L’arbre de régression multivariable et les modèles linéaires généralisés revisités : applications à l’étude de la diversité bêta et à l’estimation de la biomasse d’arbres tropicaux

En écologie, dans le cadre par exemple d’études des services fournis par les écosystèmes, les modélisations descriptive, explicative et prédictive ont toutes trois leur place distincte. Certaines situations bien précises requièrent soit l’un soit l’autre de ces types de modélisation ; le bon choix s’impose afin de pouvoir faire du modèle un usage conforme aux objectifs de l’étude. Dans le cadre de ce travail, nous explorons dans un premier temps le pouvoir explicatif de l’arbre de régression multivariable (ARM). Cette méthode de modélisation est basée sur un algorithme récursif de bipartition et une méthode de rééchantillonage permettant l’élagage du modèle final, qui est un arbre, afin d’obtenir le modèle produisant les meilleures prédictions. Cette analyse asymétrique à deux tableaux permet l’obtention de groupes homogènes d’objets du tableau réponse, les divisions entre les groupes correspondant à des points de coupure des variables du tableau explicatif marquant les changements les plus abrupts de la réponse. Nous démontrons qu’afin de calculer le pouvoir explicatif de l’ARM, on doit définir un coefficient de détermination ajusté dans lequel les degrés de liberté du modèle sont estimés à l’aide d’un algorithme. Cette estimation du coefficient de détermination de la population est pratiquement non biaisée. Puisque l’ARM sous-tend des prémisses de discontinuité alors que l’analyse canonique de redondance (ACR) modélise des gradients linéaires continus, la comparaison de leur pouvoir explicatif respectif permet entre autres de distinguer quel type de patron la réponse suit en fonction des variables explicatives. La comparaison du pouvoir explicatif entre l’ACR et l’ARM a été motivée par l’utilisation extensive de l’ACR afin d’étudier la diversité bêta. Toujours dans une optique explicative, nous définissons une nouvelle procédure appelée l’arbre de régression multivariable en cascade (ARMC) qui permet de construire un modèle tout en imposant un ordre hiérarchique aux hypothèses à l’étude. Cette nouvelle procédure permet d’entreprendre l’étude de l’effet hiérarchisé de deux jeux de variables explicatives, principal et subordonné, puis de calculer leur pouvoir explicatif. L’interprétation du modèle final se fait comme dans une MANOVA hiérarchique. On peut trouver dans les résultats de cette analyse des informations supplémentaires quant aux liens qui existent entre la réponse et les variables explicatives, par exemple des interactions entres les deux jeux explicatifs qui n’étaient pas mises en évidence par l’analyse ARM usuelle. D’autre part, on étudie le pouvoir prédictif des modèles linéaires généralisés en modélisant la biomasse de différentes espèces d’arbre tropicaux en fonction de certaines de leurs mesures allométriques. Plus particulièrement, nous examinons la capacité des structures d’erreur gaussienne et gamma à fournir les prédictions les plus précises. Nous montrons que pour une espèce en particulier, le pouvoir prédictif d’un modèle faisant usage de la structure d’erreur gamma est supérieur. Cette étude s’insère dans un cadre pratique et se veut un exemple pour les gestionnaires voulant estimer précisément la capture du carbone par des plantations d’arbres tropicaux. Nos conclusions pourraient faire partie intégrante d’un programme de réduction des émissions de carbone par les changements d’utilisation des terres.

Motivación de logro y sus relaciones con características de personalidad en adolescentes.

