The purpose of this study was to investigate the construct validity of key concepts from three prominent instruments in the family therapy field (FACES III, SFI, and FES). Through analysis of the shared variance between the items and scales which make up these instruments the convergent and divergent validity of these measures was established. Specific objectives included the assessment of (1) psychometric properties of these instruments, (2) the relative importance of the different theoretical constructs (operationalized in the scales), (3) a higher order variable working throughout each construct. / Three hundred thirty-two college students participated in this study. Each subject filled out a packet containing a demographic questionnaire and each of the three instruments. The findings were analyzed through a variety of methods. Reliabilities and factor analyses were calculated for each scale within each instrument. The instruments were then combined and additional factor analyses were run on both the item and scale level. Pearson Product Correlations were calculated between each scale as well. Finally a LISREL analysis was attempted for each instrument. / The findings of this study revealed a sense of belonging as the primary dimension from which these subjects viewed their family. The dimensions of Organization, Intellectual-Cultural Orientation, and Moral-Religious Emphasis fell out as well. While several scales of the SFI and FES loaded on this central dimension, many of the dimensions researchers believed to be important to family functioning were not discerned by these family members. Thus a single higher order construct operating throughout all the scales was not found. Questions regarding the utility of these instruments were raised and implications for future research were made. / Source: Dissertation Abstracts International, Volume: 49-12, Section: B, page: 5565. / Major Professor: Mary Hicks. / Thesis (Ph.D.)--The Florida State University, 1988.

The purpose of this study was to determine whether two parallel tests could be equated effectively (i.e., minimal equating error) using the multidimensional two-parameter IRT model (M2PL). Equatings were performed on both simulated and real data sets using the common-examinee design and two abilities for each examinee (i.e., two dimensions). Item and ability parameter estimates were found using the Multidimensional Item Response Theory Estimation (MIRTE) program developed by Carlson at ACT. The amount of equating error was evaluated by a comparison of the contour plots, response surfaces, and the mean difference and absolute mean difference between the true scores and ability estimates found on both tests for the common examinees used in the equating. / The results indicated that effective equating was possible with the techniques used in this study when true scores, the response surfaces, and the contour plots were compared. When the equating of the ability estimates was examined, unsatisfactory results were found. It was concluded that tests containing more than 40 items would be needed for stable ability estimates. / Source: Dissertation Abstracts International, Volume: 49-06, Section: B, page: 2409. / Major Professor: John R. Hills. / Thesis (Ph.D.)--The Florida State University, 1988.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008. / Source: Dissertation Abstracts International, Volume: 69-11, Section: B, page: 7185. Adviser: Hua-Hua Chang. Includes bibliographical references (leaves 84-91) Available on microfilm from Pro Quest Information and Learning.

The majority of data used in outcome research has until recently been based primarily on treatment provider observations of the patient. Estimating the effect of rehabilitation treatment on functional ability is increasingly relying on patient self-report ratings. Controlling for measurement bias associated with the subjective nature of this type of data was handled by putting self-report and clinician responses to items on an 11-item functional ability instrument into the same metric using a Rasch model, allowing for an accurate picture of whether and how their perceptions differ. For this study, the traditionally clinician-rated instrument was modified to accommodate self-report ratings. The questionnaire was verbally administered during individualized discharge interviews to 112 visually-impaired geriatric veterans whose responses were then paired with clinician ratings. Clinician ratings replicate previous findings which provided a stable foundation against which the self-report ratings were compared. Fit statistics for self-report ratings demonstrate unidimensionality of the assumed functional ability construct. Construct validity, or to what extent clinicians and patients agree on what it is that is being measured (i.e., functional ability), was supported by a moderate correlation between person ability estimates. More informative, however, was the agreement on item difficulty estimates. While six of the 11 items had roughly the same difficulty estimates across the two rating samples, 5 others lacked agreement. Two possible reasons for this incongruity are (1) patient expectations about what they should be able to do by the end of rehabilitation are not realized and (2) exemplars used in eliciting self-report ratings are not as specific as those used by clinicians. The single-factor structure was also analyzed by a confirmatory factor analysis. Although the model did not meet conventional criteria of .95 for the CFI, it was the most parsimonious solution for both sets of ratings as demonstrated by a multisample analysis. These analyses indicated that self-perceived functional ability ratings may be used in place of clinician ratings on the majority of the FAST items. Until the remaining items are modified, at this point, self-report ratings may, at best, supplement, but not be used in place of, clinician ratings.

