三类多层中介效应分析方法比较

比较了贝叶斯法、Monte Carlo法和参数Bootstrap法在2-1-1多层中介分析中的表现。结果发现：1)有先验信息的贝叶斯法的中介效应点估计和区间估计都最准确;2)无先验信息的贝叶斯法、Monte Carlo法、偏差校正和未校正的参数Bootstrap法的中介效应点估计和区间估计表现相当,但Monte Carlo法在第Ⅰ类错误率和区间宽度指标上表现略优于其他三种方法,偏差校正的Bootstrap法在统计检验力上表现略优于其他三种方法,但在第Ⅰ类错误率上表现最差;结果表明,当有先验信息时,推荐使用贝叶斯法;当先验信息不可得时,推荐使用Monte Carlo法。     

Underestimation of prior remembering and susceptibility to false memories: two sides of the same coin?

In two studies, we explored whether susceptibility to false memories and the underestimation of prior memories (i.e., forgot-it-all-along effect) tap overlapping memory phenomena. Study 1 investigated this issue by administering the Deese/Roediger–McDermott task (DRM) and the forgot-it-all-along (FIA) task to an undergraduate sample (N = 110). It was furthermore explored how performances on these tasks correlate with clinically relevant traits such as fantasy proneness, dissociative experiences, and cognitive efficiency. Results show that FIA and DRM performances are relatively independent from each other, suggesting that these measures empirically apparently refer to separate dimensions. However, they do not seem to define different profiles in terms of dissociation, fantasy proneness, and cognitive efficiency. Study 2 replicated the finding of relative independence between false memory propensity (as measured with the DRM task) and the underestimation of prior memories (as measured with an autobiographical memory dating task) in people with a history of childhood sexual abuse (N = 35).     

Methodological and empirical developments for the Ratcliff diffusion model of response times and accuracy

Summerfield, Egner, Mangels, and Hirsch (2006) suggested that visual misperception may be triggered by strong yet wrong expectation when sensory data are insufficient. Bar (2003) posits that immediately after stimulus presentation, low frequency spatial information (LFSI) convey the global form of the image which is matched to stored representations in the orbitofrontal cortex to generate predictions of the input. We used signal detection to test whether a strong prediction induced by informative global form, hence reducing the number of possible input matches, would facilitate recognition, but at the price of increasing the rate of misperceptions. Twenty-five participants were presented with target and foil images that shared global form, but differed in details. Pictures with informative global form resulted in higher confidence in recognition and shorter reaction times, but increased false alarms. Predictions of sensory input based on low frequency spatial information allow quick, facilitated recognition. However, the price for speed is the increased rate of misperceptions.     

丁超五易卦探源说

20世纪初,西方文化对中国文化产生强烈冲击,并导致中西文化之间空前交织和会通,处在这一大的文化背景下,丁超五试图会通易学与科学,收集了大量易学文献资料,追溯《易》之源头,探讨了《易》与卜筮、卜筮与科学的关系,提出易道是建立在科学的基础之上的,易学不是专为卜筮而作,易学起源“坤先乾后”等观点。虽然在易学起源问题上他有些提法值得商榷,但对于我们今天探讨易卦起源,揭示易学中的科学思想,解读《周易》中的刚柔关系,把握历史上易与道家互动关系有重要启发意义。     

An investigation of hierarchical Bayes procedures in item response theory

Hierarchical Bayes procedures for the two-parameter logistic item response model were compared for estimating item and ability parameters. Simulated data sets were analyzed via two joint and two marginal Bayesian estimation procedures. The marginal Bayesian estimation procedures yielded consistently smaller root mean square differences than the joint Bayesian estimation procedures for item and ability estimates. As the sample size and test length increased, the four Bayes procedures yielded essentially the same result.The authors wish to thank the Editor and anonymous reviewers for their insightful comments and suggestions.     

A monte carlo study of kruskal's variance based measure on stress

Researchers in the past ten years have studied various parameters involved in nonmetric multidimensional scaling by utilizing Monte Carlo procedures. This paper develops stress distributions using Kruskal's second stress formula based upon a null hypothesis of equal likelihood in the ranking of a set of proximities. These distributions can serve to determine whether a set of data has other than random structure.This research was supported in part by a grant from the Baruch College Scholar Assistance program.     

An elicitation method for multiple linear regression models

This paper describes a method of quantifying subjective opinion about a normal linear regression model. Opinion about the regression coefficients and experimental error is elicited and modeled by a multivariate probability distribution (a Bayesian conjugate prior distribution). The distribution model is richly parameterized and various assessment tasks are used to estimate its parameters. These tasks include the revision of opinion in the light of hypothetical data, the assessment of credible intervals, and a task commonly performed in cue-weighting experiments. A new assessment task is also introduced. In addition, implementation of the method in an interactive computer program is described and the method is illustrated with a practical example.     

Bayesian Extended Redundancy Analysis: A Bayesian Approach to Component-based Regression with Dimension Reduction

Abstract

Extended redundancy analysis (ERA) combines linear regression with dimension reduction to explore the directional relationships between multiple sets of predictors and outcome variables in a parsimonious manner. It aims to extract a component from each set of predictors in such a way that it accounts for the maximum variance of outcome variables. In this article, we extend ERA into the Bayesian framework, called Bayesian ERA (BERA). The advantages of BERA are threefold. First, BERA enables to make statistical inferences based on samples drawn from the joint posterior distribution of parameters obtained from a Markov chain Monte Carlo algorithm. As such, it does not necessitate any resampling method, which is on the other hand required for (frequentist’s) ordinary ERA to test the statistical significance of parameter estimates. Second, it formally incorporates relevant information obtained from previous research into analyses by specifying informative power prior distributions. Third, BERA handles missing data by implementing multiple imputation using a Markov Chain Monte Carlo algorithm, avoiding the potential bias of parameter estimates due to missing data. We assess the performance of BERA through simulation studies and apply BERA to real data regarding academic achievement.     

The influence of chemical cues on the territorial prior residence effect in convict cichlids (cichlasoma nigrofasciatum Günther)

The importance of accumulated chemical cues on the occurrence of the territorial prior residence effect was investigated in two experiments using adult convict cichlids (Cichlasonul nigrofasciatum). In the first experiment, pairs of fish, matched on a number of criteria, were randomly assigned to three independent treatment conditions in which (1) the territorial marker (pot or clump of plants) was removed just prior to a direct encounter in the aquarium of the resident (pair member in whose aquarium the encounter took place) with accumulated chemical cues remaining intact; (2) the marker was removed, as well as the chemical cues; or (3) the marker was present, but the chemical cues were removed. Results showed that a significant prior residence effect occurred when the marker was present, but did not occur in either condition in which the marker was removed. A second experiment, in which the marker was removed and the gravel substrate altered, also did not reveal a signficant prior residence effect. Apparently, the territorial resident recognizes his territory by using certain visual cues, with accumulated chemical cues being neither necessary nor sufficient in this process.