Presentar las principales corrientes teóricas surgidas en torno a la motivación de logro así como de las diversas interpretaciones que se han dado a los resultados obtenidos en las investigaciones realizadas en el área, durante los últimos 35 años, y analizar las características de personalidad de los grupos de sujetos con diferente motivación de logro. Estudiantes voluntarios de tercer curso de BUP del Instituto Padre Manjón de Granada, con una edad media de 17 años. Aplicación de diferentes cuestionarios y pruebas a los alumnos, para hallar el grado de motivación de logro resultante; basándose en el rendimiento de los sujetos y las calificaciones medias finales de curso. Medida 'N ACH' de la motivación de logro, escala de Ray-Lynn de la motivación de logro, PTM de Hermans, cuestionario de motivación de logro de Mehrbian, cuestionarios de ansiedad (DAS, TAQ, MAS) para la medida del motivo de miedo al fracaso, prueba de rendimiento, test de inteligencia general, test de aptitudes diferenciales (DAT), cuestionario de personalidad 16 PF. BMDP 2d Frecuency Count Routine, se analiza mediante un Chi cuadrado la frecuencia de historias relacionadas con el logro y no relacionadas, correlación de Pearson, aplicación de la fórmula de Kuder-Richardson, BMDP 6r Partial Correlation and Multivariate Regression, cálculo del coeficiente de semejanza de perfiles. Los resultados de la investigación apoyan la posición de Atkinson y Birch. Ante la imposibilidad de utilizar los cuestionarios como medida alternativa al sistema proyectivo, es la puntuación combinada 'N ACH-DAS' la única que ofrece las suficientes garantías de estar realmente midiendo la motivación de logro resultante de los sujetos. Son las imagenes con un mayor nivel de sugerncia las que provocan una mayor activación de la necesidad de logro, la puntuación 'N ACH TAT' permite pronosticar el rendimiento de los sujetos, los sujetos con un mismo nivel de motivación de logro resultante difieren significativamente entre si en personalidad, en función del sexo, el cuestionario PMT de Hermans y la subescala OT de Ray son los que presentaron una mayor validez predictiva referente al rendimiento de mujeres y hombres.

Cardiovascular disease in latin american patients with systemic lupus erythematosus: a cross-sectional study and a systematic review

Objective. This study was performed to determine the prevalence of and associated risk factors for cardiovascular disease (CVD) in Latin American (LA) patients with systemic lupus erythematosus (SLE). Methods. First, a cross-sectional analytical study was conducted in 310 Colombian patients with SLE in whom CVD was assessed. Associated factors were examined by multivariate regression analyses. Second, a systematic review of the literature on CVD in SLE in LA was performed. Results. There were 133 (36.5%) Colombian SLE patients with CVD. Dyslipidemia, smoking, coffee consumption, and pleural effusion were positively associated with CVD. An independent effect of coffee consumption and cigarette on CVD was found regardless of gender and duration of disease. In the systematic review, 60 articles fulfilling the eligibility criteria were included. A wide range of CVD prevalence was found (4%–79.5%). Several studies reported ancestry, genetic factors, and polyautoimmunity as novel risk factors for such a condition.Conclusions. A high rate of CVD is observed in LA patients with SLE. Awareness of the observed risk factors should encourage preventive population strategies for CVD in patients with SLE aimed at facilitating the suppression of cigarette smoking and coffee consumption as well as at the tight control of dyslipidemia and other modifiable risk factors.

Measuring and testing for the systemically important financial institutions

This paper analyzes the measure of systemic importance ∆CoV aR proposed by Adrian and Brunnermeier (2009, 2010) within the context of a similar class of risk measures used in the risk management literature. In addition, we develop a series of testing procedures, based on ∆CoV aR, to identify and rank the systemically important institutions. We stress the importance of statistical testing in interpreting the measure of systemic importance. An empirical application illustrates the testing procedures, using equity data for three European banks.

