RESUMO

Ensuring that the proposed probabilistic model accurately represents the problem is a critical step in statistical modeling, as choosing a poorly fitting model can have significant repercussions on the decision-making process. The primary objective of statistical modeling often revolves around predicting new observations, highlighting the importance of assessing the model's accuracy. However, current methods for evaluating predictive ability typically involve model comparison, which may not guarantee a good model selection. This work presents an accuracy measure designed for evaluating a model's predictive capability. This measure, which is straightforward and easy to understand, includes a decision criterion for model rejection. The development of this proposal adopts a Bayesian perspective of inference, elucidating the underlying concepts and outlining the necessary procedures for application. To illustrate its utility, the proposed methodology was applied to real-world data, facilitating an assessment of its practicality in real-world scenarios.

RESUMO

The list of occurrences linked to significant climate change has grown in recent decades. These changes can be influenced by a set of covariates, such as temperature, location and period of the year. Analyzing the relation among elements and factors that influence the behavior of such events is extremely important for decision-making in order to minimize damages and losses. Exceedance analysis uses the tail of the distribution based on Extreme Value Theory (EVT). Extensions for these models have been proposed in literature, such as regression models for the tail parameters and a parametric or semi-parametric distribution for the part that comes before the tail (well known as bulk distribution). This work presents a new extension to exceedance model, in which the parameters for the bulk distribution capture the effect of covariates such as location and seasonality. We considered a Bayesian approach in the inference procedure. The estimation was done using MCMC -- Markov Chain Monte Carlo methods. Application results for modeling maximum and minimum temperature data showed an efficient estimation of extreme quantiles and a predictive advantage compared to models previously used in literature.

RESUMO

Rapidly urbanizing cities in Latin America experience high levels of air pollution which are known risk factors for population health. However, the estimates of long-term exposure to air pollution are scarce in the region. We developed intraurban land use regression (LUR) models to map long-term exposure to fine particulate matter (PM2.5) and nitrogen dioxide (NO2) in the five largest cities in Colombia. We conducted air pollution measurement campaigns using gravimetric PM2.5 and passive NO2 sensors for 2 weeks during both the dry and rainy seasons in 2021 in the cities of Barranquilla, Bucaramanga, Bogotá, Cali, and Medellín, and combined these data with geospatial and meteorological variables. Annual models were developed using multivariable spatial regression models. The city annual PM2.5 mean concentrations measured ranged between 12.32 and 15.99 µg/m3 while NO2 concentrations ranged between 24.92 and 49.15 µg/m3. The PM2.5 annual models explained 82% of the variance (R2) in Medellín, 77% in Bucaramanga, 73% in Barranquilla, 70% in Cali, and 44% in Bogotá. The NO2 models explained 65% of the variance in Bucaramanga, 57% in Medellín, 44% in Cali, 40% in Bogotá, and 30% in Barranquilla. Most of the predictor variables included in the models were a combination of specific land use characteristics and roadway variables. Cross-validation suggests that PM2.5 outperformed NO2 models. The developed models can be used as exposure estimate in epidemiological studies, as input in hybrid models to improve personal exposure assessment, and for policy evaluation.

Assuntos

RESUMO

Improvement in treatment options has increased the survival of people living with HIV (PLHIV). Thus, we evaluated the factors associated with better health-related quality of life (HRQoL) among PLHIV in Brazil. This was a cross-sectional study carried out among 349 PLHIV. Data were collected using an interview-based questionnaire, and HRQoL was assessed by the Brazilian version of the WHOQOL HIV BREF instrument. We used non-hierarchical cluster analysis (K-means) to compile the WHOQOL HIV BREF's overall and domain scores into a unique more multidimensional measure for HRQoL consisting of three clusters: poor, fair and good; associations with clusters of better HRQoL were assessed using multinomial logistic regression models. The mean and median overall HRQoL scores were 15.13 (SD = 3.39) and 16, respectively. The reliability and validity of the Brazilian version of the WHOQOL HIV BREF instrument was confirmed among PLHIV in a non-metropolitan, medium-sized municipality of Brazil, which reaffirmed the cross-cultural validity of this instrument. The factors male sex; heterosexual and asexual orientations; higher individual income; undetectable viral load; absence of any comorbidity and presence of an infectious or a chronic comorbidity, with mental illness as the reference; and never having consumed illegal substances were independently associated with good HRQoL. Thus, the compilation of the WHOQOL HIV BREF's overall and domain scores into a unique multidimensional measure for HRQoL, which this study proposed for the first time, may facilitate more robust interpretations and models of predictors. These differentials could simplify HRQoL as an indicator of health and wellbeing to be routinely used as a key outcome in the clinical management of patients and in the global monitoring of health system responses to HIV.

