Multilevel Modeling with Correlated Effects

When there exist omitted effects, measurement error, and/or simultaneity in multilevel models, explanatory variables may be correlated with random components, and standard estimation methods do not provide consistent estimates of model parameters. This paper introduces estimators that are consistent under such conditions. By employing generalized method of moments (GMM) estimation techniques in multilevel modeling, the authors present a series of estimators along a robust to efficient continuum. This continuum depends on the assumptions that the analyst makes regarding the extent of the correlated effects. It is shown that the GMM approach provides an overarching framework that encompasses well-known estimators such as fixed and random effects estimators and also provides more options. These GMM estimators can be expressed as instrumental variable (IV) estimators which enhances their interpretability. Moreover, by exploiting the hierarchical structure of the data, the current technique does not require additional variables unlike traditional IV methods. Further, statistical tests are developed to compare the different estimators. A simulation study examines the finite sample properties of the estimators and tests and confirms the theoretical order of the estimators with respect to their robustness and efficiency. It further shows that not only are regression coefficients biased, but variance components may be severely underestimated in the presence of correlated effects. Empirical standard errors are employed as they are less sensitive to correlated effects when compared to model-based standard errors. An example using student achievement data shows that GMM estimators can be effectively used in a search for the most efficient among unbiased estimators. This research was supported by the National Academy of Education/Spencer Foundation and the National Science Foundation, grant number SES-0436274. We thank the editor, associate editor, and referees for detailed feedback that helped improve the paper.     

项目反应理论框架下的新等值方法——对数对比等值法

项目反应理论有一些以除法形式给出的多级评分模型,若采用Haebara等值法、Stocking_Lord等值法或对称相对熵等值法进行测验等值,都因其对初值有较高要求而可能导致失败。针对这一类模型,我们给出了一种新的等值方法——对数对比等值法。这种方法收敛快,对迭代初值要求低,所得结果精度较高,可以为其他等值方法提供良好的初值。研究表明,对数对比等值法还改进和推广了0-1评分的两参数Logistic模型的Logit变换等值法     

HSK主观考试评分的Rasch实验分析

主观评分中存在的不一致性导致主观评分的信度降低。多面Rasch模型基于项目反应理论,可以应用于评分员效应的识别和消除,从而提高主观评分的信度。该文介绍多面Rasch模型的理论和应用框架,设计了基于该模型的HSK主观考试评分质量控制应用框架,利用HSK作文评分数据进行了实验验证。     

What do Patients Prefer: Informed Consent Models for Genetic Carrier Testing

The recent increased number of conditions for which patients can undergo genetic carrier testing raises the question of how best to obtain pre-test informed consent. Clinical approaches vary from a minimalist model to a model where patients are given detailed information about all conditions to be screened for. Few data exist as to patient preferences, or how information impacts decision-making. Eight high-literacy focus groups were conducted to assess the knowledge and preferences of pregnant patients and their male partners. Most groups indicated that some balance between details and brevity was optimal, recognizing that anxiety can occur when patients are provided with too much information and that the wide range of tests offered during pregnancy often led to confusion. Critical areas for the informed consent process included (1) details about the conditions and risk of being a carrier, (2) logistics of testing, (3) next steps if the test is positive, and (4) prognosis, options and resources if the child were to be affected with a disorder. It will be useful to develop model consent programs and prospectively assess their impact on informed consent and patient satisfaction, both when positive and negative results are received.     

平行分析在探索性因素分析中的应用

平行分析是探索性因素分析中用来确定所保留的凶子个数的一种方法。探索性因素分析中常用的确定因子个数的方法有特征值大于1准则和碎石图,但这两种方法又各有不足。平行分析则为探索性因素分析中所保留因子个数的确定提供了另一种新思路。本文详细介绍了平行分析的步骤、潜在逻辑以及进行平行分析所用的软件,并通过实例来说明其在探索性因素分析中如何应用。     

An accumulator model for responses and response times in tests based on the proportional hazards model

Latent trait models for responses and response times in tests often lack a substantial interpretation in terms of a cognitive process model. This is a drawback because process models are helpful in clarifying the meaning of the latent traits. In the present paper, a new model for responses and response times in tests is presented. The model is based on the proportional hazards model for competing risks. Two processes are assumed, one reflecting the increase in knowledge and the second the tendency to discontinue. The processes can be characterized by two proportional hazards models whose baseline hazard functions correspond to the temporary increase in knowledge and discouragement. The model can be calibrated with marginal maximum likelihood estimation and an application of the ECM algorithm. Two tests of model fit are proposed. The amenability of the proposed approaches to model calibration and model evaluation is demonstrated in a simulation study. Finally, the model is used for the analysis of two empirical data sets.     

Comparing score tests and other local dependence diagnostics for the graded response model

Score tests for identifying locally dependent item pairs have been proposed for binary item response models. In this article, both the bifactor and the threshold shift score tests are generalized to the graded response model. For the bifactor test, the generalization is straightforward; it adds one secondary dimension associated only with one pair of items. For the threshold shift test, however, multiple generalizations are possible: in particular, conditional, uniform, and linear shift tests are discussed in this article. Simulation studies show that all of the score tests have accurate Type I error rates given large enough samples, although their small‐sample behaviour is not as good as that of Pearson's Χ² and M₂ as proposed in other studies for the purpose of local dependence (LD) detection. All score tests have the highest power to detect the LD which is consistent with their parametric form, and in this case they are uniformly more powerful than Χ² and M₂; even wrongly specified score tests are more powerful than Χ² and M₂ in most conditions. An example using empirical data is provided for illustration.     

Leader personality and 360‐degree assessments of leader behavior

To investigate the relationship between personality and multi‐source feedback, we assessed 190 health care managers by applying the Understanding Personal Potential personality test, which provides comprehensive measurement of the Big Five dimensions and eight narrower personality traits. Managers' leadership behaviors were assessed by colleagues, supervisors, a random sample of each manager's subordinates as well as the managers themselves using a 360‐degree change, production, employee (CPE) instrument. Hierarchical multivariate regression analysis showed that the Big Five variables were significantly related to the Managers' leadership behavior in all CPE dimensions. Also, addition of narrow personality variables to the Big Five increased explained variance in leadership behavior. This study is the first of its kind to include the full range of viewpoints in a 360‐degree instrument, along with a large number of subordinate assessments. We found that both the strength of the relationship between personality and behavior and the configuration of different predictors varied depending on who did the rating and what leadership orientation was investigated, and this observation merits further investigation.     

Postural control in children with and without neurofibromatosis type 1

Previous research has evaluated the motor proficiency of children with neurofibromatosis type 1 (NF1) and found delays on the balance subtest. However the balance subtest was found to have low sensitivity for identifying balance impairments. This study examines the differences in postural control between children with NF1 and peers with typical development using a force plate. A single limb stance test on a force plate was completed for all participants. The force plate variables, center of pressure maximum distance in the anterior/posterior direction (COPmax A/P) and center of pressure velocity (COPvel A/P) were compared between groups. The NF1 group’s performance was significantly poorer than the control group in both COPmax A/P (p = .01) and COPvel A/P (p = .01). When separated into specific age ranges, only the children in the NF1 group between 5 and 12 years of age demonstrated statistically significant differences in the COP variables. The COP variables for the 13- to 18-year-old group were not significantly different. These results indicate that young children with NF1 have poor postural control. However, postural control appears to improve with maturation.