Near infrared reflectance spectroscopy (NIRS) to predict biological parameters of maize silage: effects of particle comminution, oven drying temperature and the presence of residual moisture

Maize silage nutritive quality is routinely determined by near infrared reflectance spectroscopy (NIRS). However, little is known about the impact of sample preparation on the accuracy of the calibration to predict biological traits. A sample population of 48 maize silages representing a wide range of physiological maturities was used in a study to determine the impact of different sample preparation procedures (i.e., drying regimes; the presence or absence of residual moisture; the degree of particle comminution) on resultant NIR prediction statistics. All silages were scanned using a total of 12 combinations of sample pre-treatments. Each sample preparation combination was subjected to three multivariate regression techniques to give a total of 36 predictions per biological trait. Increased sample preparations procedure, relative to scanning the unprocessed whole plant (WP) material, always resulted in a numerical minimisation of model statistics. However, the ability of each of the treatments to significantly minimise the model statistics differed. Particle comminution was the most important factor, oven-drying regime was intermediate, and residual moisture presence was the least important. Models to predict various biological parameters of maize silage will be improved if material is subjected to a high degree of particle comminution (i.e., having been passed through a 1 mm screen) and developed on plant material previously dried at 60 degrees C. The extra effort in terms of time and cost required to remove sample residual moisture cannot be justified. (c) 2005 Elsevier B.V. All rights reserved.

Obesity and health in Europeans aged 50 years and older

Background: Obesity is increasing globally across all population groups. Limited data are available on how obesity patterns differ across countries. Objective: To document the prevalence of obesity and related health conditions for Europeans aged 50 years and older, and to estimate the association between obesity and health outcomes across 10 European countries. Methods: Data were obtained from the 2004 Survey of Health, Ageing and Retirement in Europe, a cross-national survey of 22 777 Continental Europeans over the age of 50 years. The health outcomes included self-reported health, disability, doctor-diagnosed chronic health conditions and depression. Multivariate regression analysis was used to predict health outcomes across weight classes (defined by body mass index [BMI] from self-reported weight and height) in the pooled sample and individually in each country. Results: The prevalence of obesity (BMI >= 30) ranged from 12.8% in Sweden to 20.2% in Spain for men and from 12.3% in Switzerland to 25.6% in Spain for women. Adjusting for compositional differences across countries changed little in the observed large heterogeneity in obesity rates throughout Europe. Compared with normal weight individuals, men and women with greater BMI had significantly higher risks for all chronic health conditions examined except heart disease in overweight men. Depression was linked to obesity in women only. Particularly pronounced risks of impaired health and chronic health conditions were found among severely obese people. The effects of obesity on health did not vary significantly across countries. Conclusions: Cross-country differences in the prevalence of obesity in older Europeans are substantial and exceed socio-demographic differentials in excessive body weight. Obesity is associated with significantly poorer health outcomes among Europeans aged 50 years and over, with effects similar across countries. Large heterogeneity in obesity throughout Europe should be investigated further to identify areas for effective public policy. (C) 2007 Published by Elsevier Ltd on behalf of The Royal Institute of Public Health.

Impact of age and menopausal status on the postprandial triacylglycerol response in healthy women

Objective: To examine the impact of age and the natural menopause on the postprandial triacylglycerol (TAG) response in healthy women. Methods and results: Thirty-seven premenopausal and sixty-one postmenopausal women underwent a sequential meal postprandial investigation, in which blood samples were taken at regular intervals after a test breakfast and lunch given at 0 and 330 min respectively. Lipids and glucose were measured in the fasting sample, with TAG analysed in the postprandial samples. Postmenopausal women were shown to have higher fasting total cholesterol, low density lipoprotein cholesterol (LDL-C) and glucose (P < 0.02). Marked differences in the postprandial TAG response were evident between the groups, with a greater incremental area under the curve (IAUC) and maximum TAG concentration in the postmenopausal women (P < 0.04). Multivariate regression analysis revealed both age and fasting TAG to be independently associated with the summary measures of the postprandial TAG response in the premenopausal women only. Interestingly, sub-division of the women into both younger and older pre- and postmenopausal subgroups, showed the most marked difference in TAG-IAUC to be between the younger and the older premenopausal women, whereas differences in fasting LDL-C were most evident between the older premenopausal and the younger postmenopausal women. Conclusions: Our results suggest a divergence in the relationship of age and menopausal status with fasting LDL-C and postprandial TAG which may reflect differences in the metabolic effects of age and the menopause on these lipid risk markers or a greater impact of early oestrogen decline on pathways of TAG rather than LDL metabolism.

