It is not seldom that I encounter the following question while marketing a solution: “What are the hypothesis you are testing for and how will you prove or disprove it?”, thereby alluding to standard hypothesis testing techniques. 3,238 more words
Tags » Bayesian
In this week’s lab meeting, I presented:
This paper describes a class of latent variable models inspired by deep neural net and hierarchical generative model, called Deep Exponential Families (DEFs). 349 more words
Dan Georgescu & Manuel Sales.
Capital requirements for financial institutions are typically calculated using a statistical model and a risk measure such as VaR, whereas stress tests designed by regulators and risk managers are often based on subjective scenarios with no associated probability level. 1,571 more words
19th century statistics was Bayesian while the 20th century was Frequentist, at least from the point of view of most scientific practitioners. The Bayesian-Frequentist debate reflects two different attitudes to the process of doing modeling, both looks quite legitimate. 405 more words
The Big Questions: Where, how and when were monuments built, used and perceived by the people who built them and others, coming after, who re-used them?
The construction of detailed chronologies of when the monuments were built and used will not only draw on AMS 14C dating but also optically stimulated luminescence on stone structures and sediments that otherwise cannot be dated, and innovative cosmogenic nuclide dating, all within Bayesian frameworks. 228 more words
I gave a lecture this last weekend on the application of probability theory to modern epistemology. It outlines a lot of my own thoughts about the mistakes in public discourse when we talk about the confidence and certainty. 95 more words