Przemyslaw Marcowski
PhD Computational Scientist
I specialize in data science and analytics. I use data to find answers, solve problems, and make things more interesting. Data is a reflection of us—our biology, behaviors, choices, and interactions. I like discovering the stories it can tell.
Skills
- R
- Python
- SQL
- Git
- Shiny
- Data Science
- Data Analysis
- Statistical Modeling
- Machine Learning
- Data Mining
- Data Visualization
- Scientific Programming
- Experimental Design
- Quantitative Research
- Behavioral Science
- Decision Science
- Problem Solving
Showcase Projects
Cross-cultural ADHD Assessment in International Sex Survey
Conducted cross-cultural validation of the Adult ADHD Self-Report Scale (ASRS) Screener across 42 countries as part of the International Sex Survey (2021/2022) team. Performed data preparation, psychometric evaluation, and cross-cultural comparisons. Analysis included Confirmatory Factor Analysis (CFA), measurement invariance testing, reliability analysis, and examination of group differences.
Effort-Based Choice Modeling
Analyzed and modeled effort-based choices in economic decision-making. Formulated a novel choice model and compared it to existing models to explain how effort influenced perceived value. Executed agent-based simulations for model recovery and parameter estimation. Performed data preprocessing, statistical analysis, model selection, and result visualization.
Model Recovery Analysis for Intertemporal Choice
Performed a model recovery analysis to validate the reliability of intertemporal choice models. Compared models, simulated choice behavior using agents, and performed recovery analysis to verify accurate recovery of true model parameters from simulated data.
Two-Armed Bandit Game with Reinforcement Learning Analysis
Developed a Two-Armed Bandit game application where players chose between two arms offering different reward potentials. Analyzed the players' choices using a reinforcement learning model, and visualized the decision history characteristics.
Dog Growth Prediction Model and Application
Built a Bayesian predictive model for dog growth trajectories based on the von Bertalanffy growth curve. Implemented the model in a Shiny app that generates personalized growth predictions based on user input.
Maze Generation and Solving
Generated random mazes using the Recursive Backtracking algorithm and solved them using a chosen path-finding algorithm. Visualized the generated mazes and their solutions, allowing for comparisons of the strengths and weaknesses of the different path-finding algorithms.
Selected Publications
People conform to social norms when gambling with lives or money
Scientific Reports, 13(1), 853 (2023)
View PublicationEffectiveness of emotion regulation strategies measured by self-report and EMG as a result of strategy used, negative emotion strength and participants' baseline HRV
Scientific Reports, 13(1), 6226 (2023)
View PublicationPath Dependency in the Discounting of Delayed and Probabilistic Gains and Losses
Scientific Reports, 9(1), 8738–8738 (2019)
View Publication