Greater impairment of postprandial triacylglycerol than glucose response in metabolic syndrome subjects with fasting hyperglycaemia

Abstract Objective: Studies have started to question whether a specific component or combinations of metabolic syndrome (MetS) components may be more important in relation to cardiovascular disease risk. Our aim was to examine the impact of the presence of raised fasting glucose as a MetS component on postprandial lipaemia. Methods: Men classified with the MetS underwent a sequential test meal investigation, in which blood samples were taken at regular intervals after a test breakfast (t=0 min) and lunch (t=330 min). Lipids, glucose and insulin were measured in the fasting and postprandial samples. Results: MetS subjects with 3 or 4 components were subdivided into those without (n=34) and with (n=23) fasting hyperglycaemia (≥ 5.6 mmol/l), irrespective of the combination of components. Fasting lipids and insulin were similar in the two groups, with glucose significantly higher in the men with glucose as a MetS component (P<0.001). Following the test meals, there was a higher maximum concentration (maxC), area under the curve (AUC) and incremental AUC (P≤0.016) for the postprandial triacylglycerol (TAG) response in men with fasting hyperglycaemia. Greater glucose AUC (P<0.001) and insulin maxC (P=0.010) was also observed in these individuals after the test meals. Multivariate regression analysis revealed fasting glucose to be an important predictor of the postprandial TAG and glucose response. Conclusion: Our data analysis has revealed a greater impairment of postprandial TAG than glucose response in MetS subjects with raised fasting glucose. The worsening of postprandial lipaemic control may contribute to the greater CVD risk reported in individuals with MetS component combinations which include hyperglycaemia.

The long-run performance of IPOs: the case of the Stock Exchange of Mauritius

This study examines the long-run performance of initial public offerings on the Stock Exchange of Mauritius (SEM). The results show that the 3-year equally weighted cumulative adjusted returns average −16.5%. The magnitude of this underperformance is consistent with most reported studies in different developed and emerging markets. Based on multivariate regression models, firms with small issues and higher ex ante financial strength seem on average to experience greater long-run underperformance, supporting the divergence of opinion and overreaction hypotheses. On the other hand, Mauritian firms do not on average time their offerings to lower cost of capital and as such, there seems to be limited support for the windows of opportunity hypothesis.

What determines the use of capital budgeting methods? : Evidence from Swedish listed companies

Purpose: This paper aims to extend and contribute to prior research on the association between company characteristics and choice of capital budgeting methods (CBMs). Design/methodology/approach: A multivariate regression analysis on questionnaire data from 2005 and 2008 is used to study which factors determine the choice of CBMs in Swedish listed companies. Findings: Our results supported hypotheses that Swedish listed companies have become more sophisticated over the years (or at least less unsophisticated) which indicates a closing of the theory-practice gap; that companies with greater leverage used payback more often; and that companies with stricter debt targets and less management ownership employed accounting rate of return more frequent. Moreover, larger companies used CBMs more often. Originality/value: The paper contributes to prior research within this field by being the first Swedish study to examine the association between use of CBMs and as many as twelve independent variables, including changes over time, by using multivariate regression analysis. The results are compared to a US and a continental European study.

Análise dos indicadores de qualidade versus taxa de abandono utilizando método de regressão múltipla para serviço de banda larga

Telecommunication is one of the most dynamic and strategic areas in the world. Many technological innovations has modified the way information is exchanged. Information and knowledge are now shared in networks. Broadband Internet is the new way of sharing contents and information. This dissertation deals with performance indicators related to maintenance services of telecommunications networks and uses models of multivariate regression to estimate churn, which is the loss of customers to other companies. In a competitive environment, telecommunications companies have devised strategies to minimize the loss of customers. Loosing customers presents a higher cost than obtaining new ones. Corporations have plenty of data stored in a diversity of databases. Usually the data are not explored properly. This work uses the Knowledge Discovery in Databases (KDD) to establish rules and new models to explain how churn, as a dependent variable, are related to a diversity of service indicators, such as time to deploy the service (in hours), time to repair (in hours), and so on. Extraction of meaningful knowledge is, in many cases, a challenge. Models were tested and statistically analyzed. The work also shows results that allows the analysis and identification of which quality services indicators influence the churn. Actions are also proposed to solve, at least in part, this problem