A preliminary taxonomy has been developed that differentiates between trait characteristics, the situation, manifest and subtle methods and interaction effects. The proposed taxonomy divides method into manifest and subtle categories. The obvious, surface characteristics of method are considered manifest, while the deeper structures of method that are not usually seen are considered subtle. Seven manifest method categories are described: stimulus format, response format, response categories, raters, whether the measure is direct or summative, rating the stimulus or the response, and opaque or transparent measures. Numerous subtle method categories can also be seen within the method rather than on its surface. These include semantic or verbal characteristics, direction of wording, measures of amount, ability, latency of response, possessions, situational context, associations, and behavior. Other method categories include report of others reactions, body symptoms, and time frame. Seven item level methods were tested in this study in the context of measurement of Introversion-Extraversion (IE). They included direct questions, direction of wording, situational context, time frame, report of others reactions, preference (semantic or verbal structure), and behavior. Three of these methods (preference, behavior, and direction of wording) introduced substantial method variance in the measurement of IE, and there were also several sizable trait*method interactions: direction of wording, time frame, and preference. Generalizability theory analysis (GT) proved to be quite useful in estimating method effects and interactions. By comparing the findings from GT analysis to confirmatory factor analysis (CFA) results, it became clear that there were problems with the CFA results that could not be ignored. Although generalizability analysis is limited in its ability to provide estimates of the trait and method contributions for individual measures, unfortunately, it informs us that the estimates provided by CFA are probably erroneous.

The invention of sophisticated measurement tools, such as motion capture devices, handheld computers, Bluetooth devices, eye-trackers, and brain scanners, has facilitated the collection of functional data that can be considered to arise from an underlying smooth function varying over a continuum such as time and space. Functional data analysis (FDA) is an emerging branch of statistics, which develops and applies statistical methods for the analysis of such types of data. Various FDA methods have been proposed by extending traditional multivariate statistical methods to accommodate functional data. Nonetheless, there has been little attempt to develop functional extensions of structural equation modeling (SEM), in spite of the remarkable popularity of SEM in various disciplines due to its flexibility of modeling complex relationships among observed and latent variables. This thesis thus aims to propose a general framework for functional SEM, called functional generalized structured component analysis (functional GSCA), to examine a variety of hypothesized relationships among observed and latent variables, while permitting observed variables to be functional rather than multivariate. The thesis begins by describing GSCA and penalized least squares smoothing as the two basic building blocks of the proposed method. Subsequently, it provides the technical details of the proposed method. The model for functional GSCA is provided and a penalized least squares criterion is developed for parameter estimation, which is minimized by an alternating penalized least squares algorithm. The thesis also demonstrates the usefulness of the proposed method by analyzing synthetic and real data sets. It concludes with discussions on limitations and possible extensions of the proposed method. / L'invention d'outils de mesures sophistiqués tel que les appareils de capture de mouvements, les ordinateurs portables, les appareils Bluetooth, l'oculométrie et les scanners cérébraux ont facilité la compilation de données fonctionnelles qui peuvent être considérées comme provenant d'une fonction variant sur un continuum tel que l'espace et le temps. L'analyse de données fonctionnelles (ADF) est une discipline émergente des