RESUMEN: La mejora en las opciones de tratamiento ha aumentado la supervivencia de las personas que viven con el VIH (PVVIH). Por lo tanto, evaluamos los factores asociados con una mejor calidad de vida relacionada con la salud (CVRS) entre las PVVIH en Brasil. Se trata de un estudio transversal realizado con 349 PVVIH. Los datos se recopilaron mediante un cuestionario basado en entrevistas y la CVRS se evaluó mediante la versión brasileña del instrumento WHOQOL VIH BREF. Usamos un análisis de conglomerados no jerárquico (K-medias) para compilar las puntuaciones generales y de dominios del WHOQOL HIV BREF en una medida única más multidimensional para la CVRS que consta de tres conglomerados: deficiente, regular y bueno; y las asociaciones con grupos de mejor CVRS se evaluaron mediante modelos de regresión logística multinomial. Las puntuaciones de la CVRS global media y mediana fueron 15,13 (DE = 3,39) y 16. La confiabilidad y validez del WHOQOL VIH BREF versión brasileña fue confirmada entre personas que viven con el VIH en un municipio no metropolitano de mediana población de Brasil, lo que reafirma la validez transcultural de este instrumento. Los factores sexo masculino; orientaciones heterosexuales y asexuales; mayores ingresos individuales; carga viral indetectable; ausencia de comorbilidad y presencia de comorbilidad infecciosa o crónica, teniendo como referencia la enfermedad mental; y nunca haber consumido sustancias ilegales se asociaron de forma independiente con una buena CVRS. Por lo tanto, la compilación de las puntuaciones generales y de dominio del WHOQOL HIV BREF en una medida multidimensional única para la CVRS, que este estudio propuso por primera vez, puede facilitar interpretaciones y modelos de predictores más robustos. Estos diferenciales podrían simplificar la HRQoL como un indicador de salud y bienestar para ser utilizado de forma rutinaria como un resultado clave en el manejo clínico de los pacientes y en el monitoreo global de las respuestas del sistema de salud al VIH.

Assuntos

RESUMO

Identifying and selecting genotypes tolerant to heat stress might improve reproductive traits in dairy cattle, including oocyte and embryo production. The temperature-humidity index (THI) was used, via random regression models, to investigate the impact of heat stress on genetic parameters and breeding values of oocyte and embryo production in Gir dairy cattle. We evaluated records of total oocytes (TO), viable oocytes (VO), cleaved embryos (CE), and viable embryos (VE) from dairy Gir donors. Twenty-four models were tested, considering age at ovum pick-up (AOPU) and THI means as a regressor in the genetic evaluation. We computed THI in eight periods, from 0 to 112 days before ovum pick-up, which were adjusted by different orders of Legendre polynomials (second, third, and fourth). The best-fit model according to Akaike's information criterion (AIC) and Model Posterior Probabilities (MPP) considered Legendre polynomials of third order and THI means of 112 days for TO, fourth order and 56 days for VO, second order and 28 days for CE, and second order and 42 days for VE, respectively. The heritability (h2) estimates across AOPU and THI scales ranged from 0.34 to 0.62 for TO, 0.31 to 0.58 for VO, 0.26 to 0.39 for CE, and 0.15 to 0.26 for VE, respectively. The fraction of the phenotypic variance explained by the permanent environment in different AOPU and THI scales ranged from 0.03 to 0.25 for TO, 0.05 to 0.26 for VO, 0.09 to 0.36 for CE, and 0.15 to 0.27 for VE, respectively. Spearman's rank correlation between the estimated breeding values in different AOPU and THI scale from the top 5% sires and females ranged from 0.18 to 0.90 for TO, 0.31 to 0.95 for VO, 0.14 to 0.85 for CE, and 0.47 to 0.94 for VE, respectively. The h2 estimates for all evaluated traits varied from moderate to high magnitude across AOPU and THI scales, indicating that genetic selection can result in rapid genetic progress for the evaluated traits. There was a reranking among the best animals in different AOPU and THI. It is possible to select dairy Gir cattle tolerant to heat stress to improve oocyte and embryo production.

