A statistical analysis system (SAS) computer program for Markov chain analysis

A computer program for Markov chain analysis is presented and discussed. The program is written in the language of the Statistical Analysis System (SAS) but detailed knowledge of SAS is not required for its use. The program tests hypotheses about the goodness of fit of first- and second-order Markov models. It also tests if transition probabilities are homogeneous between the first and the second half of each sequence.Presented, in part, at the Association for the Advancement of Behavior Therapy Convention, November 1984.     

Effects of serial dependency on the agreement between visual and statistical inference

Comparisons between visual and time-series inferences from behavioral data show that serial dependency in scores is likely to disrupt agreement between the two methods of analysis. If researchers follow an earlier recommendation that time-series analysis be used to supplement or confirm visual analysis, this study's findings suggest that the two methods will disagree most often when the data contain high levels of autocorrelation and when reliable behavorial changes are indicated by time-series analysis.     

On the large sample distributions of modified sample biserial correlation coefficients

The asymptotic distributions of Brogden's and Lord's modified sample biserial correlation coefficients are derived. The asymptotic variances of these estimators are evaluated for bivariate normal populations and compared to the asymptotic variance of the maximum likelihood estimator.The author would like to thank the referees for several suggestions which improved the presentation of the paper.     

Alternative test criteria in covariance structure analysis: A unified approach

In the context of covariance structure analysis, a unified approach to the asymptotic theory of alternative test criteria for testing parametric restrictions is provided. The discussion develops within a general framework that distinguishes whether or not the fitting function is asymptotically optimal, and allows the null and alternative hypothesis to be only approximations of the true model. Also, the equivalent of the information matrix, and the asymptotic covariance matrix of the vector of summary statistics, are allowed to be singular. When the fitting function is not asymptotically optimal, test statistics which have asymptotically a chi-square distribution are developed as a natural generalization of more classical ones. Issues relevant for power analysis, and the asymptotic theory of a testing related statistic, are also investigated.This research has been supported by the U.S.-Spanish Joint Committee for Cultural and Educational Cooperation, grant number V-B.854020. The author wishes to express his gratitude to P. M. Bentler who provided very helpful suggestions and research facilities—with an stimulating working environment—at the University of California, Los Angeles, where this work was undertaken. Thanks are also due to W. E. Saris who provided very valuable comments to earlier versions of this paper. Finally, it has also to be acknowledged the editor's and reviewers suggestions which led to substantial improvements of this article.     

Perception of ensemble statistics requires attention

To overcome inherent limitations in perceptual bandwidth, many aspects of the visual world are represented as summary statistics (e.g., average size, orientation, or density of objects). Here, we investigated the relationship between summary (ensemble) statistics and visual attention. Recently, it was claimed that one ensemble statistic in particular, color diversity, can be perceived without focal attention. However, a broader debate exists over the attentional requirements of conscious perception, and it is possible that some form of attention is necessary for ensemble perception. To test this idea, we employed a modified inattentional blindness paradigm and found that multiple types of summary statistics (color and size) often go unnoticed without attention. In addition, we found attentional costs in dual-task situations, further implicating a role for attention in statistical perception. Overall, we conclude that while visual ensembles may be processed efficiently, some amount of attention is necessary for conscious perception of ensemble statistics.     

兼顾两种匹配的考试抄袭统计量研究评述

考试抄袭统计量是专门用于识别抄袭的统计指标。它们是以被怀疑抄袭者和抄袭来源匹配反应的数目为基础建立的,按其考虑的匹配反应信息可分为两类:一类只考虑被怀疑抄袭者和抄袭来源间的错误答案匹配;另一类同时考虑两者错误答案匹配和正确答案匹配。由于第一类抄袭统计量对那些只从抄袭来源处抄袭正确答案的抄袭者检测不敏感,所以存在缺陷;第二类抄袭统计量兼顾两种匹配,考虑的信息更全面。s2、g2、ω是具有代表性的第二类抄袭统计量,它们在测量理论基础、被怀疑抄袭者和抄袭来源的异常相似反应模式确定方法及考试抄袭检测效能等方面存在差异,在抄袭识别应用中应合理选择。     

Hypercorrection of high confidence errors: Prior testing both enhances delayed performance and blocks the return of the errors

How people correct their mistakes and sustain those corrections over time is a problem of central interest to education. It might be thought that the erroneous beliefs that people hold with high confidence would be especially difficult to correct. Interestingly, people correct these high confidence errors more easily than low confidence errors, a phenomenon known as the ‘hypercorrection effect’. Unfortunately, though, with a delay in testing there is a tendency for some of these high confidence errors to reemerge – a finding with serious consequences for education. This study investigated the effect of intervening a test immediately after corrective feedback on preventing the return of the errors. It also investigated processing differences between prevention-focused and promotion-focused people. The most educationally important new finding was that testing immediately after corrective feedback not only greatly enhanced memory for the correct answers but also blocked the return of the errors.     

Routine cognitive errors: A trait-like predictor of individual differences in anxiety and distress

Five studies (N=361) sought to model a class of errors—namely, those in routine tasks—that several literatures have suggested may predispose individuals to higher levels of emotional distress. Individual differences in error frequency were assessed in choice reaction-time tasks of a routine cognitive type. In Study 1, it was found that tendencies toward error in such tasks exhibit trait-like stability over time. In Study 3, it was found that tendencies toward error exhibit trait-like consistency across different tasks. Higher error frequency, in turn, predicted higher levels of negative affect, general distress symptoms, displayed levels of negative emotion during an interview, and momentary experiences of negative emotion in daily life (Studies 2–5). In all cases, such predictive relations remained significant with individual differences in neuroticism controlled. The results thus converge on the idea that error frequency in simple cognitive tasks is a significant and consequential predictor of emotional distress in everyday life. The results are novel, but discussed within the context of the wider literatures that informed them.     

Socio-Cultural Learning as a 'Transcendental Fact': Habermas's Postmetaphysical Perspective

In the Discourse on Metaphysics Leibniz writes, 'Our perceptions are always true, it is our judgments that come from ourselves that deceive us' (section 14). Leroy Loemker in his 'Leibniz's Doctrine of Ideas' criticizes this account of error. His main worry can be presented in the form of the following syllogistic argument, which he derives from Leibniz's doctrine of ideas: (a) There cannot be a false perception; (b) All judgments are perceptions; and therefore (c) There cannot be a false judgment. However, in this paper I argue that Leibniz can distinguish between a perception and a judgment in their semantic aspect. The sense in which a perception turns out to be false (or true) for Leibniz is different from the sense in which a judgment turns out to be false (or true). This is because, while a perception, understood in Leibniz's terms, lacks truth-conditions, a judgment, in being representational, has such conditions. Thus while a perception remains true always, a judgment can be false. Pointing to the equivocal use of 'false' in (a) and (c) above, I conclude that (c) does not follow from (a) and (b).