| | |
Summary: Using a Sample Survey Project to Compare
Classical and Bayesian Approaches for Teaching
Statistical Inference
Jim Albert 1
Bowling Green State University
April 1998
1 Address for correspondence: Department of Mathematics and Statistics, Bowling Green State
University, Bowling Green, OH 43403, USA.
Abstract
This article discusses the teaching of statistical inference in a first statistics class. The
traditional and Bayesian approaches are outlined as two approaches for introducing basic
tenets of inference, and these methods are contrasted in teaching the construction and inter
pretation of an interval estimate for a proportion. A sample survey project is described as
a means of assessing the effectiveness of these two approaches in communicating inference.
There are several advantages of the Bayes viewpoint in performing this survey project, in
cluding the explicit modeling of one's prior opinion by means of a probability distribution,
and the relative ease in reporting statistical conclusions. The results of the projects used in
both traditional and Bayesian classes are described, with a focus on the students' interpre
tation of their confidence intervals. Although students in the Bayes class had more success
|
