in nature, while life satisfaction is more cognitive in nature.

@article{owidhappinessandlifesatisfaction, author = {Esteban Ortiz-Ospina and Max Roser}, title = {Happiness and Life Satisfaction}, journal = {Our World in Data}, year = {2013}, note = {https://ourworldindata.org/happiness-and-life-satisfaction} }

The zip file contains the data files and R analysis script used in the manuscript titled 'Attentional bias modification in virtual reality - a VR-based dot-probe task with 2D and 3D stimuli' Analysis_script.R is a script file that can be opened by the statistical software R (https://www.r-project.org/) and Rstudio (https://www.rstudio.com/). All analysis steps and codes are found within this file. All files under the Data_files folder are directly called by Analysis_script from R, therefore please ensure that the folder structure and file names remain the same. Folder dot_probe_raw_data_files and its subfolders contain *.xml files with attentional bias (reaction time) data from the participants, generated by the VR program. outcome_measures_and_demographic_data.xlsx contains participant demographic data and questionnaire measures, generated by the iTerapi platform. This data file has been cleaned to remove information irrelevant to the analysis (e.g. number of reminder emails sent etc.). lsas_pre_individual_items.xlsx contains participant responses to individual items of the LSAS-SR questionnaire, generated by the iTerapi platform.

This data package contains the slides, Matlab m files and a dataset for an ERP workshop I gave in Washington DC, Glasgow, Fribourg, Frankfurt & Berlin. The goal of the workshop is to use hands-on exercises to introduce the basic principles and the Matlab implementation of robust estimation, using resampling methods (bootstrap & permutation) in conjunction with robust estimators. The workshop covers why classic t-tests and ANOVAs on means are not necessarily the best options, and how robust approaches can help. In particular, it demonstrates techniques to compare entire distributions, how to build confidence intervals about any quantity using the bootstrap, and how to effectively control for multiple comparisons. The methods are applied to single-subject and group analyses, and examples are provided to integrate both levels into informative figures.

The data files submitted here are related to the research, in which we compared psychological and biological indicators of life history strategies of criminals (N=84) and control group - men without criminal record (N=117), working as soldiers (N =32, the last 32 items in the dataset) and firefighters (N =85, the first 85 items in the dataset).

We hypothesized that there would be differences in life history strategies employed by these two groups of subjects and we also expected that biological and psychological life history indicators used in the study would correlate with each other as, according to life history theory, they are reflections of one consistent life history strategy.

We used two questionnaires: the Mini-K (Figueredo et al., 2006) used to assess psychological aspects of life history strategy and the questionnaire we created to measure biological life history variables such as age of the subjects’ parents at the appearance of their first child, father presence, number of biological siblings and step-siblings, twins in family, intervals between subsequent mother’s births, age at sexual onset, having children, age of becoming a father, number of offspring, number of women with whom the subjects have children and life expectancy. The research on criminals took place in medium-security correctional institution. Firefighters and soldiers participated in the study in their workplaces. All subjects were completing questionnaires in a paper-and-pencil version.The participation was voluntary.

The results showed that criminals tended to employ faster life history strategies than men who have not been incarcerated, but this regularity only emerged in relation to biological variables. There were no intergroup differences in the context of psychological indicators of LH strategy measured by the Mini-K. Moreover, the overall correlation between the biological and psychological LH indicators used in this study was weak. Thus, in our study biological indicators proved to reliably reflect life history strategies of the subjects, in contrast to psychological variables.

All statistical analysis was performed using SPSS and Statistica. Raw data as well as encoded data in SPSS format are attached.

Figueredo, A.J., Vásquez, G., Brumbach, B.H., Schneider, S.M.R., Sefcek, J.A., Tal, I.R., Hill, D., Wenner, C.J., & Jacobs, W.J. (2006). Consilience and life history theory: From genes to brain to reproductive strategy. Developmental Review, 26, 243-275.

The purpose of this dataset is to share the positive psychology intervention of university students. The results obtained from this dataset, the descriptive analysis and the statistical analyses performed on this data were developed using SPSS and give rise to a scientific article (currently under review).

