A comparison of the alr and ilr transformations for kernel density estimation of compositional data

In a seminal paper, Aitchison and Lauder (1985) introduced classical kernel density estimation techniques in the context of compositional data analysis. Indeed, they gave two options for the choice of the kernel to be used in the kernel estimator. One of these kernels is based on the use the alr transformation on the simplex SD jointly with the normal distribution on RD-1. However, these authors themselves recognized that this method has some deficiencies. A method for overcoming these dificulties based on recent developments for compositional data analysis and multivariate kernel estimation theory, combining the ilr transformation with the use of the normal density with a full bandwidth matrix, was recently proposed in Martín-Fernández, Chacón and Mateu- Figueras (2006). Here we present an extensive simulation study that compares both methods in practice, thus exploring the finite-sample behaviour of both estimators

Compositions in life science data

The aim of this talk is to convince the reader that there are a lot of interesting statistical problems in presentday life science data analysis which seem ultimately connected with compositional statistics. Key words: SAGE, cDNA microarrays, (1D-)NMR, virus quasispecies

Elemental analysis of New Zealand Nephrite Jade (pounamu) for forensic purposes

Pounamu (NZ jade), or nephrite, is a protected mineral in its natural form following the transfer of ownership back to Ngai Tahu under the Ngai Tahu (Pounamu Vesting) Act 1997. Any theft of nephrite is prosecutable under the Crimes Act 1961. Scientific evidence is essential in cases where origin is disputed. A robust method for discrimination of this material through the use of elemental analysis and compositional data analysis is required. Initial studies have characterised the variability within a given nephrite source. This has included investigation of both in situ outcrops and alluvial material. Methods for the discrimination of two geographically close nephrite sources are being developed. Key Words: forensic, jade, nephrite, laser ablation, inductively coupled plasma mass spectrometry, multivariate analysis, elemental analysis, compositional data analysis

Coherent forecasting of multiple-decrement life tables: a test using Japanese cause of death data

Planners in public and private institutions would like coherent forecasts of the components of age-specic mortality, such as causes of death. This has been di cult to achieve because the relative values of the forecast components often fail to behave in a way that is coherent with historical experience. In addition, when the group forecasts are combined the result is often incompatible with an all-groups forecast. It has been shown that cause-specic mortality forecasts are pessimistic when compared with all-cause forecasts (Wilmoth, 1995). This paper abandons the conventional approach of using log mortality rates and forecasts the density of deaths in the life table. Since these values obey a unit sum constraint for both conventional single-decrement life tables (only one absorbing state) and multiple-decrement tables (more than one absorbing state), they are intrinsically relative rather than absolute values across decrements as well as ages. Using the methods of Compositional Data Analysis pioneered by Aitchison (1986), death densities are transformed into the real space so that the full range of multivariate statistics can be applied, then back-transformed to positive values so that the unit sum constraint is honoured. The structure of the best-known, single-decrement mortality-rate forecasting model, devised by Lee and Carter (1992), is expressed in compositional form and the results from the two models are compared. The compositional model is extended to a multiple-decrement form and used to forecast mortality by cause of death for Japan

CODAMAT: a modern analogue techinque for compositional data

The quantitative estimation of Sea Surface Temperatures from fossils assemblages is a fundamental issue in palaeoclimatic and paleooceanographic investigations. The Modern Analogue Technique, a widely adopted method based on direct comparison of fossil assemblages with modern coretop samples, was revised with the aim of conforming it to compositional data analysis. The new CODAMAT method was developed by adopting the Aitchison metric as distance measure. Modern coretop datasets are characterised by a large amount of zeros. The zero replacement was carried out by adopting a Bayesian approach to the zero replacement, based on a posterior estimation of the parameter of the multinomial distribution. The number of modern analogues from which reconstructing the SST was determined by means of a multiple approach by considering the Proxies correlation matrix, Standardized Residual Sum of Squares and Mean Squared Distance. This new CODAMAT method was applied to the planktonic foraminiferal assemblages of a core recovered in the Tyrrhenian Sea. Kew words: Modern analogues, Aitchison distance, Proxies correlation matrix, Standardized Residual Sum of Squares