statistiques, qui développe et applique les méthodes statistiques pour l'analyse de ce type de données. Plusieurs méthodes d'ADFs ont été proposées en prolongeant les méthodes traditionnelles de statistiques multi variées pour s'adapter aux données multifonctionnelles. Toutefois, peu de tentatives ont été effectuées dans le développement des extensions fonctionnelles des modèles d'équations structurelles (MES), malgré la popularité significative des MESs en plusieurs disciplines grâce à sa souplesse de la modélisation des relations complexes entre les variables observées et latentes. Cette thèse a donc pour objectif de proposer un cadre général pour les MESs fonctionnels, appelé l'analyse en composantes structurée généralisée fonctionnelle (ASSG fonctionnelle), qui combine l'analyse en composantes structurée généralisée fonctionnelle avec les moindres carrés pénalisés lissés par la fonction spline dans un cadre unifié. La méthode proposée peut être utilisée pour analyser une variété de relations hypothétiques entre des variables observées et latentes, tout en permettant aux variables observées d'être fonctionnelles plutôt que scalaires. La thèse commence en décrivant l'ACSG et les moindres carrés pénalisés lisser par la fonction spline tel que les deux parties constituantes de la méthode proposée. Le modèle pour l'ACSG fonctionnelle est apporté et le critère des moindres carrés pénalisés sont développés par une estimation paramétrique, qui est minimisé par un algorithme alternatif de moindres carrés pénalisés. La thèse démontre également l'utilité de la méthode proposée par l'analyse de base de données réelles et synthétiques. En conclusion, sont présentées les discussions, limites et possibles extensions de la méthode proposée.

A visual variation of the abstract is available in an interactive video format at razlab.mcgill.ca/thesis_aubertbonn.html.Once automatized, cognitive processes seldom return to the purview of control; when they do, however, this reversal happens with much difficulty.  Inspired by recent evidence introducing the role of suggestion in de-automatization, the present thesis elucidates how hypnotic suggestion renders a difficult task more automatic without extensive practice. Using MoTraK, a task inspired by a documented visual illusion, we investigated whether a specific hypnotic suggestion to view non-existent visual cues would increase performance. Our results show that highly suggestible individuals (i.e., participants who are likely to respond to hypnotic suggestion), but not controls, improved their accuracy after receiving the suggestion. We discuss how these findings, beyond theoretical accounts of hypnosis and visual perception, hold potential clinical implications.  In this regard, MoTraK may serve as a stepping stone in investigations concerning the regulation of mind and body through placebo responses/effects and top–down modulation. / Une vidéo interactive complémentaire à ce résumé est disponible sur le site Internet razlab.mcgill.ca/thesis_aubertbonn.html. Une fois automatisés, certains processus cognitifs retournent très difficilement au contrôle conscient. S'inspirant d'une branche de la recherche selon laquelle la suggestion peut faciliter la dé-automatisation de certains processus cognitifs, la présente thèse cherche à comprendre le rôle des suggestions hypnotiques dans l'automatisation des processus cognitifs difficiles. Nous avons utilisé MoTraK, une tâche basée sur une illusion visuelle documentée en recherche sur la perception, afin de déterminer si une suggestion hypnotique spécifique peut suffire à améliorer la performance sur cette tâche difficile. Nos résultats montrent que les individus hautement susceptibles aux suggestions ont, au contraire des individus non ou peu susceptibles, augmenté la justesse de leurs réponses après avoir reçu la suggestion. Nous établissons que les implications de nos résultats vont au-delà de la croissance des connaissances théoriques concernant l'hypnose et la perception visuelle et détiennent une valeur médicale et de potentielles applications cliniques. Suivant cet ordre d'idées, MoTraK peut servir d'outil pionnier dans l'exploration des interactions corps–esprit telles que l'effet placebo et les régulations descendantes (top–down).