Data file associated with meta-analysis of Studies 3 and 4 from "The Inherence Heuristic as a Source of Essentialist Thought" Potentially identifiable information (IP addresses, demographic data) has been removed. Please contact the authors if you require these data.

1207 participants

This is the datafile from all studies with contributing data to the meta-analysis.

Two datasets are used and can be downloaded and viewed.

1、The Netflix Life Impact Dataset (NLID) is a specialized collection and organization of movie datasets that focuses on how movies have a profound impact on viewers' emotions, psychology, and behavior. Unlike traditional movie datasets such as box office and ratings, NLID places greater emphasis on the impact of movie stories, scenes, and content on the audience's worldview, values, and even behavior.

The Netflix Life Impact Dataset (NLID) emphasizes the profound impact of movies on audience psychology and behavior, focusing on the emotional, behavioral, and psychological perspectives of movie influence. It is suitable for exploring topics such as "how movies affect people's behavior and thoughts" and has strong humanistic and social science colors.

2、Netflix film and television metadata analysis (netflix_titles. csv, etc.): It is more about content attributes (type, country, year, director, duration, etc.) and user behavior analysis, and is more suitable for technical research such as "how data science optimizes recommendation systems", "content trend analysis", "user behavior analysis", etc.

A Hybrid Data Science Framework for Personalized Netflix Recommendations Integrating Emotional Impact Analysis

Framework Content Design I. Problem (6%) - Problem Definition and Solution Steps

①Explanation: Netflix has a massive amount of content, and traditional recommendations rely heavily on user viewing behavior and metadata, lacking consideration for the emotional depth and psychological impact of movies. This leads to homogenization of recommended content, insufficient emotional resonance among users, and affects user retention and satisfaction. ②How to solve? By combining Netflix metadata (netflix_titles) and movie sentiment depth data (NLID), a hybrid recommendation system that integrates collaborative filtering and sentiment analysis is constructed to achieve more accurate and emotionally valuable content recommendations.

③Steps:Data preprocessing, behavioral data analysis, sentiment analysis, hybrid model design, recommendation system validation

II.Solutions (8%) - Data and Design

①Suitable dataset:

Netflix Movie metadata (netflix \ _titles. csv) Netflix Life Impact Dataset (NLID) User behavior log (simulated data or assumptions)

②Mockup design:

1、Display the "Emotional Resonance Recommendation" column in the homepage recommendation area, labeled with "Life Changing Timestamp".The precise minute that marks the moment of film transformation.It serves as the emotional core label for movies, used to identify and recommend film and television content that can bring psychological resonance, emotional impact, or behavioral change." 2、Display emotional tags (such as "motivation", "reflection", "warmth") when users watch videos 3、The sidebar of the recommendation page displays "life inspirations shared by the audience" and "popular emotional topic cloud"

③Example code (R):

1、Using tidyverse for data cleaning 2、Quantify emotional text using TF-IDF or sklearn 3、Implementing a collaborative filtering model using Recommenderlab 4、Use ggplot2 to draw emotional label distribution maps and user behavior trend 5、Build an interactive recommendation demonstration interface

III.Others (6%)

①Creativity and Information Flow

1. A recommendation system that integrates deep emotional tags, surpassing traditional behavior based recommendations and focusing on user emotional needs
2. Using "Life Changing Timestamp" as the core content tag, guide users to explore emotionally resonant film and television content
3. Interdisciplinary integration of data science and psychology to enhance the social and cultural value of content

②Proper flow of information: Firstly, introduce the Netflix content explosion and recommendation challenges, introduce the Netflix Movie metadata and NLID dataset and its emotional impact perspective, elaborate on the ideas of data preprocessing and model fusion, showcase example visualizations and recommendation page mockups, discuss commercial value and future improvement directions

Summary： Personalized、Emotion-aware、Hybrid 、Innovative、Effective

Coding of all studies including the moderators.

Spreadsheet contains the effect sizes and moderator codes used in the meta-analysis.