Bayesian Analysis of Data by the Up-Down Method:
Efficient use of data with a stochastic model
The Japanese Journal of
Psychonomic Science, 2011, Vol.30, 44-55.
上下法データのベイズ的分析
――確率モデルによるデータの活用――
基礎心理学研究、2011、30、44−55.
Summary
Bayesian analysis is applied to experimental data to
effectively exploit information by the up-down method. Comparing Bayesian
analysis to the standard one, which estimates the point of subjective equality
(PSE) by averaging part of the comparison stimuli, confirms the two methods do
not differ in terms of the PSE estimation. However, the standard analysis
estimates only the PSE, whereas Bayesian analysis can also estimate a just
noticeable difference (JND). Estimates of the PSE and JND determine a psychometric
function. These results reveal that the Bayesian analysis is useful and
superior to the standard analysis.
本文全文のpdfファイルはCiNii<http://ci.nii.ac.jp/naid/110008790319>に用意されています。