The purpose of this study was two-fold: examine junior high school pre-service science teachers' chemical reasoning; and establish the extent to which the pre-service science teachers' chemical abilities explain their chemical reasoning. A sample comprised 165 junior high school pre-service science teachers at Mufulira College of Education in Zambia. There were 82 males and 83 females. Data were collected using a Chemical Concept Reasoning Test (CCRT). Pre-service science teachers' chemical reasoning was established through qualitative analysis of their responses to test items. The Rasch Model was used to determine the pre-service teachers' chemical abilities and item difficulty. Results show that most pre-service science teachers had incorrect chemical reasoning on chemical concepts assessed in this study. There was no significant difference in chemical understanding between the Full-Time and Distance Education pre-service science teachers, and between second and third year pre-service science teachers. However, there was a significant difference in chemical understanding between male and female pre-service science teachers. Male pre-service science teachers showed better chemical understanding than female pre-service science teachers. The Rasch model revealed that the pre-service science teachers had low chemical abilities, and the CCRT was very difficult for this group of pre-service science teachers. As such, their incorrect chemical reasoning was attributed to their low chemical abilities. These results have implications on science teacher education, chemistry teaching and learning, and chemical education research.

A pressing need for efficient personalized recommendations has emerged in crowdsourcing systems. On the one hand, workers confront a flood of tasks, and they often spend too much time to find tasks matching their skills and interests. Thus, workers want effective recommendation of the most suitable tasks with regard to their skills and preferences. On the other hand, requesters sometimes receive results in low-quality completion since a less qualified worker may start working on a task before a better-skilled worker may get hands on. Thus, requesters want reliable recommendation of the best workers for their tasks in terms of workers' qualifications and accountability. The task and worker recommendation problems in crowdsourcing systems have brought up unique characteristics that are not present in traditional recommendation scenarios, i.e., the huge flow of tasks with short lifespans, the importance of workers' capabilities, and the quality of the completed tasks. These unique features make traditional recommendation approaches (mostly developed for e-commerce markets) no longer satisfactory for task and worker recommendation in crowdsourcing systems. In this research, we reveal our insight into the essential difference between the tasks in crowdsourcing systems and the products/items in e-commerce markets, and the difference between buyers' interests in products/items and workers' interests in tasks. Our insight inspires us to bring up categories as a key mediation mechanism between workers and tasks. We propose a two-tier data representation scheme (defining a worker-category suitability score and a worker-task attractiveness score) to support personalized task and worker recommendation. We also extend two optimization methods, namely least mean square error (LMS) and Bayesian personalized rank (BPR) in order to better fit the characteristics of task/worker recommendation in crowdsourcing systems. We then integrate the proposed representation scheme and the extended optimization methods along with the two adapted popular learning models, i.e., matrix factorization and kNN, and result in two lines of top-N recommendation algorithms for crowdsourcing systems: (1) Top-N-Tasks (TNT) recommendation algorithms for discovering the top-N most suitable tasks for a given worker, and (2) Top-N-Workers (TNW) recommendation algorithms for identifying the top-N best workers for a task requester. An extensive experimental study is conducted that validates the effectiveness and efficiency of a broad spectrum of algorithms, accompanied by our analysis and the insights gained.

