Robust Methods for Moderation Analysis with a Two-Level Regression Model

Moderation analysis has many applications in social sciences. Most widely used estimation methods for moderation analysis assume that errors are normally distributed and homoscedastic. When these assumptions are not met, the results from a classical moderation analysis can be misleading. For more reliable moderation analysis, this article proposes two robust methods with a two-level regression model when the predictors do not contain measurement error. One method is based on maximum likelihood with Student's t distribution and the other is based on M-estimators with Huber-type weights. An algorithm for obtaining the robust estimators is developed. Consistent estimates of standard errors of the robust estimators are provided. The robust approaches are compared against normal-distribution-based maximum likelihood (NML) with respect to power and accuracy of parameter estimates through a simulation study. Results show that the robust approaches outperform NML under various distributional conditions. Application of the robust methods is illustrated through a real data example. An R program is developed and documented to facilitate the application of the robust methods.     

Developmental dynamics between reading and math in elementary school

Reading and math attainment develop during elementary grades. Questions remain, though, about the co‐developmental nature of the relation between reading and math. This study examined dynamic, longitudinal pathways between reading and math in first through fourth grades. Participants of the study were 554 academically at‐risk children (M_age at the first assessment point = 6.57 years; SD = 0.38) from Texas Project Achieve. Children were assessed utilizing the Woodcock‐Johnson–III reading and math measures. Results from dynamic bivariate latent change score models indicated unidirectional longitudinal coupling effects from reading to math. Specifically, average and high levels of reading performance were associated with subsequent gains in math growth, in particular for below average performing children in math. In contrast, low levels of reading performance had negligible or no amplifying influences on change in math growth. The nature of the dynamics was replicated even when controlling for nonverbal cognitive abilities. Results demonstrated that good reading skills pave the way for children to develop their math skills. Such findings underscore the importance of considering reading performance in treating math difficulties.     

Scale Alignment in the Between-Item Multidimensional Partial Credit Model

In between-item multidimensional item response models, it is often desirable to compare individual latent trait estimates across dimensions. These comparisons are only justified if the model dimensions are scaled relative to each other. Traditionally, this scaling is done using approaches such as standardization—fixing the latent mean and standard deviation to 0 and 1 for all dimensions. However, approaches such as standardization do not guarantee that Rasch model properties hold across dimensions. Specifically, for between-item multidimensional Rasch family models, the unique ordering of items holds within dimensions, but not across dimensions. Previously, Feuerstahler and Wilson described the concept of scale alignment, which aims to enforce the unique ordering of items across dimensions by linearly transforming item parameters within dimensions. In this article, we extend the concept of scale alignment to the between-item multidimensional partial credit model and to models fit using incomplete data. We illustrate this method in the context of the Kindergarten Individual Development Survey (KIDS), a multidimensional survey of kindergarten readiness used in the state of Illinois. We also present simulation results that demonstrate the effectiveness of scale alignment in the context of polytomous item response models and missing data.     

7-10岁学龄儿童ADHD筛查研究

用SDQ（家长版）对上海10所小学二至四年级学生进行测查,以探求被试的ADHD症状表现,锁定ADHD高风险儿童。结果：（1）男生ADHD得分偏高（p<.01）,但女生在红橙两个级别内的百分数均高于男生;（2）9岁被试的ADHD得分分布最分散,占男生ADHD红色级别的比例最大,在女生ADHD得分中均值最大;（3）红橙两个级别为高风险级别。结论：（1）9岁是ADHD症状表现最严重的年龄;（2）女生具有更高的ADHD风险;（3）ADHD高风险被试晒出率：男生14.4%,女生17.4%。     

Establishing a trait anxiety threshold that signals likelihood of anxiety disorders

