Introduction
This week I had to study for a job interview at a pretty sweet place. So in preparation for it I’ve read up on statistics that I’ve listed on my resume. I’ve came across a few good papers and I’m just happy to have read it. Just wanted to post it here in case if I ever need a refresher on Bayesian.
Basic Master Level Statistic
Introductory Mathematical Statistics Methods of Estimation and Properties of Point Estimators: Fundamental Exercises with Solutions by Dr. Olga Korosteleva
This is written by my professor and it was in a neat package of overview of what I’ve learned in my master program. It is a good refresher. There were some notes I’ve written for clarifications:
- MLE - This selects the parameter values that make the data most probable
- Likelihood (frequentist point of view) - is a function of the parameters of a statistical model, given specific observed data.
- Method of Moments Estimators (MOM) & MLE are two estimator methods to do point estimation for parameter. This is the frequentist point of view on estimating parameters which are fixed. Where as Bayesian model parameter as a random variable and not a fixed point.
- Fisher information - is a way of measuring the amount of information that an observable random variable X carries about an unknown parameter theta of a distribution models X.
- Cramer-Rao Lower Bound - expresses a lower-bound on the variance of unbiased estimators of a deterministic parameter. An unbiased estimator which achieves this lower bound is efficient.
- Sufficient Statistic - a statistic that summarize all of the information in a sample about the desired parameter. (Penn State have more clarification on this).
Bayesian Review
On Bayesian Data Analysis by Christian P. Robert and Judith Rousseau (August 27, 2018)
Point estimation parameter vs parameter with distribution. Credible Interval vs Confidence Interval. Critiques of Bayesian and solutions.
An Introduction to Bayesian Statistics Without Using Equations by Tomoharu Eguchi (2008)
Great visualization take on how to explain Bayesian Statistic.
A tutorial on Bayesian nonparametric models by Samuel J. Gershman and David M. Blei (2012)
A review what I used during my time at the FDA.
Credits
First picture: https://pixabay.com/en/book-magnifying-glass-glass-2304078/