xvi, 116 p. A print copy of this thesis is available through the UO Libraries. Search the library catalog for the location and call number. / A significant challenge in developing alternate assessments is obtaining suitable sample sizes. This study investigated whether psychometric characteristics of mathematic alternate assessment items created for 2% students in grade 8 can be meaningfully estimated with data obtained from general education students in lower grades. Participants included 23 2% students in grade 8 and 235 general education students in grades 6-8. Twenty three 2% students were identified through the Student Performance Test (10 standard items and 10 2% items) and the Teacher Perception Survey. Performance on 10 2% items by the 2% students and the general education students were analyzed to address the questions: (a) are there grade levels at which the item parameters estimated from general education students in grade 6-8 are not different from those obtained using the 2% student sample? and (b) are there grade levels at which the estimated ability of general education students in grades 6-8 are not different the 2% student sample in grade 8? Results indicated that the item response patterns of 2% students in grade 8 were comparable to those of general education students in grades 6 and 7. Additionally, 2% students in grade 8 showed comparable mathematics performance on 2% items when compared to general education students in grades 6 and 7. Considering the content exposure of students in lower grades, this study concluded that data from general education students in grade 7 would be more appropriate to be used in designing alternate assessment for 2% students in grade 8 than data from students in grade 6. The general conclusion is that using data obtained from general education students in lower grade levels may be an appropriate and efficient method of designing alternate assessment items. / Advisers: Dr. Beth Ham, Co-Chair; Dr. Paul Yovanoff, Co-Chair

The Chinese government has announced the 2013 Guidelines for developing a national system for early detection of disability among children under 6 years of age. However, given limited resources, challenges exist with developmental measures required in the 2013 Guidelines. In order to meet the needs for a more accurate and cost-efficient measure for developmental assessment, the Ages & Stages Questionnaires:INVENTORY was translated into Simplified Chinese, and validated on a regional sample of 812 Chinese children ages from 1-25 months. Psychometric properties were examined; data from previous studies on the ASQ:INVENTORY in the U.S. were compared to identify differences between the two countries. Results indicated that the Chinese ASQ:INVENTORY was an instrument with sufficient internal consistency, reliability and validity. It was well accepted by parents and professionals in China. Findings suggested that the Chinese ASQ:INVENTORY provides a promising alternative measure for screening and diagnosing developmental delays in young children in China. Implications for future research and implementation are discussed.

À partir d’un corpus de 492 faits divers criminels relevés dans les quotidiens parisiens entre 1836 et 1881, ce travail s’efforce de montrer comment ce genre de discours journalistique est un lieu de citation d’autres discours, en particulier professionnels. La démarche stylistique adoptée, qui s’appuie sur les outils de l’analyse du discours, souligne la façon dont ces technolectes circulent dans la rubrique des faits divers, et sont souvent moins des citations explicites que des emprunts à des interdiscours volontiers constitués de clichés et de formules toutes prêtes et toutes faites. C’est ainsi le figement du fait divers qu’on met en avant, figement narratif, syntaxique et lexical ; ce figement lui vient parfois directement des discours auxquels il emprunte, et qui comme lui n’hésitent pas à fictionnaliser voire à inventer un événement. La démonstration s’attache à étudier la citation à l’intérieur de l’espace journalistique, afin de mettre en lumière la façon dont les faits-divers s’approprient l’article d’un autre, et à étudier leur position de sur- ou de sous-énonciateur par rapport au texte originel. C’est cette même position du fait-diversi qui est interrogée dans son rapport aux interdiscours médicaux et policiers ; ces derniers sont en effet des sources privilégiées de l’information fait-divers. L’analyse se reporte dans le même temps aux romans du siècle,feuilletons comme œuvres réalistes et naturalistes, avant de se pencher, à la fin de l’étude, sur les rapports du fait divers et de ces ouvrages. Il s’agit alors de montrer comment le fait divers,traversé de diverses voix, est un discours qui circule également dans la littérature de l’époque. / This work focuses on a corpus of 492 crime news items released in Parisian dailies between 1836 and 1881 and aims at showing how this specific journalistic discourse quotesother forms of discourse (particularly professional ones). The stylistic approach chosen, using discourse analysis tools, underlines the way those technolects circulate in crime news items and shows they are not so much explicit quotes as borrowings from interdiscourses often made up of clichés and ready-made, set phrases. This freezing of the crime news item is what stands out here: a narrative, syntactic and lexical freezing, stemming sometimes straight from the discourses from which it borrows. Both the crime news items and the discourses borrowedtend to fictionalize or even invent a drama.The work focuses on the quote within the journalistic space, so as to highlight how the crime news item writers make someone else’s article their own and studies the writers’ posture (as an over or an under-enunciator) regarding the original text. This same posture is also questioned in relation to both medical and police interdiscourses, which are the two privileged sources of information for crime news items. In the same time, the analysis refers to contemporary novels, whether serials or realist and naturalist works, before focusing on their relationships to crime news items. The aim is thus to show how the crime news item is a multiple-voice discourse which also circulates in the literature of that time.

