Jouni Helske
PhD (Statistics)
jouni.helske@utu.fi +358 29 450 3114 +358 50 461 1304 Assistentinkatu 7 Turku : 453 |
Bayesian statistics; causal inference; state space models; hidden Markov models; longitudinal data; computational statistics; probabilistic programming; R package development.
CAUSALTIME and PREDLIFE projects
I am an Academy Research Fellow in Statistics at the University of Turku. I lead the CAUSALTIME project where we develop new Bayesian methods for estimation of short- and long-term causal effects based on complex panel data, using for example dynamic multivariate panel models and hidden Markov models. I also do applied statistics mostly in sociology and other areas of social sciences, but also in fields such as epidemiology.
I was previously a PI of the Statistics subproject of the PREDLIFE Consortium at University of Jyväskylä.
I am also an associate editor of the R Journal and rOpenSci statistical software initiative, and an open science ambassador of Open Science Community Turku.
I completed my PhD in statistics at the University of Jyväskylä, Finland, in 2015. Following my PhD I worked as a Postdoctoral Researcher at University of Jyväskylä, at Linköping University, at University of Jyväskylä (again), and Senior Researcher at University of Jyväskylä, before joining the University of Turku.
My current research focuses on developing efficient and accurate Bayesian methods for estimating causal effects especially in the context of complex multivariate time series models (e.g, panel data). More broadly, my research interests are related to computational statistics, especially Bayesian methods, time series models such as state space and hidden Markov models, causal inference, visualization of complex data and models, and statistical software development.
I am not teaching at the moment.
- Adaptation to paternal leave policies in Finnish municipalities: changing gender norms and cross-border policy legacies (2024) Pasanen, Tiia-Maria; Helske, Satu; Giuliani, Giovanni Amerigo; Chapman, Simon; Helske, Jouni
- A Modern Approach to Transition Analysis and Process Mining with Markov Models in Education (2024) Learning Analytics Methods and Tutorials Helske, Jouni; Helske, Satu; Saqr, Mohammed; López-Pernas, Sonsoles; Murphy, Keefe
- dynamite: An R Package for Dynamic Multivariate Panel Models (2024) Tkka, Santtu; Helske, Jouni
- Education, family complexity and heterogeneous causal effects of parental separation (2024) Helske Satu; Erola Jani; Helske Jouni
- Estimating causal effects from panel data with dynamic multivariate panel models (2024)
- Advances in Life Course Research
- From Sequences to Variables: Rethinking the Relationship between Sequences and Outcomes (2024)
- Sociological Methodology
- Heterogeneous workplace peer effects in fathers’ parental leave uptake in Finland (2024) Helske, Satu; Helske, Jouni; Chapman, Simon; Kotimäki, Sanni; Salin, Milla; Tikka, Santtu
- Hidden Markov modelling of spatio-temporal dynamics of measles in 1750-1850 Finland (2024) Pasanen, Tiia-Maria; Helske, Jouni; Ketola, Tarmo
- Price Optimization Combining Conjoint Data and Purchase History: A Causal Modeling Approach (2024)
- Observational Studies
- Spatio-temporal modeling of co-dynamics of smallpox, measles, and pertussis in pre-healthcare Finland (2024)
- PeerJ
- Using eye tracking to support professional learning in vision-intensive professions: a case of aviation pilots (2024)
- Education and Information Technologies
- Clustering and Structural Robustness in Causal Diagrams (2023)
- Journal of Machine Learning Research
- dynamite: Bayesian Modeling and Causal Inference for Multivariate Longitudinal Data (2023) Tikka, Santtu; Helske, Jouni
- Estimating the causal effect of timing on the reach of social media posts (2023)
- Statistical Methods and Applications
- A Bayesian spatio-temporal analysis of markets during the Finnish 1860s famine (2022)
- Journal of the Royal Statistical Society: Series C
- Efficient Bayesian generalized linear models with time-varying coefficients : The walker package in R (2022)
- SoftwareX
- A nonlinear mixed model approach to predict energy expenditure from heart rate (2021)
- Physiological Measurement
- bssm: Bayesian Inference of Non-linear and Non-Gaussian State Space Models in R (2021)
- The R journal
- Can visualization alleviate dichotomous thinking Effects of visual representations on the cliff effect (2021)
- IEEE Transactions on Visualization and Computer Graphics
- Estimation of causal effects with small data in the presence of trapdoor variables (2021)
- Journal of the Royal Statistical Society: Series A