Component Models for Fuzzy Data

The fuzzy perspective in statistical analysis is first illustrated with reference to the “Informational Paradigm” allowing us to deal with different types of uncertainties related to the various informational ingredients (data, model, assumptions). The fuzzy empirical data are then introduced, referring to J LR fuzzy variables as observed on I observation units. Each observation is characterized by its center and its left and right spreads (LR₁ fuzzy number) or by its left and right “centers” and its left and right spreads (LR₂ fuzzy number). Two types of component models for LR₁ and LR₂ fuzzy data are proposed. The estimation of the parameters of these models is based on a Least Squares approach, exploiting an appropriately introduced distance measure for fuzzy data. A simulation study is carried out in order to assess the efficacy of the suggested models as compared with traditional Principal Component Analysis on the centers and with existing methods for fuzzy and interval valued data. An application to real fuzzy data is finally performed. We would like to express our gratitude to the Editor, the Associate Editor, and the Referees whose comments and suggestions improved significantly the quality of the paper.     

A Brief Scale for Measuring “Behavioral Inhibition to the Unfamiliar” in Children

The behavioral inhibition scale (BIS) is a brief rating scale for measuring behavioral inhibition in children. The present study examined the test–retest stability of the BIS in a sample of 7–12-year-olds consisting of inhibited and non-inhibited children (N = 83). Results demonstrated that the BIS scores were fairly stable over a 2-year period, with a test–retest correlation of .77. Further, the BIS scores of inhibited children significantly increased over the 2-year period, whereas those of the non-inhibited comparison group significantly decreased. Finally, the BIS was in a theoretically meaningful way associated with temperamental traits as measured by the Rothbart scales. Altogether, these results provide support for the reliability and validity of the BIS.     

Treatment Sensitivity of a Brief Rating Scale for Attention-Deficit Hyperactivity Disorder (ADHD) Symptoms

This study examined the treatment sensitivity of the ADHD Questionnaire (ADHD-Q), which is a brief rating scale for measuring symptoms of inattention, hyperactivity, and impulsivity in children. Parent, teacher, and child self-report data of the ADHD-Q were obtained for 17 clinically referred children with ADHD on the three occasions: (1) during the regular intake assessment, (2) just before the start of the stimulant medication (i.e., methylphenidate) intervention, and (3) four weeks after the start of the medication intervention. Results showed that ADHD-Q scores remained fairly stable in the period prior to the intervention, but then showed a substantial decline after the stimulant medication had been administered. Clearly, this finding supports the treatment sensitivity of the ADHD-Q.     

Gender bias in estimating political expertise

The present study reveals that there is a gender bias in estimates of spouses' political expertise. Data were collected from married couples in one city in north-eastern Japan and the results showed that when all respondents were included, the estimation of spouses' political expertise was moderately accurate. However, while husbands' estimates of the political expertise of their wives were lowered and less accurate, wives' estimates of the political expertise of their husbands were more accurate. The implication of these findings for the political equality of males and females is discussed.     

Étude de certaines propriétés psychométriques de l’Older Adult Self-Report (OASR) en population générale québécoise

The aim of the present study was to evaluate some psychometric properties of the French-Canadian version of the Older Adult Self-Report (Achenbach et al., 2004), a self-reported measure of emotional, behavioral and interpersonal difficulties intended for people aged 60 years and older. This study examines some psychometric properties of the OASR, in terms of reliability (internal consistency) of the seven syndrome scales, and construct validity (structural, convergent and criterion validity). The instrument was completed by 321 older adults aged 60 years and older (M = 68.36; SD = 5.82) who were participating at the Université du troisième âge activities, which were taking place in two cities of the province of Quebec, Canada. Polychoric alpha coefficients varied between 0,72 and 0,93 and indicated a good internal consistency for the syndrome scales. Convergent validity was measured by multiple linear regression using life satisfaction as a dependent variable. A confirmatory factor analysis supported the seven-factor structure proposed in the original version of the instrument (CFI = .916, TLI = .914, RMSEA = .022 [.019, .025]). Results showed a good convergent validity, with 37.5% of variance explained by the problem scales. Overall, the results indicated that psychometric properties of the OASR meet expected standards for professional use of the French-Canadian version of the instrument.     

Accuracy of Self-Reported Personal History of Cancer in an Outpatient Breast Center

The self-reporting of cancer history is becoming increasingly important, as it frequently guides medical decision-making. We studied the accuracy of personal cancer history using a self-administered questionnaire, comparing the results with the Tumor Registry at our institution. Among 39,662 records, we identified 3614 women with a single cancer in the Tumor Registry who reported none or one cancer on their questionnaire. The sensitivity in self-reporting cancers was 85.7%, ranging from 92.1% for breast cancer to 42.9% for leukemia. The accuracy for breast cancer and Hodgkin's Lymphoma was significantly better than other cancers (p=0.00027, CI: 1.4–3.88). Analysis of patient's characteristics showed that Caucasians reported breast cancer more accurately than Asian/Pacific Islanders (p=0.008), and those with Jewish ancestry more accurately than non-Jewish (p=0.0435). These results will help us to improve data collection and thus improve medical decision-making.     

Estimation of the Nonlinear Random Coefficient Model when Some Random Effects Are Separable

A method is presented for marginal maximum likelihood estimation of the nonlinear random coefficient model when the response function has some linear parameters. This is done by writing the marginal distribution of the repeated measures as a conditional distribution of the response given the nonlinear random effects. The resulting distribution then requires an integral equation that is of dimension equal to the number of nonlinear terms. For nonlinear functions that have linear coefficients, the improvement in computational speed and accuracy using the new algorithm can be dramatic. An illustration of the method with repeated measures data from a learning experiment is presented.     

Neuropsychological Assessment of HIV-Infected Populations in International Settings

Resource-limited regions of the world represent the areas most affected by the global HIV epidemic. Currently, there are insufficient data on the neurocognitive effects of HIV in these areas and neuropsychological studies that have been carried out thus far are marked by inconsistent methods, test batteries, and rating systems for levels of cognitive impairment. These differences in methods, along with genetic variability of both virus and host, differences in co-infections and other co-morbidities, differences in language and culture, and infrastructural deficiencies in many international settings create challenges to the assessment of neurocognitive functioning and interpretation of neuropsychological data. Identifying neurocognitive impairment directly attributable to HIV, exploring relationships between HIV-associated neurocognitive impairment, disease variables, and everyday functioning, evaluating differences in HIV-1 subtype associated neuropathology, and determining implications for treatment remain complicated and challenging goals. Endeavors to establish a more standardized approach to neurocognitive assessments across international studies in addition to accumulating appropriate normative data that will allow more accurate rating of neuropsychological test performance will be crucial to future efforts attempting to achieve these goals.     

Measuring Moral Progress

The study provides an in-depth analysis of two young adult subjects from a longitudinal study who underwent successive and significant developmental changes. Their developmental patterns, however, are only revealed by a new conception of moral stages, which is both more comprehensive and more detailed than Kohlberg’s original approach. In particular, the suggested alternative taxonomy neatly accommodates what appears as developmental anomalies in the Kohlbergian frame of reference. What is more, apart from merely matching with the observed data, the new theory also explains why the subjects developed the way they did, since it reveals the inherent cognitive conflicts at each stage and how these are resolved at the following one. Although the theory stands against the Kohlberg theory as it is, it may be understood as an extension and further development of the latter, in the sense that Kohlbergian stages are differentiated, supplemented, and theoretically substantiated within the new framework.