OLIVEIRA, Kátia Michelle Matos de. Um Estudo da Evolução da GQT por meio do modelo de resposta gradual da teoria da resposta ao item. 2010. 134f. Dissertação(Mestrado em Gestão Logística e Pesquisa Operacional)- Pró-Reitoria de Pesquisa e Pós Graduação, Universidade Federal do Ceará, Fortaleza,2010. / Submitted by Winne Gomes da Silva (winnegomez87@gmail.com) on 2012-06-08T14:29:55Z No. of bitstreams: 1 2010_dis_kmmoliveira.pdf: 2893670 bytes, checksum: 2eab8f070b3bb9e1c2b7e648d3416f20 (MD5) / Approved for entry into archive by Nirlange Queiroz(nirlange@gmail.com) on 2012-07-06T12:42:06Z (GMT) No. of bitstreams: 1 2010_dis_kmmoliveira.pdf: 2893670 bytes, checksum: 2eab8f070b3bb9e1c2b7e648d3416f20 (MD5) / Made available in DSpace on 2012-07-06T12:42:06Z (GMT). No. of bitstreams: 1 2010_dis_kmmoliveira.pdf: 2893670 bytes, checksum: 2eab8f070b3bb9e1c2b7e648d3416f20 (MD5) Previous issue date: 2010 / Aiming to evaluate the degree of maturity in the use of tools and techniques of Total Quality Management (TQM), and its evolution over the past 10 years, in the companies of transformation and construction of medium and large scale in the State of Ceara, this study used the Graded Response Model of Item Response Theory (IRT). This model was designed to examine responses graded and capable of ordinate. As a basis of comparison for possible evaluates in the maturity, it was used the work done by Alexander in 1999. The methodology used for collecting data was the quantitative survey, using a structured questionnaire in Likert scale with five response categories. The study used a model for assessment of maturity by creating a standardized measurement scale with the support of the IRT, whereby it became possible to compare and to check that there was a low evolution of maturity of organizations, especially taking into account the importance of quality as a competitive differential for maintenance companies in the global market. The scale constructed may serve as a basis to enable companies to identify potential practice has not implanted, allows, still monitoring their development level of maturity / Com o objetivo de avaliar o grau de maturidade, quanto à utilização de ferramentas e técnicas da Gestão pela Qualidade Total (GQT), e sua evolução nos últimos 10 anos, nas empresas de transformação e construção civil de portes médio e grande no Estado do Ceará, o presente trabalho utilizou o Modelo de Resposta Gradual da Teoria da Resposta ao Item (TRI). Este modelo foi projetado para analisar respostas graduadas e passíveis de ordenação. Como base de comparação para verificar uma possível evolução na maturidade, foi utilizado o trabalho realizado por Alexandre (1999). A metodologia empregada para a coleta de dados foi a pesquisa quantitativa, através de um questionário estruturado na escala de Likert com 5 categorias de resposta. O estudo utilizou o modelo de Resposta Gradual da TRI para avaliação da maturidade criando-se uma escala de medida padronizada, através do qual se tornou possível a comparação e a verificação de que houve uma evolução pouco significativa da maturidade das empresas, principalmente levando-se em conta a importância da qualidade como diferencial competitivo para a manutenção das empresas no mercado globalizado. A escala construída pode auxiliar na identificação de práticas não implantadas que poderiam melhorar a qualidade dos produtos.

