Johan Pensar

Associate Professor - Statistics and Data Science
Image of Johan Pensar
Norwegian version of this page
Room NHA 814
Visiting address Moltke Moes vei 35 Niels Henrik Abels hus 0851 Oslo
Postal address Postboks 1053 Blindern 0316 Oslo
Other affiliations Institutt for pedagogikk (Student)

Academic interests

At a general level, my research interests are focused around developing and applying statistical and machine learning methods for real-world applications. Some key topics are:

  • Statistical machine learning

  • Probabilistic graphical models

  • Network structure learning

  • Computational causal inference

  • Statistical genomics


I completed my PhD in statistics in 2016 at Åbo Akademi University (Finland), in which I developed a new class of probabilistic graphical models, along with algorithms for learning the structure of the models from data. During 2016-2020, I worked as a postdoc at University of Helsinki (Finland), developing and applying data analysis tools, primarily for applications in bacterial statistical genomics. Since February 2020, I have been working at UiO as an Associate Professor in Statistics and Data Science. 


Supervision (PhD students)

Main supervisor:

  • Anders Hjort (Department of Mathematics, Eiendomsverdi AS, 2020-): Uncertainty in house price prediction (Industrial PhD).
  • Vera Kvisgaard (Department of Mathematics, 2021-): Bayesian estimation of causal effects using directed graphical models.
  • Johan de Aguas (Department of Mathematics, Norwegian Institute of Public Health, 2022-): A Bayesian model-averaging toolkit for causal inference with observational data under nonlinear structural equations: An application to the effect of ADHD treatment on school performance by Norwegian children.


  • Juri Kuronen (Department of Biostatistics, 2018-): High-dimensional structure learning of Markov networks with applications in bacterial statistical genomics.
  • Ghadi Al Hajj (Department of Informatics, 2020-): Improving generalization of machine learning models in medical image and immune receptor sequence analysis through the incorporation of domain priors and constraints.
  • Claudio Meggio (Department of Mathematics, CompSci, 2021-): Statistical learning methods for chemistry applications.

An overview of available Master's thesis projects can be found here.


Finnish Statistical Society - Doctoral Thesis Award (2013-2016).


For a complete list, see my profile at Google Scholar.


Tags: Statistics, data science, Probabilistic Graphical Models, Machine Learning


View all works in Cristin

  • Mageiros, Leonardos; Meric, Guillaume; Bayliss, Sion; Pensar, Johan; Pascoe, Ben & Mourkas, Evangelos [Show all 19 contributors for this article] (2021). Author Correction: Genome evolution and the emergence of pathogenicity in avian Escherichia coli (Nature Communications, (2021), 12, 1, (765), 10.1038/s41467-021-20988-w). Nature Communications. ISSN 2041-1723. 12(1). doi: 10.1038/s41467-021-22238-5.

View all works in Cristin

Published Feb. 18, 2020 8:49 AM - Last modified Sep. 30, 2022 2:26 PM