Abstract

Evidence suggests that the State Trait Inventory for Cognitive and Somatic Anxiety (STICSA) may be a more pure measure of anxiety than other commonly used scales. Further, the STICSA has excellent psychometric properties in both clinical and nonclinical samples. The present study aimed to extend the utility of the STICSA – Trait version by identifying a cut-off score that could differentiate a group of clinically diagnosed anxiety disorder patients (n=398) from a group of student controls (n =439). Two receiver operating characteristic curve analyses indicated cut-off scores of 43 (sensitivity=.73, specificity=.74, classification accuracy=.74) and 40 (sensitivity=.80, specificity=.67, classification accuracy=.73), respectively. In a large community sample (n =6685), a score of 43 identified 11.5% of individuals as probable cases of clinical anxiety, while a score of 40 identified 17.0% of individuals as probable cases of clinical anxiety. As a result of differences in sensitivity and specificity, the present findings suggest a cut-off score of 43 is optimal to identify probable cases of clinical anxiety, while a cut-off score of 40 is optimal to screen for the possible presence of anxiety disorders.     

广告语言与产品卷入度对广告卷入度的影响研究

从产品角度对地方语广告进行研究。本研究将语言熟练度和地域文化认同这两个因素作为控制变量,选取产品卷入度作为调节变量,分别在语音和文本广告两种不同的广告媒介中,研究广告语言（普通话VS粤语）对广告卷入度（认知卷入度VS情感卷入度）的影响机制。结果表明：对于高卷入度产品广告,普通话比粤语产生的广告认知卷入度和情感卷入度都更高;对于低卷入度产品广告,无论广告使用普通话抑或粤语,消费者对广告的认知卷入度都没有显著差异,但粤语比普通话能带来更高的广告情感卷入度。     

Neutrality,tenderness and the analyst's subjectivity

Addressing the rôle of the analyst in the psychoanalytic relationship, the author takes issue with the emphasis on acknowledging the analyst's subjectivity and the critique of concepts like neutrality and abstinence as these issues are presented in the relational tradition. He advocates a better articulation and emphasis of these concepts in the service of understanding the impact of the analyst's subjectivity, and demonstrates how the mere loosening up of analytic neutrality and abstinence and an acceptance of the analyst's self-disclosure make transference analysis more difficult to handle. Such an attitude also increases the risk for ethically dubious conduct, since there is a close link between clinical methods and ethical standards in psychoanalysis. In conclusion, the author points to the importance of the analyst's continuous self-reflection and countertransference analysis.     

Is the Flynn effect on g?: A meta-analysis

Black/White differences in mean IQ have been clearly shown to strongly correlate with g loadings, so large group differences on subtests of high cognitive complexity and small group differences on subtests of low cognitive complexity. IQ scores have been increasing over the last half century, a phenomenon known as the Flynn effect. Flynn effect gains are predominantly driven by environmental factors. Might these factors also be responsible for group differences in intelligence? The empirical studies on whether the pattern of Flynn effect gains is the same as the pattern of group differences yield conflicting findings. A psychometric meta-analysis on all studies with seven or more subtests reporting correlations between g loadings and standardized score gains was carried out, based on 5 papers, yielding 11 data points (total N = 16,663). It yielded a true correlation of − .38, and none of the variance between the studies could be attributed to moderators. It appears that the Flynn effect and group differences have different causes. Suggestions for future research are discussed.     

The association of environmental,individual factors,and dopamine pathway gene variation with smoking cessation

This study aimed to examine whether dopamine (DA) pathway gene variation were associated with smoking cessation, and compare the relative importance of infulence factors on smoking cessation. Participants were recruited from 17 villages of Shandong Province, China. Twenty-five single nucleotide polymorphisms in 8 DA pathway genes were genotyped. Weighted gene score of each gene was used to analyze the whole gene effect. Logistic regression was used to calculate odds ratios (OR) of the total gene score for smoking cessation. Dominance analysis was employed to compare the relative importance of individual, heaviness of smoking, psychological and genetic factors on smoking cessation. 415 successful spontaneous smoking quitters served as the cases, and 404 unsuccessful quitters served as the controls. A significant negative association of total DA pathway gene score and smoking cessation was observed (p < 0.001, OR: 0.25, 95% CI 0.16–0.38). Dominance analysis showed that the most important predictor for smoking cessation was heaviness of smoking score (42%), following by individual (40%), genetic (10%) and psychological score (8%). In conclusion, although the DA pathway gene variation was significantly associated with successful smoking cessation, heaviness of smoking and individual factors had bigger effect than genetic factors on smoking cessation.