Design efficiency for imbalanced multilevel data

The importance of accurate estimation and of powerful statistical tests is widely recognized but has rarely been acknowledged in practice in the social and behavioral sciences. This is especially true for estimation and testing when one is dealing with multilevel designs, not least because approximating accuracy and power is more complex due to having multiple variances and research units at several levels. The complexity further increases for imbalanced designs, often necessitating simulation studies that perform accuracy and power calculations. However, we show, using such simulation studies, that the distortion of balance can be ignored in most cases, making efficiency studies simpler and the use of existing software valid. An exception is suggested for imbalanced data from a large majority of small groups. Furthermore, an empirical sampling distribution of variance parameters may show substantial skewness and kurtosis, depending on the number of groups and, for the random slope, depending also on the group’s size, adding another caveat to the recommendation to ignore imbalance.     

Bayesian model selection of informative hypotheses for repeated measurements

When analyzing repeated measurements data, researchers often have expectations about the relations between the measurement means. The expectations can often be formalized using equality and inequality constraints between (i) the measurement means over time, (ii) the measurement means between groups, (iii) the means adjusted for time-invariant covariates, and (iv) the means adjusted for time-varying covariates. The result is a set of informative hypotheses. In this paper, the Bayes factor is used to determine which hypothesis receives most support from the data. A pivotal element in the Bayesian framework is the specification of the prior. To avoid subjective prior specification, training data in combination with restrictions on the measurement means are used to obtain so-called constrained posterior priors. A simulation study and an empirical example from developmental psychology show that this prior results in Bayes factors with desirable properties.     

Logic and belief across the lifespan: the rise and fall of belief inhibition during syllogistic reasoning

Popular reasoning theories postulate that the ability to inhibit inappropriate beliefs lies at the heart of the human reasoning engine. Given that people's inhibitory capacities are known to rise and fall across the lifespan, we predicted that people's deductive reasoning performance would show similar curvilinear age trends. A group of children (12‐year‐olds), young adults (20‐year‐olds), and older adults (65+‐year‐olds) were presented with a classic syllogistic reasoning task and a decision‐making questionnaire. Results indicated that on syllogisms where beliefs and logic conflicted, reasoning performance showed the expected curvilinear age trend: Reasoning performance initially increased from childhood to early adulthood but declined again in later life. On syllogisms where beliefs and logic were consistent and sound reasoning did not require belief inhibition, however, age did not affect performance. Furthermore, across the lifespan we observed that the better people were at resisting intuitive temptations in the decision‐making task, the less they were biased by their beliefs on the conflict syllogisms. As with the effect of age, one's ability to override intuitions in the decision‐making task did not mediate reasoning performance on the no‐conflict syllogisms. Results lend credence to the postulated central role of inhibitory processing in those situations where beliefs and logic conflict.     

Personality Development from Age 12 to 25 and its Links with Life Transitions

During adolescence and young adulthood, individuals show personality changes and experience various life transitions. Whereas personality might affect the timing of life transitions, life transitions might also induce personality maturation. We examined Big Five personality maturation from age 12 to 25 using a 9-year longitudinal study of Dutch youths from two cohorts (n₁ = 683, M_ageT1 = 12.70; n₂ = 268, M_age T1 = 16.87). We linked personality maturation to the incidence and timing of four transitions: first romantic relationship, leaving the parental home, first job, and first cohabitation or marriage. Results indicated increases in mean levels, rank-order stabilities and profile stability of personality between age 12 and 25, which were largely replicated across the cohorts. Very few associations between personality and life transitions existed. However, higher mean-level Extraversion predicted leaving the parental home and starting the first romantic relationship, an earlier age when starting the first job, and an earlier average timing of transitions. Regarding social investment effects, we only found that those who never experienced a romantic relationship at age 25 decreased, while those who did increased in profile stability over time. These results suggest that personality consistently matures during adolescence and young adulthood and that higher Extraversion predict greater readiness for new steps towards adulthood.     

A test-theoretic approach to observed-score equating

Observed-score equating using the marginal distributions of two tests is not necessarily the universally best approach it has been claimed to be. On the other hand, equating using the conditional distributions given the ability level of the examinee is theoretically ideal. Possible ways of dealing with the requirement of known ability are discussed, including such methods as conditional observed-score equating at point estimates or posterior expected conditional equating. The methods are generalized to the problem of observed-score equating with a multivariate ability structure underlying the scores. This article is based on the author's Presidential Address given on July 7, 2000 at the 65th Annual Meeting of the Psychometric Society held at the University of British Columbia, Vancouver, Canada. The author is most indebted to Wim M.M. Tielen for his computational assistance and Cees A.W. Glas for his comments on a draft of this paper.     

