Nikola Sekulovski
Postdoctoral researcher · Psychological Methods, University of Amsterdam
I’m a postdoc in the Psychological Methods group at the University of Amsterdam and part of the Bayesian Graphical Modeling Lab. Before that, I did my PhD in the same group, supervised by Maarten Marsman and Eric-Jan Wagenmakers.
My research focuses on Bayesian statistical methods for psychological network models. I’m particularly interested in figuring out which variables are directly related, whether they form clusters, and how we can use prior information to test theories. A big part of my work also involves developing open-source software and making these methods accessible to applied researchers through R and JASP. I also enjoy collaborating with applied researchers and figuring out how statistical methods can help answer their research questions.
I also teach (mostly Bayesian statistics) in the bachelor’s and research master’s programmes and supervise bachelor’s and master’s theses.
I studied psychology in Skopje, North Macedonia, before moving to the Netherlands for a master’s in Methodology and Statistics at Utrecht University.
Publications
Each paper links to the journal version and, where there is one, a free preprint. The full list is also on Google Scholar.
Forthcoming
Analysis and reporting guidelines for Bayesian graphical modeling of cross-sectional data: A tutorial in JASP
Submitted
@article{sekulovski2026guidelines, author = {Sekulovski, N. and Huth, K. and van den Bergh, D. and van Doorn, J. and Blanken, T. F. and Wagenmakers, E.-J. and Marsman, M.}, title = {Analysis and reporting guidelines for {Bayesian} graphical modeling of cross-sectional data: {A} tutorial in {JASP}}, year = {2026}, pubstate = {submitted}, }The prevalence of Bayesian inference, preregistration, and open data in psychology, 2004–2024
Accepted
@article{pfadt2026prevalence, author = {Pfadt, J. M. and Barto{\v{s}}, F. and Godmann, H. R. and Waaijers, M. and Groot, L. and Heo, I. and Mensink, L. and Nak, J. and De Ruiter, J. P. and Sarafoglou, A. and Siepe, B. S. and Arena, G. M. and Akrong, E. and Aust, F. and van den Bergh, D. and Brenner, W. and Doekemeijer, R. A. and Donzallaz, M. C. and van Doorn, J. and Echevarria, N. O. and Finnemann, A. and Geller, G. and Hato, T. and Koskinen, E. and Krijgsman, B. and Kulbe, L. and L{\"u}ken, M. and Marsman, M. and Ott, V. L. and Pawel, S. and Piestrak, O. and de Ron, J. and Sekulovski, N. and Serry, M. and Stefan{\'o}w, A. and Stevenson, N. and Sadowski, B. and Sopuch, M. and Vasileiou, A. and Visser, I. and V{\"o}ller, M. and Wiechert, S. and de Wit, K. and Wuth, J. and Wagenmakers, E.-J.}, title = {The prevalence of {Bayesian} inference, preregistration, and open data in psychology, 2004--2024}, year = {2026}, pubstate = {accepted}, }LLM-based prior elicitation for Bayesian graphical modeling
British Journal of Mathematical and Statistical PsychologyIn press
@article{sekulovski2026llm, author = {Sekulovski, N. and Waaijers, M. and Arena, G.}, title = {{LLM}-based prior elicitation for {Bayesian} graphical modeling}, journal = {British Journal of Mathematical and Statistical Psychology}, year = {2026}, doi = {10.1111/bmsp.70045}, pubstate = {inpress}, }A stochastic block prior for clustering in graphical models
Psychological MethodsIn press
@article{sekulovski2026sbm, author = {Sekulovski, N. and Arena, G. and Haslbeck, J. M. B. and Huth, K. and Friel, N. and Marsman, M.}, title = {A stochastic block prior for clustering in graphical models}, journal = {Psychological Methods}, year = {2026}, pubstate = {inpress}, }
2026
Comparing variable selection and model averaging methods for logistic regression
Proceedings of the National Academy of Sciences, 123(19), e2534552123
@article{sekulovski2026logistic, author = {Sekulovski, N. and Barto{\v{s}}, F. and van den Bergh, D. and Arena, G. and Godmann, H. R. and Goyal, V. and Pfadt, J. M. and Marsman, M. and Raftery, A. E.}, title = {Comparing variable selection and model averaging methods for logistic regression}, journal = {Proceedings of the National Academy of Sciences}, year = {2026}, volume = {123}, number = {19}, pages = {e2534552123}, doi = {10.1073/pnas.2534552123}, }Analysis blinding as a complement to preregistration: A tutorial for network analysis
Advances in Methods and Practices in Psychological Science, 9(4)
Shared first authorship between the first three authors.