Comparing methods for dimensionality reduction when data are density functions

Functional Data Analysis (FDA) deals with samples where a whole function is observed for each individual. A particular case of FDA is when the observed functions are density functions, that are also an example of infinite dimensional compositional data. In this work we compare several methods for dimensionality reduction for this particular type of data: functional principal components analysis (PCA) with or without a previous data transformation and multidimensional scaling (MDS) for diferent inter-densities distances, one of them taking into account the compositional nature of density functions. The difeerent methods are applied to both artificial and real data (households income distributions)

Revisiting the compositional data. Some fundamental questions and new prospects in Archaeometry and Archaeology

In this paper we examine the problem of compositional data from a different starting point. Chemical compositional data, as used in provenance studies on archaeological materials, will be approached from the measurement theory. The results will show, in a very intuitive way that chemical data can only be treated by using the approach developed for compositional data. It will be shown that compositional data analysis is a particular case in projective geometry, when the projective coordinates are in the positive orthant, and they have the properties of logarithmic interval metrics. Moreover, it will be shown that this approach can be extended to a very large number of applications, including shape analysis. This will be exemplified with a case study in architecture of Early Christian churches dated back to the 5th-7th centuries AD

Eficacia diagnóstica y terapéutica de las radiografías de tórax rutinarias matutinas en cuidado intensivo pediátrico

Introducción: la utilidad de las radiografías de tórax rutinarias se encuentra en discusión, con estudios que avalan su uso y, en el otro extremo, estudios que solo encuentran utilidad marginal. Objetivos: determinar la eficacia diagnóstica y terapéutica de las radiografías de tórax rutinarias matutinas en pacientes pediátricos bajo ventilación mecánica y la identificación de subgrupos en quienes dichas radiografías sean de mayor utilidad. Metodología: estudio prospectivo, analítico, transversal, realizado en pacientes de un mes a 18 años, sometidos a ventilación mecánica por más de 48 horas, entre diciembre de 2010 a noviembre de 2011. Se emplearon las pruebas de X2 de Pearson y el test de Fischer. Para el análisis de los datos, se utilizaron los programas Statgraphics y SPSS, versión 15. Resultados: se evaluaron 53 pacientes con 536 radiografías. Los hallazgos fueron principalmente menores. Los hallazgos mayores solo corresponden al 10.3% de los casos, siendo principalmente mal posición del tubo endotraqueal y nuevos infiltrados infecciosos. No fue posible establecer subgrupos pero los datos sugieren mayor utilidad de dichas radiografías en pacientes de menor edad y peso, así como en los sometidos a alto soporte ventilatorio. Conclusiones: la utilidad de las radiografías rutinarias en pacientes pediátricos es marginal, siendo necesaria la realización de nuevos estudios para establecer su eficacia diagnóstica y su utilidad en subgrupos de pacientes. Palabras clave: radiografía de tórax, rayos x de tórax, radiología, unidad de cuidado intensivo, unidad de cuidado crítico.

COMP6049 Quantitative analysis

notes for class discussion and exercise

Analysing Qualitative Data

Slides and Handouts for class introducing some of the concepts associated with the analysis of qualitative data

Capacidades dinámicas que influyen en la operación de la Red de Turismo de La Candelaria

El desarrollo de la presente investigación, centra su atención en las capacidades dinámicas que influyen en la operación de la Red de Turismo de La Candelaria de Bogotá. Para este fin, se realizó una encuesta a 100 directivos o dueños de las empresas que conforman dicha red, y que es una muestra significativa para los propósitos de la investigación, puesto que permite describir a nivel de la empresa y a nivel de la red, la influencia de las capacidades dinámicas de absorción, adaptación e innovación. Como resultados, se obtuvieron que al nivel de empresas las tres capacidades dinámicas influyen en la operación de la misma, encontrándose una mayor relación entre las capacidades de “Innovación – Adaptación"; a nivel de red empresarial ocurre lo contrario, puesto que la relación de las capacidades dinámicas de “Innovación – Adaptación” es nula, mientras que las relaciones entre “Absorción – Innovación” y “Absorción – Adaptación” poseen una alta relación para la operación de la red. Lo anterior, se deriva del análisis realizado de los datos tabulados de la encuesta aplicada a las empresas de la red de turismo, con los estudios empíricos hallados que proponen escalas de medición para las capacidades dinámicas de absorción, adaptación e innovación, y el marco teórico elaborado como soporte para la presente investigación.

