Modelagem de dados de resposta ao item sob efeito de speededness

Em testes nos quais uma quantidade considerável de indivíduos não dispõe de tempo suciente para responder todos os itens temos o que é chamado de efeito de Speededness. O uso do modelo unidimensional da Teoria da Resposta ao Item (TRI) em testes com speededness pode nos levar a uma série de interpretações errôneas uma vez que nesse modelo é suposto que os respondentes possuem tempo suciente para responder todos os itens. Nesse trabalho, desenvolvemos uma análise Bayesiana do modelo tri-dimensional da TRI proposto por Wollack e Cohen (2005) considerando uma estrutura de dependência entre as distribuições a priori dos traços latentes a qual modelamos com o uso de cópulas. Apresentamos um processo de estimação para o modelo proposto e fazemos um estudo de simulação comparativo com a análise realizada por Bazan et al. (2010) na qual foi utilizada distribuições a priori independentes para os traços latentes. Finalmente, fazemos uma análise de sensibilidade do modelo em estudo e apresentamos uma aplicação levando em conta um conjunto de dados reais proveniente de um subteste do EGRA, chamado de Nonsense Words, realizado no Peru em 2007. Nesse subteste os alunos são avaliados por via oral efetuando a leitura, sequencialmente, de 50 palavras sem sentidos em 60 segundos o que caracteriza a presença do efeito speededness.

Assessment of data quality in a multi-centre cross-sectional study of participation and quality of life of children with cerebral palsy

Background: SPARCLE is a cross-sectional survey in nine European regions, examining the relationship of the environment of children with cerebral palsy to their participation and quality of life. The objective of this report is to assess data quality, in particular heterogeneity between regions, family and item non-response and potential for bias. Methods: 1,174 children aged 8–12 years were selected from eight population-based registers of children with cerebral palsy; one further centre recruited 75 children from multiple sources. Families were visited by trained researchers who administered psychometric questionnaires. Logistic regression was used to assess factors related to family non-response and self-completion of questionnaires by children. Results: 431/1,174 (37%) families identified from registers did not respond: 146 (12%) were not traced; of the 1,028 traced families, 250 (24%) declined to participate and 35 (3%) were not approached. Families whose disabled children could walk unaided were more likely to decline to participate. 818 children entered the study of which 500 (61%) self-reported their quality of life; children with low IQ, seizures or inability to walk were less likely to self-report. There was substantial heterogeneity between regions in response rates and socio-demographic characteristics of families but not in age or gender of children. Item non-response was 2% for children and ranged from 0.4% to 5% for questionnaires completed by parents. Conclusion: While the proportion of untraced families was higher than in similar surveys, the refusal rate was comparable. To reduce bias, all analyses should allow for region, walking ability, age and socio-demographic characteristics. The 75 children in the region without a population based register are unlikely to introduce bias

Self-reported health needs and use of primary health care services by adolescents enrolled in post-mandatory schools or vocational training programmes in Switzerland.

BACKGROUND: The second Swiss Multicenter Adolescent Survey on Health (SMASH02) was conducted among a representative sample (n = 7428) of students and apprentices aged 16 to 20 from the three language areas of Switzerland during the year 2002. This paper reports on health needs expressed by adolescents and their use of health care services over the 12 months preceding the survey. METHODS: Nineteen cantons representing 80% of the resident population agreed to participate. A complex iterative random cluster sample of 600 classes was drawn with classes as primary sampling unit. The participation rate was 97.7% for the classes and 99.8% for the youths in attendance. The self-administered questionnaire included 565 items. The median rate of item non-response was 1.8%. Ethical and legal requirements applying to surveys of adolescent populations were respected. RESULTS: Overall more than 90% of adolescents felt in good to excellent health. Suffering often or very often from different physical complaints or pain was also reported such as headache (boys: 15.9%, girls: 37.4%), stomach-ache (boys: 9.7%, girls: 30.0%), joint pain (boys: 24.7%, girls: 29.5%) or back pain (boys: 24.3%, girls: 34.7%). Many adolescents reported a need for help on psychosocial and lifestyle issues, such as stress (boys: 28.5%, girls: 47.7%) or depression (boys: 18.9%, girls: 34.4%). Although about 75% of adolescents reported having consulted a general practitioner and about one-third having seen another specialist, reported reasons for visits do not correspond to the expressed needs. Less than 10% of adolescents had visited a psychiatrist, a family planning centre or a social worker. CONCLUSIONS: The reported rates of health services utilisation by adolescents does not match the substantial reported needs for help in various areas. This may indicate that the corresponding problems are not adequately detected and/or addressed by professionals from the health and social sectors.