@article{hoekstra2026blinding, author = {Hoekstra, R. H. A. and Huth, K. and Sekulovski, N. and Delhalle, M. and Sarafoglou, A.}, title = {Analysis blinding as a complement to preregistration: {A} tutorial for network analysis}, journal = {Advances in Methods and Practices in Psychological Science}, year = {2026}, volume = {9}, number = {4}, doi = {10.1177/25152459261481079}, }
2025
Bayes factor tests for group differences in ordinal and binary graphical models
Psychometrika, 90(5), 1809–1842
@article{marsman2025group, author = {Marsman, M. and Waldorp, L. J. and Sekulovski, N. and Haslbeck, J. M. B.}, title = {{Bayes} factor tests for group differences in ordinal and binary graphical models}, journal = {Psychometrika}, year = {2025}, volume = {90}, number = {5}, pages = {1809--1842}, doi = {10.1017/psy.2025.10060}, }The impact of dichotomization on network recovery
Behavior Research Methods, 57(12), 342
@article{sekulovski2025dichotomization, author = {Sekulovski, N. and Blanken, T. F. and Haslbeck, J. M. B. and Marsman, M.}, title = {The impact of dichotomization on network recovery}, journal = {Behavior Research Methods}, year = {2025}, volume = {57}, number = {12}, pages = {342}, doi = {10.3758/s13428-025-02861-6}, }
2024
A Good check on the Bayes factor
Behavior Research Methods, 56(8), 8552–8566
@article{sekulovski2024good, author = {Sekulovski, N. and Marsman, M. and Wagenmakers, E.-J.}, title = {A {Good} check on the {Bayes} factor}, journal = {Behavior Research Methods}, year = {2024}, volume = {56}, number = {8}, pages = {8552--8566}, doi = {10.3758/s13428-024-02491-4}, }Testing conditional independence in psychometric networks: An analysis of three Bayesian methods
Multivariate Behavioral Research, 59(5), 913–933
@article{sekulovski2024testing, author = {Sekulovski, N. and Keetelaar, S. and Huth, K. B. S. and Wagenmakers, E.-J. and van Bork, R. and van den Bergh, D. and Marsman, M.}, title = {Testing conditional independence in psychometric networks: {An} analysis of three {Bayesian} methods}, journal = {Multivariate Behavioral Research}, year = {2024}, volume = {59}, number = {5}, pages = {913--933}, doi = {10.1080/00273171.2024.2345915}, }Sensitivity analysis of prior distributions in Bayesian graphical modeling: Guiding informed prior choices for conditional independence testing
Advances in Psychology, 2, e92355
@article{sekulovski2024sensitivity, author = {Sekulovski, N. and Keetelaar, S. and Haslbeck, J. M. B. and Marsman, M.}, title = {Sensitivity analysis of prior distributions in {Bayesian} graphical modeling: {Guiding} informed prior choices for conditional independence testing}, journal = {Advances in Psychology}, year = {2024}, volume = {2}, pages = {e92355}, doi = {10.56296/aip00016}, }Comparing maximum likelihood and maximum pseudolikelihood estimators for the Ising model
Advances in Psychology, 2, e25745
@article{keetelaar2024ising, author = {Keetelaar, S. and Sekulovski, N. and Borsboom, D. and Marsman, M.}, title = {Comparing maximum likelihood and maximum pseudolikelihood estimators for the {Ising} model}, journal = {Advances in Psychology}, year = {2024}, volume = {2}, pages = {e25745}, doi = {10.56296/aip00013}, }Simplifying Bayesian analysis of graphical models for the social sciences with easybgm: A user-friendly R-package
Advances in Psychology, 2, e66366
@article{huth2024easybgm, author = {Huth, K. and Keetelaar, S. and Sekulovski, N. and van den Bergh, D. and Marsman, M.}, title = {Simplifying {Bayesian} analysis of graphical models for the social sciences with easybgm: {A} user-friendly {R}-package}, journal = {Advances in Psychology}, year = {2024}, volume = {2}, pages = {e66366}, doi = {10.56296/aip00010}, }Prevalence, patterns, and predictors of paranormal beliefs in the Netherlands: A several-analysts approach
Royal Society Open Science, 11(9), 240049
@article{hoogeveen2024paranormal, author = {Hoogeveen, S. and Borsboom, D. and Kucharsk{\'y}, {\v{S}}. and Marsman, M. and Molenaar, D. and de Ron, J. and Sekulovski, N. and Visser, I. and van Elk, M. and Wagenmakers, E.-J.}, title = {Prevalence, patterns, and predictors of paranormal beliefs in the {Netherlands}: {A} several-analysts approach}, journal = {Royal Society Open Science}, year = {2024}, volume = {11}, number = {9}, pages = {240049}, doi = {10.1098/rsos.240049}, }
2023
A default Bayes factor for testing null hypotheses about the fixed effects of linear two-level models
Psychological Methods, 30(3), 579–598
@article{sekulovski2023default, author = {Sekulovski, N. and Hoijtink, H.}, title = {A default {Bayes} factor for testing null hypotheses about the fixed effects of linear two-level models}, journal = {Psychological Methods}, year = {2023}, volume = {30}, number = {3}, pages = {579--598}, doi = {10.1037/met0000573}, }
Software
Most of the methods I work on end up in an R package or in JASP.
