Second Brain
About
A structured knowledge base covering Bayesian statistics, econometrics, causal inference, and agent-based modeling. Notes are cross-linked by topic — use the graph view or search bar to explore connections across the collection.
Selected Analyses
How can SMM be used to calibrate agent based models?
April 11, 2026 · Agent Based Modeling · Calibration · Simulation Estimation · Econometrics
The Simulated Method of Moments (SMM) calibrates an ABM by choosing structural parameters to minimize a weighted distance between observed macro-level data moments and their simulated counterparts produced by running the ABM at .
What are some ways to uncover causal estimates from non-experimental data?
April 10, 2026 · Causal Inference · Econometrics · Identification · Observational Studies
When randomization is impossible, causal estimates can be recovered through several “quasi-experimental” strategies, each exploiting a different source of exogenous variation or structural assumption.
What are some differences between frequentist and Bayesian statistics?
April 9, 2026 · Bayesian Statistics · Frequentist · Probability · Research Methodology
The core divide is philosophical: frequentists treat probability as long-run frequency and parameters as fixed unknowns to be estimated, while Bayesians treat probability as a degree of belief and parameters as random variables with distributions.
What are some common pitfalls in statistical modeling a data scientist should be aware of?
April 9, 2026 · Research Methodology · Bayesian Statistics · Causal Inference · Model Comparison · Statistical Modeling
The vault identifies eight major pitfall categories: (1) confusing correlation with causation via confounds and selection bias, (2) the garden of forking paths and multiple comparisons, (3) overfitting vs.
How should I handle multiple comparisons when selecting from hundreds of models?
April 9, 2026 · Multiple Comparisons · Research Methodology · Bayesian Statistics · Model Comparison
Running hundreds of models and selecting variables or transformations based on statistical significance is a textbook instance of the Garden of Forking Paths problem — the p-values from selected models are invalid because the selection procedure is data-contingent.
Knowledge Base
| Domain | Core Topics |
|---|---|
| Bayesian Statistics | Inference fundamentals, hierarchical models, MCMC, model checking |
| Econometrics | Identification strategies, regression foundations, simulation-based estimation |
| Agent-Based Modeling | Calibration methods, social dynamics, consumer behavior |
| Research Methodology | Experimental design, multiple comparisons, causal reasoning |
Browse the full collection via the search bar or explore topic connections in the graph view.