Information and Model Misspecification - Classical Statistics vs. Info-Metrics
Offered By: Santa Fe Institute via YouTube
Course Description
Overview
Explore the challenges of model misspecification in statistical analysis through this insightful seminar by SFI External Professor Amos Golan. Delve into the info-metrics framework and its approach to handling imperfect and incomplete information across various scientific disciplines. Compare classical statistical methods with info-metrics, focusing on constraint specification and criterion selection. Examine a practical example investigating power law distributions using Shannon entropy and Empirical Likelihood, highlighting the complexities of identifying misspecification in seemingly equivalent predictions. Gain valuable insights into the nuances of statistical modeling and inference under conditions of uncertainty.
Syllabus
Introduction
Misspecification
Infometrics
Delta
Background
Infomatrix Framework
Modeling and Influence
Misspecifications
Summary
Example
Summarize
Prediction
Practical Approach
Summarizing
Taught by
Santa Fe Institute
Tags
Related Courses
Discrete Inference and Learning in Artificial VisionÉcole Centrale Paris via Coursera Teaching Literacy Through Film
The British Film Institute via FutureLearn Linear Regression and Modeling
Duke University via Coursera Probability and Statistics
Stanford University via Stanford OpenEdx Statistical Reasoning
Stanford University via Stanford OpenEdx