Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn Bayesian statistical analysis and causal inference through this comprehensive lecture series that challenges conventional statistical thinking and emphasizes practical modeling approaches. Master fundamental concepts starting with the "Golem of Prague" metaphor for statistical models, then progress through Bayesian inference, geocentric models, and advanced techniques including categories, curves, and splines. Explore critical topics in causal reasoning such as elemental confounds, good versus bad controls, and overfitting prevention strategies. Develop proficiency in Markov chain Monte Carlo methods for computational statistics and apply these techniques to model various data types including events, counts, and ordered categories. Advance to sophisticated multilevel modeling approaches, including multi-multilevel models and correlated varying effects for hierarchical data structures. Investigate specialized applications such as social network analysis, Gaussian processes for spatial and temporal modeling, and methods for handling measurement error and missing data. Conclude with generalized linear models and their extensions, gaining practical experience through hands-on examples and real-world applications that demonstrate how to think clearly about statistical problems and build robust, interpretable models for scientific inference.
