L4: Interpretable Linear Regressions (State of Bayes Lecture Series)

State of Bayes is a series of webinars about advances in practical methods and modeling intuition. The major focus of the webinar series will be on understanding concepts of advanced statistical models and introducing prior knowledge into the loop. This free course will be interesting for Bayesian practitioners who want to deepen their understanding about Bayesian modeling. #InterpretableRegression #ExplainableAI #LinearModeling #TransparencyInML #FeatureImportance #ModelInterpretability #RegressionAnalysis #statisticalmodeling #PredictiveAnalytics #DataScienceInsights #LinearRegressions #Bayesianmodeling #BayesianThinking #Hierarchicalmodelling #interpretableLinearRegressions #BayesianABtesting #GaussianProcesses #TimeSeries a) Sign up on Meetup for the live events: https://www.meetup.com/pymc-labs-online-meetup/ b) State of Bayes Lecture Series playlist: https://www.youtube.com/playlist?list=PL1iMFW7frOOsh5KOcfvKWM12bjh8zs9BQ Slides: https://drive.google.com/file/d/1X_QBDRpdetNom5tu9dxt-PbxJyiTBmGi/view The full course will include: 1: Introduction 2: Bayesian Thinking 3: Hierarchical modelling 4: Interpretable Linear Regressions 5: Bayesian AB testing 6: Gaussian Processes 7: Gaussian Processes for Time Series ## About the speaker Maxim Kochurov Maxim is a core developer of PyMC, a probabilistic programming language. Since the foundation of PyMC Labs he helps to improve complex statistical models and create a reusable solution. Besides strong expertise in Bayesian modeling his background includes economics, software engineering, and large-scale computer vision. LinkedIn: https://www.linkedin.com/in/ferrine Twitter: https://twitter.com/ferrine96 GitHub: https://github.com/ferrine Website: https://ferrine.github.io ## Connecting with PyMC Labs - LinkedIn: https://www.linkedin.com/company/pymc-labs/ - Twitter: https://twitter.com/pymc_labs ## Lecture 4 timestamps 00:00:00 Introduction 00:00:24 Agenda 00:01:14 Why linear regression is a thing? 00:02:16 Notation 00:03:13 More than just linear 00:04:33 GLMs: Understanding basics 00:05:45 Heteroscedasticity 00:06:29 Other Likelihoods 00:07:34 Estimations 00:08:41 Priors 00:09:39 Setting priors 00:11:31 The more parameters, the bigger the issue 00:12:36 A quick Fix 00:13:50 A practical approach 00:15:13 What we know that we know 00:16:28 The R squared prior 00:19:10 Setting R squared prior 00:21:36 Prior R squared 00:23:56 Feel the difference? 00:24:43 Variable importance 00:26:43 What is variable importance? 00:28:42 Understanding FVE prior 00:31:00 Alpha FVE in Examples 00:33:45 Alpha FVE and R squared 00:34:33 Putting it all together 00:37:50 Can we add More? R2D2M2CP 00:40:00 Technical Details 00:41:18 Can we add more? R2D2M2CP 00:41:39 Technical Details 00:41:49 Putting all together 00:42:31 Back to GLMs 00:44:04 Remarks 00:45:44 Q/A Clarify when to use T distribution ...? 00:47:07 Q/A would you use this prior also in media mix modelling ...? 01:13:34 Q/A Phi interpretation 01:20:39 Webinar ends #bayes #statistics #probabilistic