Person‐specific versus multilevel autoregressive models: Accuracy in parameter estimates at the population and individual levels

This paper compares the multilevel modelling (MLM) approach and the person‐specific (PS) modelling approach in examining autoregressive (AR) relations with intensive longitudinal data. Two simulation studies are conducted to examine the influences of sample heterogeneity, time series length, sample size, and distribution of individual level AR coefficients on the accuracy of AR estimates, both at the population level and at the individual level. It is found that MLM generally outperforms the PS approach under two conditions: when the sample has a homogeneous AR pattern, namely, when all individuals in the sample are characterized by AR processes with the same order; and when the sample has heterogeneous AR patterns, but a multilevel model with a sufficiently high order (i.e., an order equal to or higher than the maximum order of individual AR patterns in the sample) is fitted and successfully converges. If a lower‐order multilevel model is chosen for heterogeneous samples, the higher‐order lagged effects are misrepresented, resulting in bias at the population level and larger prediction errors at the individual level. In these cases, the PS approach is preferable, given sufficient measurement occasions (T ≥ 50). In addition, sample size and distribution of individual level AR coefficients do not have a large impact on the results. Implications of these findings on model selection and research design are discussed.     

Teacher-student relationship quality type in elementary grades: Effects on trajectories for achievement and engagement

Teacher, peer, and student reports of the quality of the teacher-student relationship were obtained for an ethnically diverse and academically at-risk sample of 706 second- and third-grade students. Cluster analysis identified four types of relationships based on the consistency of child reports of support and conflict in the relationship with reports of others: Congruent Positive, Congruent Negative, Incongruent Child Negative, and Incongruent Child Positive. The cluster solution evidenced good internal consistency and construct validity. Group membership predicted growth trajectories for teacher-rated engagement and standardized achievement scores over the following three years, above prior performance. The predictive associations between child reports of teacher support and conflict and the measured outcomes depended on whether child reports were consistent or inconsistent with reports of others. Study findings have implications for theory development, assessment of teacher-student relationships, and teacher professional development.     

When should clinicians switch treatments? An application of signal detection theory to two treatments for women with alcohol use disorders

Statistical application of signal detection theory has been used to study the clinical utility of early treatment response in a range of treatments and psychiatric disorders. The current study sought to examine the predictive value of weekly within-treatment drinking using receiver operator curves (ROCs) and zero-inflated Poisson (ZIP) regression in 102 women with alcohol use disorders (AUDs) randomized to either alcohol behavioral individual treatment (ABIT; n = 52) or alcohol behavioral couples treatment (ABCT; n = 50). ROC analyses indicated that failure to achieve or sustain abstinence by the end-of-treatment and one-year follow-up was predicted with reasonable accuracy by week 4 percent days abstinent (PDA) in ABIT. ZIP models yielded similar results with evidence for within-treatment PDA with week 6 PDA predicting both the abstinence as well as percent days drinking at the end-of-treatment and one-year follow-up. Within-treatment PDA was a significantly better predictor of outcomes for ABIT than ABCT, despite a better overall treatment response for ABCT. Implications for stepped care models of alcohol treatment are discussed and recommendations for future research made. When Should Clinicians Switch Treatments: An Application of Signal Detection Theory to Two Treatments for Women with Alcohol Use Disorders.     

An imprecise goal programming approach for modeling design team's preferences in quality function deployment planning process

The Quality Function Deployment (QFD) is an approach that facilitates designing product by analyzing and projecting the Customer's Needs (CNs) in the Engineering Characteristics (ECs) of a product. The aim of QFD planning process is to determine the target levels for ECs of a product that achieve high level of overall customers' satisfaction. However, integrating design team's preferences in this preliminary stage of product design could make the design more realistic and could also avoid unfeasibility in posterior phases of the product development processes. Moreover, this process is performed within an imprecise environment, and more than one factor must be taken into account in determining targets levels of ECs; especially, the limited resources and increased market competition. This paper presents an imprecise goal programming approach to determine the best aspiration levels of ECs in QFD planning process. Based on benchmarking data of ECs, the concept of satisfaction functions will be utilized to integrate explicitly the design team's preferences and incorporate the competitive analysis of target market into the modelling and solution processes. In addition, the relationships linking CNs and ECs and the ECs to each other are integrated by functional relationships. The proposed approach will be illustrated through an example of product development of an emulsification dynamite packing machine. Copyright © 2011 John Wiley & Sons, Ltd.     