A crescente importância da QV enquanto desfecho em saúde fez o grupo WHOQOL, da OMS, elaborar medidas de avaliação de QV para utilização internacional. Com a necessidade de instrumentos menores que demandassem pouco tempo para o preenchimento, foi desenvolvido o EUROHIS-QOL 8-ITEM, originado dos itens do WHOQOL- BREF. Objetivos: Testar as propriedades psicométricas do EUROHIS-QOL 8-ITEM em uma amostra brasileira. Métodos: A amostra foi constituída de 325 indivíduos. Eles foram divididos em dois grupos, 151 indivíduos constituiram o grupo dos doentes do Hospital de Clínicas de Porto Alegre, RS, e 174 o grupo dos saudáveis. Para a avaliação das propriedades psicométricas do índice EUROHIS-QOL 8-ITEM, foram realizadas algumas análises. A Consistência Interna, foi avaliada usando o Alpha de Cronbach. A validade discriminante foi avaliada comparando o grupo de doentes e saudáveis e também o de deprimidos e não-deprimidos. A análise da validade convergente ocorreu através da correlação do EUROHIS-QOL 8-ITEM com diferentes medidas de QV já validadas e reconhecidas, o SF-36 e o WHOQOL-BREF. A análise fatorial foi avaliada usando o modelo de equação estrutural (SEM). Avaliou-se a unidimensionalidade usando as propriedades do modelo de Rasch. Resultados: A consistência interna avaliada pelo Alpha de Cronbach (com valor de 0,81) monstrou-se boa. O índice EURO-HIS–QOL 8-ITEM também mostrou boa capacidade discriminativa entre os grupos de doentes e saudáveis (média1=3,32; DP1=0,70; média2=3,77; DP2=0,63 t =6,12, p < 0,001) e também entre os grupos de deprimidos e não deprimidos (média3=3,14; DP3=0,69; média4=3,72; DP4=0,61 t = 7,25 p <0,001). O instrumento demonstrou boa validade convergente, através de correlações significativas (p < 0,001) entre o EUROHIS-QOL 8-ITEM e todos os domínidos do WHOQOL- BREF (QV Geral r = 0,47; Saúde Geral r= 0,54; Físico r = 0,69; Psicológico r = 0,62; Relações Sociais r = 0,55; Meio Ambiente r = 0,55) e entre o EUROHIS-QOL 8-ITEM e os domínios do SF-36 (QV Geral r = 0,36; Capacidade Funcional r =0,49; Limitação Física r = 0,45; Dor r = 0,43; Saúde Geral r = 0,52; Vitalidade r = 0,21; Aspectos Sociais r = 0,45; Aspectos Emocionais r = 0,38 e Saúde Mental r = 0,17), com exceção do domínio social (p = 0,38). Na análise de Rasch, as medidas de ajuste geral do modelo apresentaram adequado desempenho estatístico e foi considerado um bom ajuste logo na primeira avaliação (Ajuste de resíduo Interação Item pessoa: M= 0,01 e DP= 1,51; ajuste de resíduo de pessoa: M = -0,38 e DP= 1,19 e Item traço: Item total X²=69,60 p=0,00. Personal Separation Index = 0,82), ou seja, os resíduos foram aceitáveis, não foi preciso excluir itens. O EUROHIS-QOL 8-ITEM, apresentou bom ajuste aos dados na análise fatorial confirmatória (X²= 18,46; DF= 15; CFI= 0,99; RMSEA= 0,03; GFI = 0,99; RMR=0,03; P = p,24). Conclusão: O EURHIS-QOL 8-ITEM, validado em amostras europeias apresentou adequadas propriedades psicométricas neste estudo, mostrando-se uma medida confiável de QV para ser usada em amostras brasileiras. / In the 70s, quality of life began to be considered a health outcome. With the growing importance of this assessment in different areas of medicine, there were no instruments developed in the cross-cultural perspective for international use. In this context, quality of life assessement outcome measures were developed by the WHOQOL group from WHO. With the need of shorter instruments which demanded less time to be filled in, the EUROHIS-QOL 8 ITEM was developed, originated from WHOQOL-BREF items. Objectives: Test the psychometric properties of EUROHIS-QOL 8-ITEM in a Brazilian sample. Methods: The sample consisted of 325 individuals. They were divided in to two groups, 151 subjects constituted the group of patients from the Hospital de Clinicas de Porto Alegre, RS, and 174 subjects the group of healthy controls. Some analyses were performed for the assessment of the psychometric properties of EUROHIS-QOL 8-ITEM index. Internal consistency was measured by using Cronbach’s alpha. Discriminant validity was assessed by comparing the group of patients and healthy controls and also the depressed and nondepressed. Analysis