Identifying Variables Responsible for Data not Missing at Random

When data are not missing at random (NMAR), maximum likelihood (ML) procedure will not generate consistent parameter estimates unless the missing data mechanism is correctly modeled. Understanding NMAR mechanism in a data set would allow one to better use the ML methodology. A survey or questionnaire may contain many items; certain items may be responsible for NMAR values in other items. The paper develops statistical procedures to identify the responsible items. By comparing ML estimates (MLE), statistics are developed to test whether the MLEs are changed when excluding items. The items that cause a significant change of the MLEs are responsible for the NMAR mechanism. Normal distribution is used for obtaining the MLEs; a sandwich-type covariance matrix is used to account for distribution violations. The class of nonnormal distributions within which the procedure is valid is provided. Both saturated and structural models are considered. Effect sizes are also defined and studied. The results indicate that more missing data in a sample does not necessarily imply more significant test statistics due to smaller effect sizes. Knowing the true population means and covariances or the parameter values in structural equation models may not make things easier either. The research was supported by NSF grant DMS04-37167, the James McKeen Cattell Fund.     

When the mental number line involves a delay: the writing of numbers by children of different arithmetical abilities

Our study focused on number transcoding in children. It investigated how 9-year-olds with and without arithmetical disabilities wrote Arabic digits after they had heard them as number words. Planning time before writing each digit was registered. Analyses revealed that the two groups differed not only in arithmetical abilities but also in verbal and reading abilities. Children with arithmetical disabilities were overall slower in planning Arabic digits than were control children with normal arithmetical abilities. In addition, they showed a number size effect for numbers smaller than 10, suggesting a semantically mediated route in number processing. Control children did not need more planning time for large numbers (e.g., 8) than for small numbers (e.g., 3), suggesting a direct nonsemantic route. For both two- and three-digit numbers, both groups of children showed a number size effect, although the effect was smaller each time for control children. The presence of the stronger number size effect for children with arithmetical disabilities was seen as a delay in the development of quick and direct transcoding. The relation between transcoding problems and arithmetical disabilities is discussed. A defect in the linking of numerical symbols to analog numerical representations is proposed as an explanation for the transcoding problems found in some children.     

Horse (Equus caballus) whinnies: a source of social information

Many animal species that rely mainly on calls to communicate produce individual acoustic structures, but we wondered whether individuals of species better known as visual communicants, with small vocal repertoires, would also exhibit individual distinctiveness in calls. Moreover, theoretical advances concerning the evolution of social intelligence are usually based on primate species data, but relatively little is known about the social cognitive capacities of non-primate mammals. However, some non-primate species demonstrate auditory recognition of social categories and possess mental representation of their social network. Horses (Equus caballus) form stable social networks and although they display a large range of visual signals, they also use long-distance whinny calls to maintain contact. Here, we investigated the potential existence of individual acoustic signatures in whinny calls and the ability of horses to discriminate by ear individuals varying in their degree of familiarity. Our analysis of the acoustic structure of whinnies of 30 adult domestic horses (ten stallions, ten geldings, ten mares) revealed that some of the frequency and temporal parameters carried reliable information about the caller’s sex, body size and identity. However, no correlations with age were found. Playback experiments evaluated the behavioural significance of this variability. Twelve horses heard either control white noise or whinnies emitted by group members, familiar neighbours or unfamiliar horses. While control sounds did not induce any particular response, horses discriminated the social category of the callers and reacted with a sound-specific behaviour (vigilance and attraction varied with familiarity). Our results support the existence of social knowledge in horses and suggest a process of vocal coding/decoding of information.     

数量化维度特征搜索的影响因素探索

有关数量化维度特征搜索的研究表明 ,目标搜索斜率 (反应时间对呈现项目数量函数的斜率 )是由目标与干扰子之间的差异决定的 ,然而以往研究中其差异的值取决于具体的实验条件。根据韦伯定律 ,笔者推测 ,目标搜索斜率应由目标与干扰子之间的相对差异 (C)决定 ,C为目标值 (T)与干扰子值 (D)的差值与该干扰子值的比值。当C值对应相等时 ,不同几何形状刺激的目标搜索斜率应无差异。为此笔者分别采用圆 (实验一 )和三角形 (实验二 )进行实验研究。实验结果支持了上述假设 ,并发现目标大于干扰子时的目标搜索斜率对C值的函数是单调递减函数     