Rol del residente de Medicina Interna de la Universidad del Rosario como docente

Antecedentes: Cada vez es mayor la relevancia que se da al papel del residente como docente, no solo por su importancia en la formación de estudiantes, internos y otros miembros del equipo de salud, sino por su deber en la instrucción del paciente y su familia. A pesar de ello, el rol del residente como docente no se encuentra plenamente definido en nuestro medio. Objetivo: Caracterizar el rol de los residentes de Medicina Interna de la Universidad el Rosario en la Fundación Cardioinfantil como docentes. Métodos: Estudio cualitativo a partir de observaciones en escenarios de enseñanza y entrevistas semiestructuradas a 44 participantes distribuidos en grupos focales Resultados: Los residentes asumen un rol docente en diversos escenarios educativos con estudiantes, internos, residentes y docentes. Reconocen que no tienen la preparación necesaria para asumir esta responsabilidad ni funciones establecidas para tal fin. A pesar de esto, utilizan diferentes estrategias para enseñar y se sienten motivados para hacerlo. Conclusiones: El rol del residente como docente en el servicio de Medicina Interna en la Fundación Cardioinfantil es fundamental para la formación de los futuros médicos y especialistas según la percepción que tienen los grupos focales. Los encuentros pedagógicos están enmarcados por la disponibilidad de tiempo y dependen de características personales del residente, conocimiento disciplinar y formación para enseñar. Se considera que se debe apoyar más el entrenamiento en docencia de los residentes, avanzar en la formalización de las funciones docentes de los mismos y generar sistemas de evaluación de este proceso de enseñanza y aprendizaje.

Natural resource windfalls and efficiency of local government expenditures: evidence from Peru

We study the role of natural resource windfalls in explaining the efficiency of public expenditures. Using a rich dataset of expenditures and public good provision for 1,836 municipalities in Peru for period 2001-2010, we estimate a non-monotonic relationship between the efficiency of public good provision and the level of natural resource transfers. Local governments that were extremely favored by the boom of mineral prices were more efficient in using fiscal windfalls whereas those benefited with modest transfers were more inefficient. These results can be explained by the increase in political competition associated with the boom. However, the fact that increases in efficiency were related to reductions in public good provision casts doubts about the beneficial effects of political competition in promoting efficiency.

Eye tracking data representation and visualization : on information and communication studies at CETAC.MEDIA

Eye tracking has become a preponderant technique in the evaluation of user interaction and behaviour with study objects in defined contexts. Common eye tracking related data representation techniques offer valuable input regarding user interaction and eye gaze behaviour, namely through fixations and saccades measurement. However, these and other techniques may be insufficient for the representation of acquired data in specific studies, namely because of the complexity of the study object being analysed. This paper intends to contribute with a summary of data representation and information visualization techniques used in data analysis within different contexts (advertising, websites, television news and video games). Additionally, several methodological approaches are presented in this paper, which resulted from several studies developed and under development at CETAC.MEDIA - Communication Sciences and Technologies Research Centre. In the studies described, traditional data representation techniques were insufficient. As a result, new approaches were necessary and therefore, new forms of representing data, based on common techniques were developed with the objective of improving communication and information strategies. In each of these studies, a brief summary of the contribution to their respective area will be presented, as well as the data representation techniques used and some of the acquired results.