Objectives: Individuals with chronic physical illness are 1.6 times more likely than people without chronic illness to die from suicide, controlling for mental disorders. A number of studies have described administering item 9 of the Patient Health Questionnaire-9 (PHQ-9), a self-administered measure of depression symptoms, to screen patients in medical settings for suicide ideation. This item asks whether patients have had "thoughts that you would be better off dead or of hurting yourself in some way?" Between 12% and 17% of patients in different medical settings endorse item 9 of the PHQ-9, and researchers have suggested referral of positive screens for psychiatry assessment. The item, however, is ambiguous as it includes both passive thoughts of death and more active ideas of self-harm. No studies, however, have compared PHQ-9 item 9 responses to more specific assessments of suicidal ideation or plan. Thus, the objectives of the two studies in this thesis were (1) to determine the proportion of patients with scleroderma (SSc; study 1) and coronary artery disease (CAD; study 2) who responded anything other than "not at all" to item 9 who endorsed active suicidal ideation in response to more direct questions during a structured clinical interview and (2) to assess the association between the PHQ-9 and the PHQ-8, a possible alternative measure, which does not include item 9. Methods: All patients in both studies were administered the PHQ-9. CAD patients were administered the Computerized Diagnostic Interview Schedule (C-DIS). SSc patients were administered the Composite International Diagnostic Interview (CIDI). Item 9 responses were compared to suicidal ideation and intent in the last year based on the C-DIS for CAD patients, and the CIDI for SSc patients. Scores on the PHQ-8 were obtained by subtracting item 9 out of the PHQ-9. Pearson correlations between the PHQ-8 and PHQ-9 were computed. Results: Of 1,022 patients with CAD, 110 (10.8%) endorsed item 9. Of those, 22 (19.8%) reported thoughts about committing suicide, and 9 (8.1%) reported a suicide plan at some point in the last year. Of 345 SSc patients interviewed, 31 (9.0%) endorsed item 9. Of those, 14 (45.2%) had passive thoughts of suicide or death. One (3.2%) had thought about suicide in some detail. The correlation between PHQ-9 and PHQ-8 scores was r > 0.99 for both samples. Conclusion: Item 9 appears to identify many patients who do not report active suicidal ideation and it not an ideal method for identifying patients who may be considering suicide. The PHQ-8 may be a better option for assessment of depressive symptoms than the PHQ-9 in SSc and CAD patients. / Objectifs: Les individus souffrant d'une maladie chronique sont 1,6 fois plus susceptibles de mourir par suicide que les personnes ne souffrant pas de maladie chronique, en considérant statistiquement les maladies mentales. Un certain nombre d'études a décrit l'utilisation de l'énoncé 9 du questionnaire d'auto-évaluation de la santé par le patient (PHQ-9). Ce questionnaire utilisé dans les milieux médicaux, mesure les symptômes de dépression des patients afin de dépister des idées suicidaires chez ceux-ci. Cet énoncé demande aux patients s'ils ont eu des « pensées selon lesquelles ils seraient mieux morts ou s'ils ont eu l'idée de se faire du mal ». Entre 12% et 17% des patients de différents milieux médicaux ont endossé l'énoncé 9 du PHQ-9, et les chercheurs ont suggéré que les dépistages positifs soient référés pour une évaluation psychiatrique. Cet énoncé contient cependant une ambigüité, puisqu'il intègre à la fois des pensées passives liées à la mort, et des pensées plus actives liées à l'idée de se faire du mal. Aucune étude n'a toutefois comparé les réponses de l'énoncé 9 du PHQ-9 à des évaluations plus spécifiques à des idées ou à un plan suicidaires. Ainsi, les objectifs des deux études comprises dans cette thèse sont (1) de déterminer la proportion de patients atteints de sclérodermie (SSc, étude 1) et de maladie des artères coronaires (MAC; étude 2) qui ont répondu autre chose que « pas du tout » à l'énoncé 9, et qui ont endossé des idées suicidaires actives en répondant à des questions directes au cours d'une entrevue clinique structurée; et (2) d'évaluer l'association entre le PHQ-9 et le PHQ-8, une mesure alternative possible ne comprenant pas l'énoncé 9. Méthodes: Tous les patients des deux études ont répondu au PHQ-9. Les patients MAC ont répondu au C-DIS (Computerized Diagnostic Interview Schedule) et les patients SSc ont répondu au CIDI (Composite