无法重复实验结果在何时不构成II类错误？
When is a failure to replicate not a type II error?
作者信息
Vasconcelos Marco, Urcuioli Peter J, Lionello-DeNolf Karen M
机构信息
Department of Psychological Sciences, Purdue University, 703 Third Street, West Lafayette, IN 47907, USA.
出版信息
J Exp Anal Behav. 2007 May;87(3):405-7. doi: 10.1901/jeab.2007.10-07.
Zentall and Singer (2007) challenge our conclusion that the work-ethic effect reported by Clement, Feltus, Kaiser, and Zentall (2000) may have been a Type I error by arguing that (a) the effect has been extensively replicated and (b) the amount of overtraining our pigeons received may not have been sufficient to produce it. We believe that our conclusion is warranted because (a) the original effect has not been replicated despite multiple attempts to do so and (b) the statement that more extended overtraining may be needed itself suggests that the original effect is not reliable.
曾塔尔和辛格（2007年）对我们的结论提出质疑，我们的结论是，克莱门特、费尔图斯、凯泽和曾塔尔（2000年）所报告的职业道德效应可能是I型错误，他们的理由是：（a）该效应已被广泛重复验证；（b）我们的鸽子接受的过度训练量可能不足以产生该效应。我们认为我们的结论是有依据的，因为：（a）尽管多次尝试，但原始效应并未得到重复验证；（b）认为可能需要更长时间的过度训练这一说法本身就表明原始效应不可靠。
Zotero 插件