Mosaic Monte Carlo: A New Method of Simulation Design to Improve the Generalizability of Findings
Journal of Behavioral Data Science · 2026
DOI: 10.35566/jbds/gomer2026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Behavioral Data Science, 2026. Verfasst von Brenna Gomer und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Monte Carlo simulation studies are an essential tool to test the performance of statistical methods. They are often implemented by generating data from a small number of data-generating models for a large number of replications. However, it is not guaranteed that a statistical method tested on a handful of data-generating models will perform well in other scenarios. Simulations are necessarily limited in scope, and so it is all too possible for results to unknowingly fail to generalize to real applications. This issue of generalizability is particularly relevant for methods that are more sensitive to parameter values such as those used in missing data analysis and Bayesian statistics. In this paper, we propose a new type of simulation design called Mosaic Monte Carlo that can help improve the generalizability of Monte Carlo simulation studies to real world applications. This method implements simulations by breaking up replications into smaller subsets, each using a different data-generating model. This approach to simulation design improves the generalizability of results beyond traditional designs.
Zitieren
APA
Gomer, B., Lee, H. B., & Kim, Y. M. (2026). Mosaic Monte Carlo: A New Method of Simulation Design to Improve the Generalizability of Findings. Journal of Behavioral Data Science. https://doi.org/10.35566/jbds/gomer2026
Vancouver
Gomer B, Lee HB, Kim YM. Mosaic Monte Carlo: A New Method of Simulation Design to Improve the Generalizability of Findings. Journal of Behavioral Data Science. 2026. doi:10.35566/jbds/gomer2026
BibTeX
@article{Gomer2026,
author = {Gomer, Brenna and Lee, Han Byul and Kim, Young Min},
title = {Mosaic Monte Carlo: A New Method of Simulation Design to Improve the Generalizability of Findings},
journal = {Journal of Behavioral Data Science},
year = {2026},
doi = {10.35566/jbds/gomer2026}
}
EUVIMED