Frequentism and Bayesianism: A Python-driven Primer
Jake Vanderplas · Proceedings of the Python in Science Conferences · 2014
This paper presents a brief, semi-technical comparison of the essential features of the frequentist and Bayesian approaches to statistical inference, with several illustrative examples implemented in Python.The differences between frequentism and Bayesianism fundamentally stem from differing definitions of probability, a philosophical divide which leads to distinct approaches to the solution of statistical problems as well as contrasting ways of asking and answering questions about unknown parameters.After an example-driven discussion of these differences, we briefly compare several leading Python statistical packages which implement frequentist inference using classical methods and Bayesian inference using Markov Chain Monte Carlo. 1
Cited by 73 works. doi:10.25080/majora-14bd3278-00e Open-access PDF
Authors
References
- AN ESSAY TOWARDS SOLVING A PROBLEM IN THE DOCTRINE OF CHANCES
- All Of Statistic A Concise Course In Statistical Inference
- An invariant form for the prior probability in estimation problems
- Statsmodels: Econometric and Statistical Modeling with Python
- All of Statistics: A Concise Course in Statistical Inference
- Ensemble samplers with affine invariance
- The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
- An essay towards solving a problem in the doctrine of chances
- PyMC: Bayesian Stochastic Modelling inPython
- What is Bayesian statistics?