Méthodes de rééchantillonnage en méthodologie d'enquête

Le sujet principal de cette thèse porte sur l'étude de l'estimation de la variance d'une statistique basée sur des données d'enquête imputées via le bootstrap (ou la méthode de Cyrano). L'application d'une méthode bootstrap conçue pour des données d'enquête complètes (en absence de non-réponse) en présence de valeurs imputées et faire comme si celles-ci étaient de vraies observations peut conduire à une sous-estimation de la variance. Dans ce contexte, Shao et Sitter (1996) ont introduit une procédure bootstrap dans laquelle la variable étudiée et l'indicateur de réponse sont rééchantillonnés ensemble et les non-répondants bootstrap sont imputés de la même manière qu'est traité l'échantillon original. L'estimation bootstrap de la variance obtenue est valide lorsque la fraction de sondage est faible. Dans le chapitre 1, nous commençons par faire une revue des méthodes bootstrap existantes pour les données d'enquête (complètes et imputées) et les présentons dans un cadre unifié pour la première fois dans la littérature. Dans le chapitre 2, nous introduisons une nouvelle procédure bootstrap pour estimer la variance sous l'approche du modèle de non-réponse lorsque le mécanisme de non-réponse uniforme est présumé. En utilisant seulement les informations sur le taux de réponse, contrairement à Shao et Sitter (1996) qui nécessite l'indicateur de réponse individuelle, l'indicateur de réponse bootstrap est généré pour chaque échantillon bootstrap menant à un estimateur bootstrap de la variance valide même pour les fractions de sondage non-négligeables. Dans le chapitre 3, nous étudions les approches bootstrap par pseudo-population et nous considérons une classe plus générale de mécanismes de non-réponse. Nous développons deux procédures bootstrap par pseudo-population pour estimer la variance d'un estimateur imputé par rapport à l'approche du modèle de non-réponse et à celle du modèle d'imputation. Ces procédures sont également valides même pour des fractions de sondage non-négligeables.