of convergent validity was through the correlation of EUROHIS-QOL 8-ITEM with different quality of life measures already validated and recognized as the SF-36 and WHOQO-BREF. Factor analysis was assessed using structural equation model (SEM). Unidimensionality was assessed using the properties of the Rasch model. Results: The Cronbach's alpha showed good internal consistency (with a value of 0.81). The measure also showed good discriminative ability between the groups of patients and healthy controls (mean1=3.32; SD1=0.70; mean2=3.77; SD2=0.63 t =6.12, p = 0,00) and between the depressed and nondepressed groups (mean3=3.14; SD3=0.69; mean4=3.72; SD4=0.61 t = 7.25 p =0.00). The instrument showed good convergent validity through significant correlations ( p < 0.001 ) between the EUROHIS–QOL 8-ITEM and all domains of WHOQOL-BREF (QV Overall r = 0.47; General Health r= 0.54; Physical Health r = 0.69; Psychological Health r = 0.62; Social Relationship r = 0.55; Meio Environment r = 0.55) and between EUROHIS-QOL 8-ITEM and the domains of the SF-36 (QV Overall r = 0.36; Functioning Physical r =0.49; Role Physical r = 0.45; Bodily Pain r = 0.43; General Health r = 0.52; Vitality r = 0.21; Social Functioning r = 0.45; Role Emotional r = 0.38 and Mental Health r = 0.17) , except for the social domain ( p = 0.38). In the Rasch analysis, general fit measures of the model had adequate statistical performance and were considered a good fit at the first assessment (residual fit Item-person Interaction: M = 0.01, SD = 1.51; person residual fit: M = -0.38, SD = 1.19 and Item-trait: Total Item X² = 69.60 p = 0.00. Personal Separation Index = 0.82), that is, the residuals were acceptable, it was not necessary to exclude items. The EUROHIS-QOL 8-ITEM showed a good fit to the data in the confirmatory factor analysis (X² = 18.46, DF = 15; CFI = 0.99; RMSEA = 0.03; GFI = 0.99; RMR = 0.03; P = 24). Conclusion: EUROHIS-QOL 8-ITEM, validated in European samples, showed adequate psychometric properties in this study showing to be a reliable quality of life measure to be used in Brazilian samples.

Weve presented the results of our research for the conception, execution and evaluation of an informatized adaptive tool, known as DIA (in portuguese), that allows evaluate and give a feedback to the student under the perspective of formative evaluation. At the first stage, we used the PCN: Sciency of the Nature, Mathematics and its Technologies (BRASIL, 1998) and the Curriculum Matrices of Reference from the Instituto Nacional de Estudos e Pesquisas Educacionais -INEP, to the Sistem of Evaluation for Basic Education - SAEB (BRASIL, 2005) to build a scale in wich the objectives are in increasing order, according to the vertical development of the knowledge construction in Mathematics. We linked the proposed objectives to create a Data Bank (BI, in portuguese) that was used in our simulations. Weve analized the results of our essay to evaluate the comunication between the data bank and the scale under the perspective of giving a diagnosis of the construction of the mathematics knowledge. In our essay, we simulated the functionning of the DIA tool through an adaptive informatized test based on the "Teoria de Resposta ao Item" (TRI). We were also interested on determing a profile of a Data Bank (BI) that is able to significantly dialogue with our scale through the TRI. The scale and the associated data bank should provide a constructive feedback that will help the stundents develop their metacognitives competencies. / Apresentamos os resultados de nossa pesquisa para concepção, execuçãoo e avaliação de uma ferramenta adaptativa informatizada, denominada DIA, que permita tanto avaliar como fornecer feedback a estudantes sob uma perspectiva de avaliação formativa. Na primeira etapa, usamos os PCN: Ciências da Natureza, Matemática e suas Tecnologias (BRASIL, 1998) e as Matrizes Curriculares de Referência do Instituto Nacional de Estudos e Pesquisas Educacionais - INEP, para o Sistema de Avaliação para a Educação Básica- SAEB (BRASIL, 2005), para construir uma escala, em que os objetivos estão em ordem crescente, de acordo com o desenvolvimento