固定位置区域提示下视觉注意范围等级的ERP研究

研究视觉空间注意中注意范围的脑内时程的动态变化。被试为 14名青年人 ,使用固定位置的、3种不同直径的线圈作为注意范围的区域性提示 ,祛除空间定位因素的影响 ,记录反应时和事件相关电位 (ERP)数据。结果显示 :提示范围由小到中等时 ,反应时延长 ,而由中等到大范围时 ,反应时缩短 ;提示物和靶刺激诱发ERP的早成分 (N1、P1)不受提示范围大小的调节 ,而其P2、N2的波幅与潜伏期均明显受到提示范围大小的影响。这些结果说明 :①视觉注意诱发的P1、N1成分 ,主要与空间定位信息的加工相关 ;②提示物诱发的P2、N2成分与注意范围相关 ;③在视觉信息加工过程中 ,空间位置的信息要早于其它信息被加工 ,支持视觉信息串行加工观点     

A Statistical Interpretive Method for Neuropsychological Test Data

The accurate interpretation of large numbers of neuropsychological tests within a flexible battery approach is a difficult and sometimes controversial process. We present a statistically based method of interpretation (Rohling's Interpretive Method or RIM) and evaluation of neuropsychological data that allows for varying numbers of tests along a varying number of cognitive domains, yet remains psychometrically based. This method requires informed clinical judgment in that the level of confidence for tests, cognitive domains, and global indices are used as the backdrop for interpretive decisions. Specific procedures for use are presented in a systematic, detailed fashion to allow the interested reader to replicate the method. Two case examples are presented: a straightforward case of cerebrovascular insult and a more complicated case of mixed etiology. Examples include a variety of different neuropsychological tests commonly used in a flexible battery approach. A discussion of the practicality, ease of use, and potential limitations of this method are further presented.     

基于两水平回归模型的调节效应分析及其效应量

使用多元回归法进行调节效应分析在社科领域已常有应用。简述了目前多元回归法的调节效应分析存在的不足,包括人为变换检验模型、自变量和调节变量区分不足、误差方差齐性的假设难以满足、调节效应量指标ΔR²没有直接测量调节变量对自变量与因变量关系的调节程度。比较好的方法是用两水平回归模型进行调节效应分析并使用相应的效应量指标。在介绍新方法和新效应量后,总结出一套调节效应的分析流程,通过一个例子来演示如何用Mplus软件进行两水平回归模型的调节效应及其效应量分析。最后讨论了两水平回归模型的调节效应分析的发展,包括稳健的调节效应分析、潜变量的调节效应分析、有调节的中介效应分析和有中介的调节效应分析等。     

Perceived social context and risk preference: A re-examination of framing effects in a life-death decision problem

This study examines the effects of perceived group context on subjects risk attitudes and their sensitivity to the framing of choice outcomes in a ‘life-death’ decision problem. It seeks to uncover the psychological mechanisms underlying decision-making biases by systematically manipulating the decision context in which the ‘life-death’ problem was described. The study revealed that subjects risk preferences varied as a function of the experimental manipulations. Previously observed reversals in preferences (framing effects) appeared in large-group contexts and disappeared in small-group and family contexts. When considering the fate of small groups, subjects unambiguously favored the probabilistic outcome, no matter how the ‘life-death’ decision problem was framed. The empirical data obtained from the present study suggest that human choice patterns are behaviorally distinguishable across large-group, small-group, and family social contexts.     

差数显著性t检验与元分析的对比研究

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,探讨显著性ｔ检验方法与元分析方法在检验实验结果数据方面的差异。在模拟实验过程中,ｔ验受到显著性水平、样本容量和总体效果大小的影响,因此最终影响了统计推断的可靠性,建议：在进行显著性检验过程中,应对统计检验能力进行估计;元分析方法以样本为元素对总体进行推断,因此具有很高的准确性和可靠性,它将很有可能成为今后心理学研究的重要统计工具。     

Determinants of pausing under variable-ratio schedules: Reinforcer magnitude, ratio size, and schedule configuration

Pigeons pecked a key under two-component multiple variable-ratio schedules that offered 8-s or 2-s access to grain. Phase 1 assessed the effects of differences in reinforcer magnitude on postreinforcement pausing, as a function of ratio size. In Phase 2, postreinforcement pausing and the first five interresponse times in each ratio were measured as a function of differences in reinforcer magnitude under equal variable-ratio schedules consisting of different configurations of individual ratios. Rates were also calculated exclusive of postreinforcement pause times in both phases. The results from Phase 1 showed that as ratio size increased, the differences in pausing educed by unequal reinforcer magnitudes also increased. The results of Phase 2 showed that the effects of reinforcer magnitude on pausing and IRT durations were a function of schedule configuration. Under one configuration, in which the smallest ratio was a fixed-ratio 1, pauses were unaffected by magnitude but the first five interresponse times were affected. Under the other configuration, in which the smallest ratio was a fixed-ratio 7, pauses were affected by reinforcer magnitude but the first five interresponse times were not. The effect of each configuration seemed to be determined by the value of the smallest individual ratio. Rates calculated exclusive of postreinforcement pause times were, in general, directly related to reinforcer magnitude, and the relation was shown to be a function of schedule configuration.