Assuntos

RESUMO

Introduction: Chronic kidney disease (CDK) progression studies increasingly use surrogate endpoints based on the estimated glomerular filtration rate. The clinical characteristics of these endpoints bring new challenges in comparing groups of patients, as traditional Cox models may lead to biased estimates mainly because they do not assume a hazard function. Objective: This study proposes the use of parametric survival analysis models with the three most commonly used endpoints in nephrology based on a case study. Estimated glomerular filtration rate (eGFR) decay > 5 mL/year, eGFR decline > 30%, and change in CKD stage were evaluated. Method: The case study is a 5-year retrospective cohort study that enrolled 778 patients in the predialysis stage. Exponential, Weibull, Gompertz, lognormal, and logistic models were compared, and proportional hazard and accelerated failure time (AFT) models were evaluated. Results: The endpoints had quite different hazard functions, demonstrating the importance of choosing appropriate models for each. AFT models were more suitable for the clinical interpretation of the effects of covariates on these endpoints. Conclusion: Surrogate endpoints have different hazard distributions over time, which is already recognized by nephrologists. More flexible analysis techniques that capture these relevant clinical characteristics in decision-making should be encouraged and disseminated in nephrology research.

RESUMO

The global trade of agricultural commodities has profound social-ecological impacts, from potentially increasing food availability and agricultural efficiency, to displacing local communities, and to incentivizing environmental destruction. Supply chain stickiness, understood as the stability in trading relationships between supply chain actors, moderates the impacts of agricultural commodity production and the possibilities for supply-chain interventions. However, what factors determine stickiness, that is, how and why farmers, traders, food processors, and consumer countries, develop and maintain trading relationships with specific producing regions, remains unclear. Here, we use data on the Brazilian soy supply chain, a mixed methods approach based on extensive actor-based fieldwork, and an explanatory regression model, to identify and explore the factors that influence stickiness between places of production and supply chain actors. We find four groups of factors to be important: economic incentives, institutional enablers and constraints, social and power dimensions, and biophysical and technological conditions. Among the factors we explore, surplus capacity in soy processing infrastructure, (i.e., crushing and storage facilities) is important in increasing stickiness, as is export-oriented production. Conversely, volatility in market demand expressed by farm-gate soy prices and lower land-tenure security are key factors reducing stickiness. Importantly, we uncover heterogeneity and context-specificity in the factors determining stickiness, suggesting tailored supply-chain interventions are beneficial. Understanding supply chain stickiness does not, in itself, provide silver-bullet solutions to stopping deforestation, but it is a crucial prerequisite to understanding the relationships between supply chain actors and producing regions, identifying entry points for supply chain sustainability interventions, assessing the effectiveness of such interventions, forecasting the restructuring of trade flows, and considering sourcing patterns of supply chain actors in territorial planning.

