News
Call for Papers: Hotspots in Psychology 2026
For more details click here
#metaanalysis #machinelearning
New paper: Potential COVID-19 test fraud detection: Statistical versus conventional approaches
Background: Some COVID-19 testing centres have reported manipulated test numbers for antigen tests/rapid tests. This study compares statistical approaches with traditional fraud detection methods. The extent of agreement between traditional and statistical methods was analysed, as well as the extent to which statistical approaches can identify additional cases of potential fraud. Methods: Outlier detection marking a high number of tests, modeling of the positivity rate (Poisson Regression), deviation from distributional assumptions regarding the first digit (Benford’s Law) and the last digit of the number of reported tests. The basis of the analyses were billing data (April 2021 to August 2022) from 907 testing centres in a German city. Results: The positive agreement between the conventional and statistical approaches (‘sensitivity’) was between 8.6% and 24.7%, the negative agreement (‘specificity’) was between 91.3% and 94.6%. The proportion of potentially fraudulent testing centres additionally identified by statistical approaches was between 7.0% and 8.7%. The combination of at least two statistical methods resulted in an optimal detection rate of test centres with previously undetected initial suspicion. Conclusions: The statistical approaches were more effective and systematic in identifying potentially fraudulent testing centres than the conventional methods. Testing centres should be urged to map paradata (e.g. timestamps of testing) in future pandemics.
Our Guest: Prof. Dr. Clemens Stachl
Institute of Behavioral Science & Technology, University of St. Gallen
Invited Talk: Tuesday, 4 February 2025, 18:00 Uhr, in D 435
Investigating Psychological Characteristics with Mobile Technologies and Machine Learning
Mobile technologies, such as smartphones, offer a powerful means of capturing rich, real-time behavioral data in everyday settings. In this talk, I explore how data from mobile devices - such as communication patterns, social interactions, physical activity, and app usage - can be utilized to predict psychological traits, including personality, affect, and cognitive abilities. I will present key methodologies for processing and interpreting this data, address the challenges related to privacy, and examine the potential for personalized psychological interventions. Empirical findings will demonstrate how machine learning models can predict psychological outcomes, while highlighting current limitations and future directions for research in this emerging field.
Associate Professor Clemens Stachl is the Director of the Institute of Behavioral Science and Technology at the University of St. Gallen in Switzerland. He studied Psychology at the University of Graz in Austria before pursuing his PhD in Psychology and Statistics at the Ludwig-Maximilians Universität München in Germany, where he also completed two years of postdoctoral research. During this time, he worked both in academia and as a researcher in industry in Ingolstadt. Following his academic career in Germany, Stachl held a postdoctoral position at Stanford University in the United States, before joining the University of St. Gallen in his current role. Stachl’s research focuses on studying human behavior in naturalistic settings, utilizing digital tools to collect and analyze behavioral data. His work explores how digital traces can help understand psychological characteristics, such as personality traits, and their relation to economic outcomes. By combining traditional psychological approaches with large-scale data and predictive modeling techniques, his research offers insights into how technology can enhance our understanding of behavior. Stachl's research is supported by numerous public and private funding organizations across Germany, Switzerland, and the United States.