A challenge for statistical<br>instructors: Teaching Bayesian inference without discarding the "official"significance tests.


Authors: 
Lecoutre, B., Lecoutre, M.-P., &amp; Grouin, J.-M.
Pages: 
online
Year: 
2001
Publisher: 
Bayesian Methods with Applications to Science, Policy and OfficialStatistics,
URL: 
http://www.univ-rouen.fr/LMRS/Persopage/Lecoutre/telechargements/Lecoutre_et_al-Teaching.pdf
Abstract: 

The use of frequentist Null Hypothesis Significance Testing (NHST) is so<br>an integral part of scientists' behavior that its uses cannot be discontinued<br>by flinging it out of the window. Faced with this situation, our teaching<br>strategy involves a smooth transition towards the Bayesian paradigm. Its<br>general outlines are as follows. (1) To present natural Bayesian interpretations<br>of NHST outcomes to draw attention to their shortcomings. (2) To create<br>as a result of this the need for a change of emphasis in the presentation and<br>interpretation of results. (3) Finally to equip students with a real possibility of<br>thinking sensibly about statistical inference problems and behaving in a more<br>reasonable manner. Our conclusion is that teaching the Bayesian approach in<br>the context of experimental data analysis appears both desirable and feasible.