Influences of information processing and disengagement in infants' looking behaviour

The present study considers the joint influences of information processing and disengagement in looking behaviour within a habituation paradigm. Six‐month‐old infants were habituated, during which their heart rate (HR) was measured. A parametric model of habituation yielded for each infant parameter estimates of their habituation performance. These parameters were interpreted as assessing information processing and disengagement. Corresponding measures were obtained from the HR data. The HR measures and habituation model parameter estimates were significantly correlated, as predicted. In addition, an attention getter, presented prior to each habituation trial, influenced indicators of information processing, but not of disengagement. Results confirmed the advantages of a modelling approach. In addition, and more importantly, findings led to the conclusion that both information processing as well as disengagement are involved in infants' looking behaviour in visual habituation. Copyright © 2009 John Wiley & Sons, Ltd.     

Memory span and general intelligence: A latent-variable approach

There are several studies showing that working memory and intelligence are strongly related. However, working memory tasks require simultaneous processing and storage, so the causes of their relationship with intelligence are currently a matter of discussion. The present study examined the simultaneous relationships among short-term memory (STM), working memory (WM), and general intelligence (g). Two hundred and eight participants performed six verbal, quantitative, and spatial STM tasks, six verbal, quantitative, and spatial WM tasks, and eight tests measuring fluid, crystallized, spatial, and quantitative intelligence. Especial care is taken to avoid misrepresenting the relations among the constructs being studied because of specific task variance. Structural equation modelling (SEM) results revealed that (a) WM and g are (almost) isomorphic constructs, (b) the isomorphism vanishes when the storage component of WM is partialed out, and (c) STM and WM (with its storage component partialed out) predict g.     

Family and work predictors of parenting role stress among two‐earner families of children with disabilities

Family resources (i.e. household income and spouse support), parenting challenges (i.e. number of children, difficulty finding reliable child care, and child characteristics), work rewards (i.e. work interest) and work demands (i.e. hours and work overload) were tested as predictors of parenting role stress among mothers and fathers in two‐earner families of five‐year old children with disabilities. The two‐level hierarchical model was adapted to assess mothers and fathers as nested within married couples. Both common and unique predictors of maternal and paternal parenting role stress were found. Having fewer children in the family predicted less stress for both parents. Household income and an interaction between child behaviour problems and work interest were significant predictors of maternal parenting role stress. In contrast, greater difficulty in finding reliable child care predicted higher levels of parenting role stress for fathers but not mothers. The policy and research implications of these findings are discussed. Copyright © 2005 John Wiley & Sons, Ltd.     

Doing cognitive neuroscience: a third way

The “top-down” and “bottom-up” approaches have been thought to exhaust the possibilities for doing cognitive neuroscience. We argue that neither approach is likely to succeed in providing a theory that enables us to understand how cognition is achieved in biological creatures like ourselves. We consider a promising third way of doing cognitive neuroscience, what might be called the “neural dynamic systems” approach, that construes cognitive neuroscience as an autonomous explanatory endeavor, aiming to characterize in its own terms the states and processes responsible for brain-based cognition. We sketch the basic motivation for the approach, describe a particular version of the approach, so-called ‘Dynamic Causal Modeling’ (DCM), and consider a concrete example of DCM. This third way, we argue, has the potential to avoid the problems that afflict the other two approaches.     

Understanding Gang Joining from a Cross Classified Multi-Level Perspective

The present study seeks to address the gap in our understanding of the role of community- and school-level factors on individual-level gang joining. We assess our research question by bringing together data from a statewide survey of more than 35,000 school youth who were enrolled in more than 250 schools and resided in more than 300 communities. We first use multilevel modeling techniques to examine the independent relationship of community and school on the likelihood of individual youth gang joining. Second, while controlling for individual-level risk and protective factors, we examine the simultaneous relationship of community- and school-level conditions on gang joining. Overall, the results of the present study suggest that both community- and school-level characteristics play a role in gang joining. The results of the cross-classified model suggests that community structural characteristics may serve as protection against gang joining. Individual-level risk and protective factors remain important for understanding gang joining. A variety of factors are related to gang joining. Though individual-level factors are important, community- and school-level factors are meaningful in the understanding of gang joining.     

Adolescents' music preferences and personality characteristics

The present paper examined the structure of Dutch adolescents' music preferences, the stability of music preferences and the relations between Big‐Five personality characteristics and (changes in) music preferences. Exploratory and confirmatory factor analyses of music‐preference data from 2334 adolescents aged 12–19 revealed four clearly interpretable music‐preference dimensions: Rock, Elite, Urban and Pop/Dance. One thousand and forty‐four randomly selected adolescents from the original sample filled out questionnaires on music preferences and personality at three follow‐up measurements. In addition to being relatively stable over 1, 2 and 3‐year intervals, music preferences were found to be consistently related to personality characteristics, generally confirming prior research in the United States. Personality characteristics were also found to predict changes in music preferences over a 3‐year interval. Copyright © 2007 John Wiley & Sons, Ltd.