International Diagnostic Interview). Les réponses à l'énoncé 9 ont été comparées aux idées et aux intentions suicidaires de la dernière année, en se basant sur les réponses au C-DIS pour les patients MAC, et au CIDI pour les patients SSc. Les résultats du PHQ-8 ont été obtenus en soustrayant l'énoncé 9 des PHQ-9. Les corrélations de Pearson ont été calculées entre le PHQ-8 et le PHQ-9. Résultats : Des 1 022 patients atteints de MAC, 110 (10,8%) ont endossé l'énoncé 9. De ce nombre, 22 (19,8%) ont rapporté des pensées suicidaires, et 9 (8,1%) ont eu un plan de suicide au courant de la dernière année. Des 345 patients SSc interviewés, 31 (9,0%) ont endossé l'énoncé 9. De ce nombre, 14 (45,2%) ont eu des pensées passives liées au suicide ou à la mort. Un répondant (3,2%) a pensé au suicide de façon détaillée. La corrélation entre les résultats du PHQ-9 et du PHQ-8 était de r> 0,99 pour les deux échantillons. Conclusion: L'énoncé 9 semble identifier plusieurs patients ne rapportant pas d'idées suicidaires actives et ne représente une méthode idéale d'identification des patients envisageant le suicide. Pour les patients atteints de SSc et de MAC, le PHQ-8 pourrait constituer une meilleure mesure d'évaluation des symptômes de dépression, comparativement au PHQ-9.

In structural equation models with latent variables, maximum likelihood (ML) estimation is currently the most prevailing estimation method. However, the ML method fails to provide accurate solutions in a number of situations including those involving small sample sizes, nonnormality, and model misspecification. To over come these difficulties, regularized extensions of two-stage least squares estimation are proposed that incorporate a ridge type of regularization in the estimation of parameters. Two simulation studies and two empirical applications demonstrate that the proposed method is a promising alternative to both the maximum likelihood and non-regularized two-stage least squares estimation methods. An optimal value of the regularization parameter is found by the K-fold cross validation technique. A nonparametric bootstrap method is used to evaluate the stability of solutions. A goodness-of-fit measure is used for assessing the overall fit. / Dans les modèles d'équations structurales avec des variables latentes, l'estimation demaximum devraisemblance est la méthode d'estimation la plus utilisée. Par contre, la méthode de maximum devraisemblance souvent ne réussit pas á fournir des solutions exactes, par exemple lorsque les échantillons sont petits, les données ne sont pas normale, ou lorsque le modèle est mal specifié. L'estimation des moindres carrés á deux-phases est asymptotiquement sans distribution et robuste contre mauvaises spécifications, mais elle manque de robustesse quand les chantillons sont petits. Afin de surmonter les trois difficultés mentionnés ci-dessus et d'obtenir une estimation plus exacte, des extensions régularisées des moindres carrés á deux phases sont proposé á qui incorporent directement un type de régularisation dans les modèles d'équations structurales avec des variables latentes. Deux études de simulation et deux applications empiriques démontrent que la méthode propose est une alternative prometteuse aux méthodes de maximum vraisemblance et de l'estimation des moindres carrés á deux-phases. Un paramètre de régularisation valeur optimale a été trouvé par la technique de validation croisé d'ordre K. Une méthode non-paramétrique Bootstrap est utilisée afin d'évaluer la stabilité des solutions. Une mesure d'adéquation est utilisée pour estimer l'adéquation globale.

<p> Distracted driving can be dangerous and new technology is being implemented into vehicles that will likely increase the amount of distraction present. New input device technology has made it possible to use force feedback to aid in task completion which may help reduce the cognitive load of secondary tasks. In the present study, participants performed a simulated lane change task while simultaneously completing a target selection task. Participants used the Novint Falcon input device which is capable of applying guiding force feedback. Two levels of two different force feedback models were used on the secondary task as well as a no force feedback baseline. Results indicated that when force feedback was enabled on the secondary task and at its highest magnitude, driving performance was better than when no force feedback was enabled. Additionally, secondary task performance was consistent with previous single-task force feedback research.</p>