Lecture 21 – Inference for Modeling
Presented by Fernando Perez and Suraj Rampure
Content by Suraj Rampure, Fernando Perez, John DeNero, Sam Lau, Ani Adhikari, Deb Nolan
The Data 8 textbook chapter on estimation may be very helpful.
The Quick Check for this lecture is due Monday, November 23rd at 11:59PM. A random one of the following Google Forms will give you an alphanumeric code once you submit; you should take this code and enter it into the “Lecture 21” question in the “Quick Check Codes” assignment on Gradescope to get credit for submitting this Quick Check.
A big picture overview of inference. Parameters and estimators. Bias and variance of estimators. The sample mean estimator.
Using bootstrap resampling in order to estimate the sampling distribution of an estimator.
Defining confidence intervals more generally. Describing and demoing how we can use the bootstrap to create confidence intervals for population parameters.
The assumptions we make when modeling with linear regression..
Using the bootstrap to estimate the sampling distributions of parameters in a linear regression model. Inference for the true slope of a feature.
Multicollinearity, and its impacts on the interpretability of the parameters of our model. A summary of the lecture, and a brief overview of the ML taxonomy.