R packages I maintain
bgmElicit
Uses large language models to help you set priors on the network structure in Bayesian graphical models.
Software I contribute to
bgms
Bayesian analysis of networks of binary, ordinal and continuous variables.
easybgm
A user-friendly wrapper for Bayesian graphical modeling in R.
JASP
Free, open-source statistics software from the University of Amsterdam. I work on its Bayesian network module.
Talks & workshops
Talks
- Jul 2026Talk
LLM-based prior elicitation for Bayesian graphical modeling
International Meeting of the Psychometric Society (IMPS) · Seoul, South Korea
- Dec 2025Invited
Frequentist and Bayesian statistics with examples in JASP
Ss. Cyril and Methodius University · Skopje, North Macedonia
- Dec 2025Talk
A stochastic block prior for clustering in graphical models
CFE-CMStatistics · London, UK
- Dec 2025Talk
LLM-based prior elicitation for Bayesian graphical modeling
IOPS Winter Conference · Utrecht, the Netherlands
- Jul 2025Talk
Using the stochastic block model for clustering in psychological networks
European Association of Methodology (EAM) · Tenerife, Spain
- Oct 2024Poster
A Good check on the Bayes factor
Bayesian Methods for the Social Sciences II · Amsterdam, the Netherlands
- Jul 2024Talk
Testing conditional independence in psychometric networks
International Meeting of the Psychometric Society (IMPS) · Prague, Czech Republic
- Sep 2023Invited
Bayesian approaches for assessing conditional independence and prior sensitivity in network psychometrics
DynaNeT Workshop, Utrecht University · Utrecht, the Netherlands
- Jun 2023Poster
Testing conditional independence in psychometric networks: An analysis of three Bayesian methods
IOPS Summer Conference · Tilburg, the Netherlands
Workshops I taught or assisted with
- 2025–2026
The Bayesian analysis of networks
PSYNETS workshops (January and July editions) · with Maarten Marsman
- Oct 2024
Bayesian graphical modeling
Bayesian Methods for the Social Sciences II, Amsterdam · with Maarten Marsman
- Sep 2024
Bayesian graphical modeling
What is Psychometrics? (IOPS course) · with Maarten Marsman
- Jun 2024
An introduction to JASP
New Horizons in Psychological Science and Practice, Skopje
- Jul 2022
Introduction to multilevel analysis
Utrecht Summer School · teaching assistant
Blog
Tutorials for some of my papers, and the occasional post.
- Clustering in Bayesian graphical models using bgms and easybgm
A short software tutorial that goes with the paper “A stochastic block prior for clustering in graphical models”.
- A Good check on the Bayes factor↗
Two theorems from Turing and Good, explained with a coin toss, and a simple simulation check on whether a Bayes factor is computed correctly. Posted on Bayesian Spectacles.
- A default Bayes factor for the fixed effects of linear two-level models
A tutorial that goes with the paper on testing null hypotheses about the fixed effects in two-level models.
Contact
Email is the easiest way to reach me.
n.sekulovski@uva.nlPsychological Methods, Department of Psychology
University of Amsterdam, the Netherlands