“Classical” statistics

There is a tendency to describe traditional frequentist methods as “classical” statistics, often making a contrast with modern Bayesian methods, which are (or at least appear in ther modern guise) much newer and a break with tradition. That’s kind of fair enough but I don’t like the term classical being applied to traditional statistics, for two main reasons.

1. “Classical” is already in use for describing other types of thing (music. literature, architecture) and it has connotations of quality that aren’t really applicable to statistics. These are classical:



2. It’s inaccurate. Frequentist statistics dates from the mid 20th century. Bayesian statistics goes back much further, to Laplace (early 19th century) and Bayes (18th century) – so if anything should be called “classical”, it is the Bayesian approach.


Original post http://blogs.warwick.ac.uk/simongates/entry/classical_statistics/  25 January 2015


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s