Inférence robuste à la présence des valeurs aberrantes dans les enquêtes

Cette thèse comporte trois articles dont un est publié et deux en préparation. Le sujet central de la thèse porte sur le traitement des valeurs aberrantes représentatives dans deux aspects importants des enquêtes que sont : l’estimation des petits domaines et l’imputation en présence de non-réponse partielle. En ce qui concerne les petits domaines, les estimateurs robustes dans le cadre des modèles au niveau des unités ont été étudiés. Sinha & Rao (2009) proposent une version robuste du meilleur prédicteur linéaire sans biais empirique pour la moyenne des petits domaines. Leur estimateur robuste est de type «plugin», et à la lumière des travaux de Chambers (1986), cet estimateur peut être biaisé dans certaines situations. Chambers et al. (2014) proposent un estimateur corrigé du biais. En outre, un estimateur de l’erreur quadratique moyenne a été associé à ces estimateurs ponctuels. Sinha & Rao (2009) proposent une procédure bootstrap paramétrique pour estimer l’erreur quadratique moyenne. Des méthodes analytiques sont proposées dans Chambers et al. (2014). Cependant, leur validité théorique n’a pas été établie et leurs performances empiriques ne sont pas pleinement satisfaisantes. Ici, nous examinons deux nouvelles approches pour obtenir une version robuste du meilleur prédicteur linéaire sans biais empirique : la première est fondée sur les travaux de Chambers (1986), et la deuxième est basée sur le concept de biais conditionnel comme mesure de l’influence d’une unité de la population. Ces deux classes d’estimateurs robustes des petits domaines incluent également un terme de correction pour le biais. Cependant, ils utilisent tous les deux l’information disponible dans tous les domaines contrairement à celui de Chambers et al. (2014) qui utilise uniquement l’information disponible dans le domaine d’intérêt. Dans certaines situations, un biais non négligeable est possible pour l’estimateur de Sinha & Rao (2009), alors que les estimateurs proposés exhibent un faible biais pour un choix approprié de la fonction d’influence et de la constante de robustesse. Les simulations Monte Carlo sont effectuées, et les comparaisons sont faites entre les estimateurs proposés et ceux de Sinha & Rao (2009) et de Chambers et al. (2014). Les résultats montrent que les estimateurs de Sinha & Rao (2009) et de Chambers et al. (2014) peuvent avoir un biais important, alors que les estimateurs proposés ont une meilleure performance en termes de biais et d’erreur quadratique moyenne. En outre, nous proposons une nouvelle procédure bootstrap pour l’estimation de l’erreur quadratique moyenne des estimateurs robustes des petits domaines. Contrairement aux procédures existantes, nous montrons formellement la validité asymptotique de la méthode bootstrap proposée. Par ailleurs, la méthode proposée est semi-paramétrique, c’est-à-dire, elle n’est pas assujettie à une hypothèse sur les distributions des erreurs ou des effets aléatoires. Ainsi, elle est particulièrement attrayante et plus largement applicable. Nous examinons les performances de notre procédure bootstrap avec les simulations Monte Carlo. Les résultats montrent que notre procédure performe bien et surtout performe mieux que tous les compétiteurs étudiés. Une application de la méthode proposée est illustrée en analysant les données réelles contenant des valeurs aberrantes de Battese, Harter & Fuller (1988). S’agissant de l’imputation en présence de non-réponse partielle, certaines formes d’imputation simple ont été étudiées. L’imputation par la régression déterministe entre les classes, qui inclut l’imputation par le ratio et l’imputation par la moyenne sont souvent utilisées dans les enquêtes. Ces méthodes d’imputation peuvent conduire à des estimateurs imputés biaisés si le modèle d’imputation ou le modèle de non-réponse n’est pas correctement spécifié. Des estimateurs doublement robustes ont été développés dans les années récentes. Ces estimateurs sont sans biais si l’un au moins des modèles d’imputation ou de non-réponse est bien spécifié. Cependant, en présence des valeurs aberrantes, les estimateurs imputés doublement robustes peuvent être très instables. En utilisant le concept de biais conditionnel, nous proposons une version robuste aux valeurs aberrantes de l’estimateur doublement robuste. Les résultats des études par simulations montrent que l’estimateur proposé performe bien pour un choix approprié de la constante de robustesse.

Adjusted jackknife for imputation under unequal probability sampling without replacement

Imputation is commonly used to compensate for item non-response in sample surveys. If we treat the imputed values as if they are true values, and then compute the variance estimates by using standard methods, such as the jackknife, we can seriously underestimate the true variances. We propose a modified jackknife variance estimator which is defined for any without-replacement unequal probability sampling design in the presence of imputation and non-negligible sampling fraction. Mean, ratio and random-imputation methods will be considered. The practical advantage of the method proposed is its breadth of applicability.

