Math 50 Linear regression modeling

Schedule

Before going through Unit 1, please review Unit 0. This material will not be covered in class and it is expected that if you are not already familiar with it, you will learn it by the end of the first week.

Note This schedule is subject to changes throughout the term. Please check this schedule on a weekly basis. Changes will only effect exams in rare circumstances. You should check the commit history on a weekly basis to check if any changes have been made.

Date Unit Material Topics Notes
Week 1      
Mon Sept 15 Unit 1 Intro, Unit 1.1 (Probability models)  
Wed Sept 17 Unit 1 Unit 1.2 (Conditional probability, marginalization)  
Fri Sept 19 Unit 1 Python, working with tabular data Course survey
Week 2      
Mon Sept 22 Unit 2 Unit 2.1 (Expectation, conditional expectation, variance)  
Wed Sept 24 Unit 2 Unit 2.2 (Continuous distributions, Normal distribution and CLT) I didn’t cover continious distributions in detial. This will not be so important for future sections.
Fri Sept 26 Unit 3 Unit 2.3 (linear regression with binary predictor) I introduced the idea of sample distribution in the context of linear regression with binary predictor
Week 3      
Mon Sept 29 Unit 3 Unit 3.1 cont. (estimators, bias, consistency) Unit 3.2 (linear regression with normal predictor)  
Wed Oct 1 Unit 3 Unit 3.2 cont. (Least squares, Correlation, coefficient of determination)  
Fri Oct 3 Unit 3 Unit 3 leftover if needed + Exploratory data analysis/project discussion End of midterm material
Week 4      
Mon Oct 6 Review   Come with questions!
Wed Oct 8 MIDTERM IN CLASS    
Fri Oct 10 Work on project   project progress (on canvas)
Week 5      
Mon Oct 13 Unit 4 Unit 4.1 (Multiple predictor regression examples, interpreting regression coefficients)  
Wed Oct 15 Unit 4 Unit 4.2 (Simpsons paradox, effects of adding predictors)  
Fri Oct 17 Unit 4 Unit 4 (colinearity, the joint sample distribution)  
Week 6      
Mon Oct 20 Unit 4 Unit 4 (models with catagorical predictors)  
Wed Oct 22 Unit 4 Unit 4 (analysis of variance)  
Fri Oct 24 Unit 5 Unit 5 (interactions, residual plots)  
Week 7      
Mon Oct 27 Unit 5 Unit 5 (polynomial regression, linear regression view of fourier series )  
Wed Oct 29 Unit 5 Unit 5(bias-variance trafeoff revisited and overfitting)  
Fri Oct 31 Unit 6 Unit 6.3 (overparamaterized models, ridge and lasso regression)  
Week 8      
Mon Nov 3 Unit 6 Unit 6 (bayesian inference for bernoulli model, beta distribution laplace rule of succession)  
Wed Nov 5 Unit 6 Unit 6 (bayesian linear regression)  
Fri Nov 7 Unit 6 Unit 6 (connection between bayesian inference and regularization) Last day of final material
Week 9      
Mon Nov 10 Unit 7 statistics vs. machine learning, the kernel trick  
Wed Nov 12 Unit 7 Gaussian processes as a Bayesian forier model  
Fri Nov 14 Unit 7 Logistic regression, project  
Week 1      
Mon Nov 17 Review