Just a place to write down the assignment and how I'm tackling it.
ASSIGNMENT:
Hypothesis Testing: Let’s talk about t-tests, p-values. How are they related? What is it telling you? How does it relate to precision-recall? What are the underlying assumptions?
Bayesian posterior inference: Explain Bayes’ Rule. Write some code to actually perform posterior sampling. Work out an example using conjugate priors. How does this compare with hypothesis testing? What are the underlying assumptions?
If X1 and X2 are your two normal distributions, define X3 as the average of X1 and X2: X3=(X1+X2)/2. X3 will follow a normal distribution with mean (m1+m2)/2 and variance (s21+s22)/4. For
Be prepared to give a short mock “lecture” (30 minutes) about these two topics with your prepared Jupyter notebooks. The Jupyter notebooks are more meant to be notes for yourself and visual aides for your lecture. We’ll be looking for
-
How well you present: remember that this material should be approachable, applied, and not just a series of formulas
-
How well you understand these topics in depth (the mathematics, the underlying assumptions behind ideas, etc ...)
RESOURCES:
https://www.statwing.com/demos/logistic-regression#workspaces/39258
see "One-sample