Group Effects on Individual Learning Achievement

This study focuses on the impact of the social context of a class on student behaviour, in particular, the effects of pupil-pupil interaction on learning achievement. Two major functions of reference groups are distinguished: a normative and a comparative function. The normative function deals with norm setting and enforcing norms. The comparative function is merely a standard of comparison for the individual. This study deals with the question as to what extent contextual effects at classroom level can be accounted for by these two types of reference processes. The development of mathematical achievement of some 3,600 students in Year 8 (11 or 12 years of age) in about 200 primary schools in the Netherlands was followed. Students were asked to rate their classmates on two/three-point scales: a comparative scale and a normative scale. It appears that both the comparative and the normative reference structure of classes have substantial effects on individual achievement. The effect of the normative reference group, however, is by far the strongest.     

Finding a serial burglar's home using distance decay and conditional origin–destination patterns: a test of empirical Bayes journey-to-crime estimation in the Hague

Can we tell where an offender lives from where he or she commits crimes? Journey-to-crime estimation is a tool that uses crime locations to tell us where to search for a serial offender's home. In this paper, we test a new method: empirical Bayes journey-to-crime estimation. It differs from previous methods because it utilises an ‘origin–destination’ rule in addition to the ‘distance decay’ rule that prior methods have used. In the new method, the profiler not only asks ‘what distances did previous offenders travel between their home and the crime scenes?’ but also ‘where did previous offenders live who offended at the locations included in the crime series I investigate right now?’. The new method could not only improve predictive accuracy, it could also reduce the traditional distinction between marauding and commuting offenders. Utilising the CrimeStat software, we apply the new method to 62 serial burglars in The Hague, The Netherlands, and show that the new method has higher predictive accuracy than methods that only exploit a distance decay rule. The new method not only improves the accuracy of predicting the homes of commuters—offenders who live outside their offending area—it also improves the search for marauders—offenders who live inside their offending area. After presenting an example of the application of the technique for prediction of a specific burglar, we discuss the limitations of the method and offer some suggestions for its future development. Copyright © 2009 John Wiley & Sons, Ltd.     

The effect of dopaminergic medication on conflict adaptation in Parkinson's disease

Parkinson's disease (PD) is a neurological disorder associated primarily with motor symptoms such as tremor, slowness of movement, and difficulties with gait and balance. Most patients take dopaminergic medication to improve their motor functions. Previous studies reported indications that such medication can impair higher cognitive functions (cf. dopamine overdose hypothesis). In the present study, we examined the effect of medication status on conflict adaptation. PD patients performed a Stroop task in which we manipulated the proportion of congruent and incongruent items, thereby allowing us to explore conflict adaptation. The use of mouse movements allowed us to examine the action dynamics of conflict adaptation in PD, and their sensitivity to dopaminergic medication. Each patient performed the same task twice: once without making changes to their regular medication regime, and once after overnight withdrawal from their medication. Results showed that medication improved mouse movements and alleviated motor symptoms. Moreover, patients' mouse movements were modulated as a function of the proportion congruency manipulation, revealing conflict adaptation in PD, which was unaffected by medication status. The present study extends earlier work on conflict adaptation in PD where reduced transient (trial-by-trial) conflict adaptation was observed ON compared to OFF medication (Duthoo et al., 2013, Neuropsychology, 27, 556). Our findings suggest that more sustained cognitive control processes may not be sensitive to dopamine overdose effects.     

Unconscious task application

The nature of unconscious information processing is a heavily debated issue in cognitive science (e.g., Kouider & Dehaene, 2007), and neuroscience (e.g., Crick & Koch, 1998). Traditionally, it has been thought that unconscious cognitive processing is restricted to knowledge that is strongly prepared by conscious processes (e.g., Dehaene et al., 1998). In three experiments, we show that the task that is performed consciously can also be applied unconsciously to items outside the current task set. We found that a same–different judgment of two target stimuli was also performed on two subliminally presented prime stimuli. This was true for target and prime stimuli from entirely different categories, as well as for prime and target stimuli at different levels of abstraction. These results reveal that unconscious processing can generalize more widely than previously accepted.     

Marginal likelihood inference for a model for item responses and response times

Marginal maximum‐likelihood procedures for parameter estimation and testing the fit of a hierarchical model for speed and accuracy on test items are presented. The model is a composition of two first‐level models for dichotomous responses and response times along with multivariate normal models for their item and person parameters. It is shown how the item parameters can easily be estimated using Fisher's identity. To test the fit of the model, Lagrange multiplier tests of the assumptions of subpopulation invariance of the item parameters (i.e., no differential item functioning), the shape of the response functions, and three different types of conditional independence were derived. Simulation studies were used to show the feasibility of the estimation and testing procedures and to estimate the power and Type I error rate of the latter. In addition, the procedures were applied to an empirical data set from a computerized adaptive test of language comprehension.