Edit Number of Uniform Prior Samples

Overview

In the machine learning framework, probabilities are estimated by using the Maximum Likelihood Estimation (MLE) method, in which the probability of each state corresponds to its observed frequency in the data set. As such, MLE is a purely Frequentist approach. However, it is possible to make this method Bayesian, as opposed to Frequentist, by mixing the particles described in a dataset with virtual particles defined by Dirichlet Priors.

The easiest way to define Dirichlet Priors in BayesiaLab is to specify so-called uninformative priors, which state that everything is possible. This uninformative prior knowledge can be represented with a Bayesian network in which all nodes are independent and all states of all nodes are uniformly distributed. This is the approach that BayesiaLab takes to generate Uniform Prior Samples, which facilitates what we used to call Smooth Probability Estimation.

Usage

To access the function, select Edit > Edit Number of Uniform Prior Samples.