Livestream: How to think about Bayesian, frequentist, and likelihoodist methods

NOTE: Please sign-in at via the Livestream link below. Thank you!
https://livestream.com/metis/events/7560442

https://secure.meetupstatic.com/photos/event/5/6/0/b/600_462382027.jpeg

Greg Gandenberger is a data scientist at Uptake. He has a Ph.D. in History and Philosophy of Science from the University of Pittsburgh.

There are longstanding debates about whether frequentist or Bayesian methods are more appropriate for evaluating the outcomes of A/B tests. According to many accounts, the main point at issue in these debates is whether probabilities are long-run frequencies or degrees of belief. These accounts are not helpful to practitioners, because whether a frequentist or Bayesian approach will work better for a given problem has little if anything to do with the true nature of probability. I provide a different perspective on these debates that keeps the focus on methodological issues: frequentist and Bayesian methods, as well as methods of a third kind called "likelihoodist," are different responses to the inadequacy of the apparent truism that one should proportion one's beliefs to one's evidence.

Warning: This talk addresses issues that are valuable for data practitioners to understand, but it does not contain any code and is not immediately practical.

The following blog posts provide useful background for this talk:

http://gandenberger.org/2014/07/21/intro-to-statistical-methods/

http://gandenberger.org/2014/07/28/intro-to-statistical-methods-2/

http://gandenberger.org/2014/08/26/intro-to-statistical-methods-3/

Metis has partnered with PyData (https://www.meetup.com/PyDataChi/) for this event.

About Metis

https://secure.meetupstatic.com/photos/event/6/d/e/3/600_460828131.jpeg

Metis (thisismetis.com) accelerates careers in data science by providing full-time immersive bootcamps, evening part-time professional development courses, online resources, and corporate programs based in Seattle, New York, Chicago, and San Francisco.

Brought to you by Kaplan, Metis focuses primarily on Python, machine learning, data visualization, deep learning, big data processing, statistical foundations, and more. Students and alumni of the bootcamp program receive continuous support from our career advisors, empowering them to pursue a successful career in the fast-growing field of data science.

Learn more about us at https://thisismetis.c... (https://thisismetis.com/).

Sign up for Demystifying Data Science: A Free Online Conference
https://www.thisismetis.com/demystifying-data-science

Join our Metis Community Slack channel! Apply here: https://bit.ly/metis-... (https://bit.ly/metis-community-slack)

Metis Code of Conduct

Metis is dedicated to providing a harassment-free experience for everyone, regardless of gender identity, age, sexual orientation, disability, physical appearance, body size, race, or religion (or lack thereof).

We do not tolerate harassment of students, staff, or visitors in any form. Sexual language and imagery is not appropriate for any event including talks, workshops, parties, and other online media. Individuals and groups that do not abide by these rules will be asked to leave and, if necessary, prohibited from future events.

If you have any questions or you're made to feel uncomfortable by anyone on our campus or at one of our offsite events, please let one of the staff members know right away. The matter will be taken seriously and promptly addressed.