Análise de desempenho de vendas em telecomunicações utilizando técnicas de mineração de dados

Nowadays, telecommunications is one of the most dynamic and strategic areas in the world. Organizations are always seeking to find new management practices within an ever increasing competitive environment where resources are getting scarce. In this scenario, data obtained from business and corporate processes have even greater importance, although this data is not yet adequately explored. Knowledge Discovery in Databases (KDD) appears then, as an option to allow the study of complex problems in different areas of management. This work proposes both a systematization of KDD activities using concepts from different methodologies, such as CRISP-DM, SEMMA and FAYYAD approaches and a study concerning the viability of multivariate regression analysis models to explain corporative telecommunications sales using performance indicators. Thus, statistical methods were outlined to analyze the effects of such indicators on the behavior of business productivity. According to business and standard statistical analysis, equations were defined and fit to their respective determination coefficients. Tests of hypotheses were also conducted on parameters with the purpose of validating the regression models. The results show that there is a relationship between these development indicators and the amount of sales

Espectroscopia no infravermelho próximo e métodos de calibração multivariada aplicados à determinação simultânea de parâmetros bioquímicos em plasma sanguíneo

In this work, the quantitative analysis of glucose, triglycerides and cholesterol (total and HDL) in both rat and human blood plasma was performed without any kind of pretreatment of samples, by using near infrared spectroscopy (NIR) combined with multivariate methods. For this purpose, different techniques and algorithms used to pre-process data, to select variables and to build multivariate regression models were compared between each other, such as partial least squares regression (PLS), non linear regression by artificial neural networks, interval partial least squares regression (iPLS), genetic algorithm (GA), successive projections algorithm (SPA), amongst others. Related to the determinations of rat blood plasma samples, the variables selection algorithms showed satisfactory results both for the correlation coefficients (R²) and for the values of root mean square error of prediction (RMSEP) for the three analytes, especially for triglycerides and cholesterol-HDL. The RMSEP values for glucose, triglycerides and cholesterol-HDL obtained through the best PLS model were 6.08, 16.07 e 2.03 mg dL-1, respectively. In the other case, for the determinations in human blood plasma, the predictions obtained by the PLS models provided unsatisfactory results with non linear tendency and presence of bias. Then, the ANN regression was applied as an alternative to PLS, considering its ability of modeling data from non linear systems. The root mean square error of monitoring (RMSEM) for glucose, triglycerides and total cholesterol, for the best ANN models, were 13.20, 10.31 e 12.35 mg dL-1, respectively. Statistical tests (F and t) suggest that NIR spectroscopy combined with multivariate regression methods (PLS and ANN) are capable to quantify the analytes (glucose, triglycerides and cholesterol) even when they are present in highly complex biological fluids, such as blood plasma

Ontogenetic variation in skull shape of Thrichomys apereoides (Rodentia : Echimyidae)

The pattern of change in shape during postnatal development in skulls of punare (Thrichomys apereoides) skulls, was studied by geometric morphometric techniques. Skull shape observed in T. apereoides varied both with size and age, but variation in size explains most of the overall change in shape. Differences in shape observed among the eight age categories showed that main changes in shape occurred principally between the first and second age categories. Among the other age classes, changes became less pronounced leading to elongation of the snout and the mid-face and narrowing of the basicranium. The change in global shape resulted in lateral compression of the skull. Despite the high level of integration observed, localized transformations dominated the ontogenetic changes in shape indicating the presence of two large scale cranium components-the orofacial and the basicranial region. The ontogenetic pattern in this species seems to follow the same trends observed in the initial phases of development.