The effect of uncertainty of item parameter estimation on ability estimates

The conventional method of measuring ability, which is based on items with assumed true parameter values obtained from a pretest, is compared to a Bayesian method that deals with the uncertainties of such items. Computational expressions are presented for approximating the posterior mean and variance of ability under the three-parameter logistic (3PL) model. A 1987 American College Testing Program (ACT) math test is used to demonstrate that the standard practice of using maximum likelihood or empirical Bayes techniques may seriously underestimate the uncertainty in estimated ability when the pretest sample is only moderately large.This work was partially supported under contract No. N00014-85-K-0113, NR150-535, from the Cognitive Science Program, Office of Naval Research. The authors wish to thank Mark D. Reckase for providing the ACT data used in the illustration and two referees, Asociate Editor and Editor for helpful suggestions.     

项目反应理论中潜在心理特质“填补”的参数估计方法及其演变

在心理与教育测量中, 项目反应理论(Item Response Theory, IRT)模型的参数估计方法是理论研究与实践应用的基本工具。最近, 由于IRT模型的不断扩展与EM (expectation-maximization)算法自身的固有问题, 参数估计方法的改进与发展显得尤为重要。这里介绍了IRT模型中边际极大似然估计的发展, 提出了它的阶段性特征, 即联合极大似然估计阶段、确定性潜在心理特质“填补”阶段、随机潜在心理特质“填补”阶段, 重点阐述了它的潜在心理特质“填补” (data augmentation)思想。EM算法与Metropolis-Hastings Robbins-Monro (MH-RM)算法作为不同的潜在心理特质“填补”方法, 都是边际极大似然估计的思想跨越。目前, 潜在心理特质“填补”的参数估计方法仍在不断发展与完善。     

时间间隔对面部表情唤醒度阈下情绪启动的影响

采用3×4混合实验设计,研究了启动刺激与靶刺激的时间间隔对面部表情唤醒度阈下情绪启动效应的影响,实验因素为启动刺激的唤醒度和时间间隔。结果发现,当时间间隔为200ms、300ms、500ms时,出现了阈下情绪启动效应,时间间隔为700ms时,启动效应消失。上述结果表明阈下情绪启动效应可在唤醒度维度上实现,但此效应只能在启动刺激与靶刺激间隔时间较短的情况下出现。     

预期式时距估计年龄差异的初步研究

以5s、13s和26s为目标时距,采用产生法和复制法,探讨了预期式条件下时距估计的年龄差异。结果表明在单任务作业中。年老被试和年轻被试两个年龄组之间估计时距的平均值没有显著差异,但年老被试比年轻被试的估计时距具有更大的变异性。单一的内部时钟频率变化的假设并不能对单任务条件下时距估计的年龄差异做出合理的解释。时距估计的年龄差异可能是内部时钟频率变化和认知过程变化交互作用的结果。     

Distorted distance estimation induced by a self-relevant national boundary

Six experiments explored the possibility that the categorization of self versus not-self can distort visual estimations of distance. In Experiments 1-3, Americans overestimated the distance between a U.S. location and a foreign location relative to a visually equidistant U.S. location. In Experiment 4, Canadians overestimated foreign relative to Canadian locations. Experiment 5 showed that this effect occurs even when the domestic context is not physically contiguous. Experiment 6 showed that distance distortion occurs only when crossing one’s own border to a foreign location, not when crossing borders from one foreign location to another. Thus, crossing the psychological boundary between self and not-self creates a visual illusion that distorts on-line distance estimates.     

Evaluating a model of global psychophysical judgments—II: Behavioral properties linking summations and productions

Steingrimsson and Luce [Journal of Mathematical Psychology, in press] outlined the second author's proposed psychophysical theory [Luce (2002), Psychological Review, 109, 520-532; Luce (2004a) Psychological Review, 111, 446-454] and tested behavioral attributes that, separately, gave rise to two psychophysical functions, Ψ_⊕ and Ψ_°p. The function Ψ_⊕ maps pairs of physical intensities onto the positive real numbers and represents subjective summation, and the function Ψ_°p represents a form of ratio production. This article evaluates properties linking summation and production in such a way as to force Ψ_°p=Ψ_⊕=Ψ. These properties, which are a form of distributivity, are subjected to an empirical evaluation in three experiments. The testing strategy is carried out in the auditory domain and concerns the subjective perception of loudness. Considerable support is provided for the existence of a single function Ψ for both summation and ratio production.     

GPCM模型项目参数估计程序的开发与研究

该文对GPCM的项目参数估计的方法进行较为深入的探讨,特别对容易混淆的参数初值计算以及项目参数分两步进行估计的原因进行了阐述。并且基于MMLE／EM算法,开发了相应的项目参数估计程序。通过大量的蒙特卡洛模拟,与国外专业软件PARSCALE比较,本程序的步骤参数估计值更好,区分度参数估计值相当,具有较好的应用价值。     

Sex differences in number line estimation: The role of numerical estimation

Sex differences in mathematical performance have frequently been examined over the last decades indicating an advantage for males especially when numerical problems cannot be solved by (classroom‐)learnt strategies and/or estimation. Even in basic numerical tasks such as number line estimation, males were found to outperform females – with sex differences argued to emerge from different solution strategies applied by males and females. We evaluated the latter using two versions of the number line estimation task: a bounded and an unbounded task version. Assuming that women tend more strongly to apply known procedures, we expected them to be at a particular disadvantage in the unbounded number line estimation task, which is less prone to be solved by specific strategies such as proportion judgement but requires numerical estimation. Results confirmed more pronounced sex differences for unbounded number line estimation with males performing significantly more accurately in this task version. This further adds to recent evidence suggesting that estimation performance in the bounded task version may reflect solution strategies rather than numerical estimation. Additionally, it indicates that sex differences regarding the spatial representation of number magnitude may not be universal, but associated with spatial–numerical estimations in particular.     

Explaining High Conjunction Fallacy Rates: The Probability Theory Plus Noise Account

The conjunction fallacy occurs when people judge the conjunctive probability P(A ∧ B) to be greater than a constituent probability P(A), contrary to the norms of probability theory. This fallacy is a reliable, consistent and systematic part of people's probability judgements, attested in many studies over at least 40 years. For some events, these fallacies occur very frequently in people's judgements (at rates of 80% or more), while for other events, the fallacies are very rare (occurring at rates of 10% or less). This wide range of fallacy rates presents a challenge for current theories of the conjunction fallacy. We show how this wide range of observed fallacy rates can be explained by a simple model where people reason according to probability theory but are subject to random noise in the reasoning process. Copyright © 2016 John Wiley & Sons, Ltd.