Evaluating interobserver reliability of interval data

Previous recommendations to employ occurrence, nonoccurrence, and overall estimates of interobserver reliability for interval data are reviewed. A rationale for comparing obtained reliability to reliability that would result from a random-chance model is explained. Formulae and graphic functions are presented to allow for the determination of chance agreement for each of the three indices, given any obtained per cent of intervals in which a response is recorded to occur. All indices are interpretable throughout the range of possible obtained values for the per cent of intervals in which a response is recorded. The level of chance agreement simply changes with changing values. Statistical procedures that could be used to determine whether obtained reliability is significantly superior to chance reliability are reviewed. These procedures are rejected because they yield significance levels that are partly a function of sample sizes and because there are no general rules to govern acceptable significance levels depending on the sizes of samples employed.     

A SIMPLIFIED TIME-SERIES ANALYSIS FOR EVALUATING TREATMENT INTERVENTIONS

Time-series analysis procedures for analyzing behavioral data are receiving increasing support. However, several authorities strongly recommend using at least 50–100 points per experimental phase. A complex mathematical model must then be empirically developed using computer programs to extract serial dependency from the data before the effects of treatment interventions can be evaluated. The present discussion provides a simple method of evaluating intervention effects that can be used with as few as 8 points per experimental phase. The calculations are easy enough to do by hand.     

The stability and clinical significance of distress: A rejoinder to pepper and coyne

Past research has established that some individuals with high Beck Depression Inventory (BDI) scores at one time point have scores that are lower at a second time point. Recently, we provided evidence indicating that the temporal instability of certain BDI scores may be due partly to the regression to the mean phenomenon. Pepper and Coyne (1996) question this statistical interpretation; they argue that distress among students is unstable for substantive reasons. In the current paper, we reaffirm our view that statistical and measurement factors may account, in part, for changes in BDI scores over time. Given this possibility, inferences about distress or depression as a latent construct in student samples are not warranted if these inferences are based on the administration of a single instrument such as the BDI; any conclusions about distress as a psychological construct must be qualified by acknowledging the possible roles of error and method variance. Clearly, empirical research is needed in order to obtain a better understanding of the nature of distress as a latent variable, especially in light of evidence which indicates that subthreshold levels of depression have a high degree of clinical significance.     

Assessing local influence for specific restricted likelihood: Application to factor analysis

In restricted statistical models, since the first derivatives of the likelihood displacement are often nonzero, the commonly adopted formulation for local influence analysis is not appropriate. However, there are two kinds of model restrictions in which the first derivatives of the likelihood displacement are still zero. General formulas for assessing local influence under these restrictions are derived and applied to factor analysis as the usually used restriction in factor analysis satisfies the conditions. Various influence schemes are introduced and a comparison to the influence function approach is discussed. It is also shown that local influence for factor analysis is invariant to the scale of the data and is independent of the rotation of the factor loadings. The authors are most grateful to the referees, the Associate Editor, and the Editor for helpful suggestions for improving the clarity of the paper.     

检验能力对统计显著性检验的影响

利用计算机构造被试总体、模拟实验研究程序进行抽样研究,探讨抽样样本总体达到t检验显著性的数目与统计检验能力之间的一致性。模拟实验结果表明,统计检验能力与样本总体t检验显著性的数目具有很高的一致性,但两者同时受到显著性水平α、样本客量n和总体效果大小δ的影响,从而有可能影响统计推断的可靠性。因此,在进行显著性检验过程中,应对统计检验能力进行估计,这将有利于心理学研究成果的积累。     

内隐和外显记忆测验的信度比较研究及思考

任务分离的实验范式以功能分离和随机独立性等证据说明不同记忆任务的底层系统或加工机制。近期研究发现,两种记忆测量重测信度、复本信度和分半信度差异显著,内隐测验的信度更低一些,因而对变量效果缺乏足够的敏感性。两种测验信度差异对任务分离提出了区别于系统说或加工观点的另外解释。以后在研究外显和内隐记忆分离的时候应该慎重考虑测验信度的检验问题,还应通过各种方法来提高内隐记忆测验的信度,使两种记忆测验的信度具有可比性。     

Cardinality without Enumeration

We show that the notion of cardinality of a set is independent from that of wellordering, and that reasonable total notions of cardinality exist in every model of ZF where the axiom of choice fails. Such notions are either definable in a simple and natural way, or non-definable, produced by forcing. Analogous cardinality notions exist in nonstandard models of arithmetic admitting nontrivial automorphisms. Certain motivating phenomena from quantum mechanics are also discussed in the Appendix.     

THE FALSE PROMISE OF QUANTUM MECHANICS

The causal indeterminacy suggested by quantum mechanics has led to its being the centerpiece of several proposals for divine action that does not contradict natural laws. However, even if the theoretical concerns about the reality of causal indeterminacy are ignored, quantum‐level divine action fails to resolve the problem of ongoing, responsive divine activity. This is because most quantum‐level actions require a significant period of time in order to reach macroscopic levels whether via chaotic amplification or complete divine control of quantum events. Therefore, quantum‐level divine action either requires divine foreknowledge of purportedly free or random events or imposes such limitations on divine actions that they become late, potentially impotent, and confused. I argue that the theological problem of divine action remains; even at its most promising, quantum mechanics offers insufficient resolution. This failure suggests a reexamination of the assumptions that God is temporal and lacks foreknowledge of future contingencies.     

统计概要表征的内容与机制

人类能够快速提取集合刺激中的统计信息, 并形成以集中趋势和变异性为主要内容的统计概要表征。根据注意资源的使用, 统计概要表征的加工方式可分为分布式注意下的整体加工和聚焦注意下的个体加工。两种加工在工作记忆中相互影响, 共同构建了对集合刺激的表征。统计概要表征适用于多种刺激类型, 发生在低水平和高水平加工中, 因而可能是一种普遍的知觉加工方式。未来研究可关注统计概要表征的神经基础及其对决策的影响。