vertical da construção do conhecimento em Matemática. Entrelaçamos os objetivos propostos para criar um Banco de Itens (BI), que foi usado em nossas simulações. Analisamos os resultados obtidos em nosso ensaio para avaliar o diálogo entre o BI e a escala sob a perspectiva de oferecer um diagnóstico de lacunas na construção do conhecimento matemático. Em nosso ensaio, simulamos o funcionamento da ferramenta DIA através de um teste adaptativo informatizado baseado na Teoria de Resposta ao Item (TRI). Também estamos interessados em determinar um perfil de um Banco de Itens, que seja capaz de forma significativa de dialogar com nossa escala através de TRI. A escala e o banco de itens a ela associado devem viabilizar um feedback construtivo que ajude os alunos a desenvolverem competências metacognitivas.

We apply multidimensional item response theory models (MIRT) to analyse multi-category purchase decisions. We further compare their performance to benchmark models by means of topic models. Estimation is based on two types of data sets. One contains only binary the other polytomous purchase decisions. We show that MIRT are superior w. r. t. our chosen benchmark models. In particular, MIRT are able to reveal intuitive latent traits that can be interpreted as characteristics of households relevant for multi-category purchase decisions. With the help of latent traits marketers are able to predict future purchase behaviour for various types of households. These information may guide shop managers for cross selling activities and product recommendations.

Introdução: A Teoria de Resposta ao Item constitui-se em um novo grupo de modelos psicométricos de construção, validação e avaliação de instrumentos de aferição em desfechos em saúde. Dentre tais modelos, o Modelo de Rasch se destaca como uma possibilidade de testar a Teoria de Mensuração Conjunta e, portanto, desenvolver escalas de medida com estrutura intervalar. De fato, as robustas estratégias estatísticas utilizadas recentemente demandam que as variáveis apresentem propriedades intervalares para que resultados fidedignos sejam obtidos. Na área da saúde mental, o Modelo de Rasch agrega a possibilidade de que os construtos sejam avaliados quanto à dimensionalidade. Os instrumentos podem ser explorados quanto à invariância dos itens, calibragem, adequação das escalas de resposta e adequação dos itens ao modelo teórico subjacente.Objetivos: Explorar a aplicação do Modelo de Rasch no desenvolvimento de instrumentos de qualidade de vida e atitudes frente ao envelhecimento. Utilizar o Modelo de Rasch na validação cultural de um instrumento de depressão geriátrica, assim como testar a adequação de uma escala de resposta Likert de acordo com o nível educacional, através da aplicação do Modelo de Rasch. Método: Dados internacionais de qualidade de vida, atitudes frente ao envelhecimento e depressão foram utilizados nestes estudos. Os dados são provenientes do Projeto WHOQOL-OLD e AAQ, coordenado pela Organização Mundial de Saúde em 20 países. Uma combinação de Teoria Clássica emPsicometria e Modelo de Rasch foi utilizada para a análise dos dados. O Modelo de Rasch foi implementado através do software RUMM2020. Resultados: A utilização do Modelo de Rasch possibilitou um refinamento dos instrumentos testados, gerando instrumentos com novos formatos mais adequados. No instrumento WHOQOL-OLD, em sua versão em Português, dois domínios dos seis apresentaram interação item-total insuficiente. O remodelamento da escala de resposta e a exclusão de itens de performance inadequada acarretaram melhora da escala. O instrumento Atitudes Frente ao Envelhecimento também necessitou de exclusão de itens e agrupamento de categorias de resposta, em sua versão em Português, para que seu desempenho psicométrico fosse adequado. Em relação ao nível de escolaridade, a análise dos dados gerados pelo instrumento WHOQOL-BREF em uma amostra internacional de idosos por Modelo de Rasch evidenciou que uma escala Likert de cinco pontos não é adequada para sujeitos analfabetos, em oposição aos achados com sujeitos universitários. A escala de depressão geriátrica GDS também foi analisada em uma