Evaluation of a skin self examination attitude scale using an item response theory model approach

Introduction The Skin Self-Examination Attitude Scale (SSEAS) is a brief measure that allows for the assessment of attitudes in relation to skin self-examination. This study evaluated the psychometric properties of the SSEAS using Item Response Theory (IRT) methods in a large sample of men ≥ 50 years in Queensland, Australia. Methods A sample of 831 men (420 intervention and 411 control) completed a telephone assessment at the 13-month follow-up of a randomized-controlled trial of a video-based intervention to improve skin self-examination (SSE) behaviour. Descriptive statistics (mean, standard deviation, item–total correlations, and Cronbach’s alpha) were compiled and difficulty parameters were computed with Winsteps using the polytomous Rasch Rating Scale Model (RRSM). An item person (Wright) map of the SSEAS was examined for content coverage and item targeting. Results The SSEAS have good psychometric properties including good internal consistency (Cronbach’s alpha = 0.80), fit with the model and no evidence for differential item functioning (DIF) due to experimental trial grouping was detected. Conclusions The present study confirms the SSEA scale as a brief, useful and reliable tool for assessing attitudes towards skin self-examination in a population of men 50 years or older in Queensland, Australia. The 8-item scale shows unidimensionality, allowing levels of SSE attitude, and the item difficulties, to be ranked on a single continuous scale. In terms of clinical practice, it is very important to assess skin cancer self-examination attitude to identify people who may need a more extensive intervention to allow early detection of skin cancer.

The Development and Testing of a New Version of the Cognitive Reflection Test Applying Item Response Theory (IRT)

The cognitive reflection test (CRT) is a short measure of a person's ability to resist intuitive response tendencies and to produce a normatively correct response, which is based on effortful reasoning. Although the CRT is a very popular measure, its psychometric properties have not been extensively investigated. A major limitation of the CRT is the difficulty of the items, which can lead to floor effects in populations other than highly educated adults. The present study aimed at investigating the psychometric properties of the CRT applying item response theory analyses (a two-parameter logistic model) and at developing a new version of the scale (the CRT-long), which is appropriate for participants with both lower and higher levels of cognitive reflection. The results demonstrated the good psychometric properties of the original, as well as the new scale. The validity of the new scale was also assessed by measuring correlations with various indicators of intelligence, numeracy, reasoning and decision-making skills, and thinking dispositions. Moreover, we present evidence for the suitability of the new scale to be used with developmental samples. Finally, by comparing the performance of adolescents and young adults on the CRT and CRT-long, we report the first investigation into the development of cognitive reflection.

A comparison of discriminant logistic regression and Item Response Theory Likelihood-Ratio Tests for Differential Item Functioning (IRTLRDIF) in polytomous short tests

Resumen tomado de la publicaci??n

Detection of determinant genes and diagnostic via Item Response Theory

ABSTRACT: This work presents a method to analyze characteristics of a set of genes that can have an influence in a certain anomaly, such as a particular type of cancer. A measure is proposed with the objective of diagnosing individuals regarding the anomaly under study and some characteristics of the genes are analyzed. Maximum likelihood equations for general and particular cases are presented.

Multidimensional item response theory models with general and specific latent traits for ordinal data

The aim of the thesis is to propose a Bayesian estimation through Markov chain Monte Carlo of multidimensional item response theory models for graded responses with complex structures and correlated traits. In particular, this work focuses on the multiunidimensional and the additive underlying latent structures, considering that the first one is widely used and represents a classical approach in multidimensional item response analysis, while the second one is able to reflect the complexity of real interactions between items and respondents. A simulation study is conducted to evaluate the parameter recovery for the proposed models under different conditions (sample size, test and subtest length, number of response categories, and correlation structure). The results show that the parameter recovery is particularly sensitive to the sample size, due to the model complexity and the high number of parameters to be estimated. For a sufficiently large sample size the parameters of the multiunidimensional and additive graded response models are well reproduced. The results are also affected by the trade-off between the number of items constituting the test and the number of item categories. An application of the proposed models on response data collected to investigate Romagna and San Marino residents' perceptions and attitudes towards the tourism industry is also presented.