Indicadores da individualização de cuidados para o curso de licenciatura em enfermagem

RESUMO: A individualização dos cuidados de enfermagem tem sido associada a uma evolução clínica mais favorável, representando um importante parâmetro de avaliação e de desenvolvimento dos serviços de saúde. A tónica atribuída a esta problemática não só é evidenciada por diversos autores, como se enquadra nas metas de modernização do Sistema Nacional de Saúde e é destaque em vários códigos normativos da profissão nacionais e internacionais, como uma obrigação moral e deontológica. Assim, pretende-se mediante os ganhos em saúde sensíveis às intervenções de enfermagem, identificar quais indicadores do cuidado individualizado, para se efectivar a sua incorporação na formação inicial em enfermagem. Para tal efeito, construiu-se uma bateria de indicadores mediante análise de duas revisões sistemáticas da literatura, que teve por base o Modelo da Eficácia do Papel de Enfermagem, desenvolvido por Irvine et al. (1998). Para à adaptação à realidade portuguesa recorreu-se à técnica de Delphi, com duas rondas, que incluiu respectivamente, 12 e 10 peritos de enfermagem. Na análise de dados utilizou-se o nível de concordância superior ou igual a 90%, na última ronda. Na segunda fase do estudo, aplicou-se um inquérito por questionário (α de Cronbach = 0,919) para testar a sua aplicabilidade dos indicadores, a 156 enfermeiros, do mesmo hospital da área da grande Lisboa, no Serviço de Medicina e Cirurgia. Recorreu-se ao SPSS, versão 19 e realizou-se análise univariada e estatística analítica. Na bateria final de indicadores foram incorporados aqueles com ponderação positiva (≥51%). Os dados qualitativos obtidos foram submetidos a análise de conteúdo. Dos 58 indicadores iniciais, consolidaram-se 8 categorias: cuidado à pessoa em fim de vida e família, toque terapêutico, educação para a auto-gestão da saúde, cuidados de proximidade, gestão de casos, empoderamento/ literacia para a saúde, linha telefónica de apoio permanente/ tele-assistência e apoio psico-emocional, com valorização de 28 indicadores. O tempo de experiência profissional, tipo de serviço e tempo de permanência no mesmo serviço influenciou a percepção dos enfermeiros, confirmando os pressupostos de Irvine et al. (1998) e Benner (2001). A correlação total dos indicadores, no questionário, variou entre 0,248 e 0,650, para p<0,01. O facto de todas as correlações serem positivas significa que provavelmente estão associados à problemática da individualização, pelo que se sugere a sua transposição para o ensino de enfermagem. ABSTRACT: The individualization of nursing care has been associated with a more favorable clinical evolution, an important parameter for the evaluation and development of health services. The emphasis given to this problem is not only evidenced by several authors, as fits the goals of modernizing the National Health System and is featured in several normative codes of the profession nationally and internationally, as a moral and ethical obligation. Thus, it is intended by the gains in health sensitive to nursing interventions, identify indicators of individualized care and give effect to its incorporation into the initial training in nursing. For this purpose, we constructed a series of indicators by analyzing two systematic reviews of literature, which was based on the The Nursing Role Effectiveness Model developed by Irvine et al. (1998). For the adaptation to the Portuguese appealed to the Delphi technique with two rounds, which included, respectively, 10 and 12 nursing experts. In data analysis we used the level of agreement greater than or equal to 90% in the last round. In the second phase of the study, we applied a questionnaire (Cronbach's α = 0.919) to test the applicability of the indicators, the 156 nurses in the same hospital in the Greater Lisbon area, the Department of Medicine and Surgery. Done using the SPSS, version 19 and conducted a univariate analysis and analytical statistics. In the final heat of indicators were incorporated into those with positive weight (≥ 51%). Qualitative data were subjected to content analysis. Of the initial 58 indicators, eight were consolidated categories: care to the person and family life, therapeutic touch education for self-management of health care outreach, case management, empowerment / literacy to health, a telephone line permanent support / tele-assistance and psycho-emotional, with an appreciation of 28 indicators. The length of professional experience, type of service and length of stay in the same service influenced the perception of nurses, confirming the assumptions of Irvine et al. (1998) and Benner (2001). The total correlation of the indicators in the questionnaire ranged between 0.248 and 0.650, p <0.01. The fact that all correlations are positive means that are probably associated with the problem of individuation, which is suggested by its implementation in nursing education.