p-values and hypothesis tests: the Bayesian(s) rule

The American Statistical Association of which I am a longtime member issued an important statement today which will hopefully move statistical practice in engineering and especially in the sciences away from the misleading practice of using p-values and hypothesis tests. There are many fields in which these remain acceptable practices, despite their well known drawbacks, e.g., climate sciences, and despite there being several good alternatives, e.g., already in use in these fields (also here, here, and here).

The detailed statement is here, and there is a discussion available.

Demidenko offers a contrasting perspective in the context of Big Data, which is interesting, even if it doesn’t address the full range of benefits alternatives to hypothesis testing provide.

Update, 2017-10-18

Professor Deborah Mayo offers a blog post on “Deconstructing a `World Beyond p-Values`”.

About hypergeometric

See http://www.linkedin.com/in/deepdevelopment/ and https://667-per-cm.net/about
This entry was posted in approximate Bayesian computation, arXiv, Bayes, Bayesian, Bayesian inversion, bollocks, Christian Robert, climate, complex systems, data science, Frequentist, information theoretic statistics, likelihood-free, Markov Chain Monte Carlo, MCMC, Monte Carlo Statistical Methods, population biology, rationality, reasonableness, science, scientific publishing, statistical dependence, statistics, stochastics, Student t distribution. Bookmark the permalink.