# Bayesian Inference **Bayesian inference is concerned with beliefs about what λ might be**. Rather than trying to guess λ exactly, we can only talk about what λ is likely to be by assigning a probability distribution to λ. This might seem odd at first. After all, λ is fixed; it is not (necessarily) random! How can we assign probabilities to values of a non-random variable? Uh-oh; we have fallen for our old, frequentist way of thinking. Recall that under Bayesian philosophy, we can assign probabilities if we interpret them as beliefs. And it is entirely acceptable to have beliefs about the parameter λ. --- Date: 20220522 Links to: [Bayesian Inference](Bayesian%20Inference.md) Tags: #review References: * Bayesian Methods for Hackers, Chapter 1