amostra brasileira. O formato original de 15 itens se mostrou inadequado, e a exclusão de itens é fundamental para que o desempenho deste instrumento seja satisfatório. Por fim, o impacto de sintomas depressivos clínicos e subclínicos na qualidade de vida de idosos foi avaliado. Mesmo níveis subclínicos de depressão mostraram-se significativamente associados a decréscimo de qualidade de vida e atitudes frente ao envelhecimento em uma amostra de 5566 idosos. Conclusão: A aplicação do Modelo de Rasch no desenvolvimento e validação de instrumentos na área da saúde mental mostrou-se marcadamente relevante. Tal modelo proporcionou que as escalas possam ser examinadas em detalhes. A avaliação dos itens de modo individual permite que a sua adequação seja determinada e que o instrumento seja refinado de acordo com as modificações sugeridas pelas análises de Rasch. Por fim, o Modelo de Rasch permite o teste de invariância dos itens, que assume particular importância na utilização transcultural de instrumentos na área da saúde mental. / Background: Item Response Theory represents a novel group of psychometric models for constructing, validating and evaluating health outcome instruments. Among these models, the Rasch Model is able to test the Theory of Conjoint Measurement and, so, develop intervalar scales. In fact, the recently applied robust statistical strategies demand that the variables have an intervalar structure, so that reliable results are obtained. In the mental health field, the Rasch Model assures that the constructs may be tested for dimensionality. The instruments may be explored regarding item invariance, targetting, response scales adequacy and item fit to the underlying theoretical model. Objectives: To explore the role of the Rasch Model for the development of quality of life and attitudes to aging instruments. In addition, to apply the Rasch Model in the cultural validation of a geriatric depression scale, as well as test the suitability of a 5-point Likert response scale according to the educational level. Method: International data on quality of life, attitudes to aging and depression were analyzed in these studies. Data were drawn from the WHOQOL-OLD and AAQ Project, coordinated by the World Health Organization in 20 countries. A combination of Classical Test Theory and Rasch Model was used to data analysis. The Rasch Model was implemented by RUMM2020 software. Results: The application of the Rasch Model determined a refinement of the original instruments, deriving more adequate versions. The Portuguese version of the WHOQOL-OLD instrument presented insufficient item-total interaction in two domains out of six. Rescoring the response scale and deleting items led to 14 improvement of the instrument. The Attitudes to Aging Questionnaire (Portuguese version) has also demanded rescoring and item deletion in order to present adequate psychometric performance. Regarding the educational level, the Rasch analysis of data obtained using the WHOQOL-BREF in an international sample of older adults indicated that a 5-point Likert scale is not suitable for illiterate subjects. In opositte, this Likert scale is suitable for graduate older adults. The Geriatric Depression Scale was explored in a Brazilian sample. Its original 15-item format has proven to be inadequate, and item exclusion is crucial to obtain a satisfactory performance. Finally, the impact of clinical and subclinical depressive symptoms in quality of life was assessed. Even subthreshold symptomatology is significantly associated to impairments in quality of life and attitudes to aging in a sample of 5566 older adults. Conclusion: The application of the Rasch Model to the development and validation of mental health instruments has proven to be highly relevant. This model brings the possibilty of examining scales in depth. The individual assessment of each item makes it possible to determine item fit and, thus, to refine the instruments according to the alterations claimed by the Rasch analysis. Finally, the Rasch Model implements the item invariance test, which is particularly important for utilizing instruments in transcultural investigations