文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > 自然科学 > 数学 > BayesSDT Software for Bayesian inference with signal detection theory
侵权投诉

BayesSDT Software for Bayesian inference with signal detection theory

454 LEE

Figure 3. The BayesSDT graphical user interface.

D.labels is a character array with a string label

for each data set.

D.linecolor is a character array with a MATLAB color for each data set, using the standard MATLAB plot colors.

D.linestyle is a character array with a MATLAB color for each data set, using the standard MATLAB line styles.

D.linewidth is an array of positive numbers con-taining line widths for each data set.

D.dcheck, D.hcheck, D.fcheck, D.kcheck, D.ccheck, and D.bcheck are vectors of 0 and 1 entries for each data set, indicating whether or not the d , h, f, k, c, and ; parameters, respectively, should be analyzed.

The BayesSDT function generates graphs of posterior distributions for the analyzed parameters. It also returns two structured variables—samples and stats— returned by WinBUGS. The fields in samples give the full list of posterior samples of each parameter for each data set. These samples allow more advanced Bayesian analyses based on the full-joint posterior distribution

BayesSDT Software for Bayesian inference with signal detection theory

(e.g., Lee, 2008). The fields in stats provide means and standard deviations for the posterior samples of each parameter for each data set. The syntax for the Bayes-SDT function call is simply [samples stats] BayesSDT(D).

Conclusion

SDT is a highly useful and widely used method for ana-lyzing psychological data. Bayesian inference for SDT has a number of attractive properties, using the full poste-rior distributions of parameters to represent what is known about discriminability, bias, criterion, and hit and false alarm rates. The BayesSDT software package provides a simple WinBUGS implementation of a suitable Bayesian graphical model and provides a MATLAB GUI and func-tion call for performing the Bayesian analysis.

AUTHOR NOTE

I thank Douglas Creelman and two anonymous reviewers for help-ful comments, and Joachim Vandekerckhove, Andrew Heathcote, and Geoff Iverson for useful discussions. Correspondence concerning this article should be addressed to M. D. Lee, Department of Cognitive Sci-ences, University of California, 3151 Social Sciences Plaza, Irvine, CA 92697-5100 (e-mail: mdlee@uci.edu).

上一页第5页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email