RESUMO

The number of dairy farms adopting automatic milking systems (AMS) has considerably increased around the world aiming to reduce labor costs, improve cow welfare, increase overall performance, and generate a large amount of daily data, including production, behavior, health, and milk quality records. In this context, this study aimed to (1) estimate genomic-based variance components for milkability traits derived from AMS in North American Holstein cattle based on random regression models; and (2) derive and estimate genetic parameters for novel behavioral indicators based on AMS-derived data. A total of 1,752,713 daily records collected using 36 milking robot stations and 70,958 test-day records from 4,118 genotyped Holstein cows were used in this study. A total of 57,600 SNP remained after quality control. The daily-measured traits evaluated were milk yield (MY, kg), somatic cell score (SCS, score unit), milk electrical conductivity (EC, mS), milking efficiency (ME, kg/min), average milk flow rate (FR, kg/min), maximum milk flow rate (FRM, kg/min), milking time (MT, min), milking failures (MFAIL), and milking refusals (MREF). Variance components and genetic parameters for MY, SCS, ME, FR, FRM, MT, and EC were estimated using the AIREMLF90 software under a random regression model fitting a third-order Legendre orthogonal polynomial. A threshold Bayesian model using the THRGIBBS1F90 software was used for genetically evaluating MFAIL and MREF. The daily heritability estimates across days in milk (DIM) ranged from 0.07 to 0.28 for MY, 0.02 to 0.08 for SCS, 0.38 to 0.49 for EC, 0.45 to 0.56 for ME, 0.43 to 0.52 for FR, 0.47 to 0.58 for FRM, and 0.22 to 0.28 for MT. The estimates of heritability (± SD) for MFAIL and MREF were 0.02 ± 0.01 and 0.09 ± 0.01, respectively. Slight differences in the genetic correlations were observed across DIM for each trait. Strong and positive genetic correlations were observed among ME, FR, and FRM, with estimates ranging from 0.94 to 0.99. Also, moderate to high and negative genetic correlations (ranging from -0.48 to -0.86) were observed between MT and other traits such as SCS, ME, FR, and FRM. The genetic correlation (± SD) between MFAIL and MREF was 0.25 ± 0.02, indicating that both traits are influenced by different sets of genes. High and negative genetic correlations were observed between MFAIL and FR (-0.58 ± 0.02) and MFAIL and FRM (-0.56 ± 0.02), indicating that cows with more MFAIL are those with lower FR. The use of random regression models is a useful alternative for genetically evaluating AMS-derived traits measured throughout the lactation. All the milkability traits evaluated in this study are heritable and have demonstrated selective potential, suggesting that their use in dairy cattle breeding programs can improve dairy production efficiency in AMS.

Assuntos

RESUMO

The body weight (BW) of an animal is a vital economic trait that might help in decision-making in the handling of animals. The objective of the present study was to develop equations for the prediction of BW in Pelibuey sheep using scrotal circumference (SC). The BW (23.40 ± 6.96 kg) and SC (20.25 ± 6.19 cm) have been recorded in 405 male Pelibuey at the Southeastern Center for Ovine Integration, Mexico. Linear, logarithmic, quadratic, exponential, cubic, and power regression models were used for data analysis. Pearson correlation (R), Coefficient of determination (R2), Adjusted coefficient of determination (Adj.R2) Root mean square error (RMSE), Akaike information criterion (AIC), and Bayesian information criterion (BIC) were used to select the best model. Power regression model showed the highest R (0.93), R2 (0.86), Adj.R2 (0.86) and lowest RMSE (0.02), AIC (-989.44) and BIC (-981.44). The current study suggests that SC might be used as the only predictor for BW of growing Pelibuey sheep raised under tropical conditions.

O peso corporal (PC) do animal é uma característica econômica importante, que pode auxiliar na tomada de decisões no manejo dos animais. O objetivo do presente estudo foi desenvolver equações para a predição do PC em ovinos Pelibuey por meio da circunferência escrotal (CE). O PC (23,40±6,96kg) e a CE (20,25±6,19cm) foram registrados em 405 ovinos machos da raça Pelibuey no Centro de Integração Ovina da Região Sudeste do México. Os modelos lineares, logarítmicos, quadráticos, exponenciais, cúbicos e de regressão de potência foram utilizados para a análise dos dados. A correlação de Pearson (R), o coeficiente de determinação (R2), o coeficiente de determinação ajustado (Adj.R2), o erro do quadrado médio (EQM), o critério de informação de Akaike (AIC) e o critério de informação bayesiano (BIC) foram usados para selecionar o melhor modelo. O modelo de regressão de potência apresentou maiores R (0,93), R2 (0,86), Adj.R2 (0,86) e menores EQM (0,02), AIC (-989,44) e BIC (-981,44). O estudo atual sugere que a CE pode ser usada como um único preditor para o PC de ovinos Pelibuey em crescimento criadas em condições tropicais.

Assuntos

RESUMO

Introducción: La relación entre funciones ejecutivas y habilidades matemáticas ha sido ampliamente estudiada. Sin embargo, no existe consenso respecto de la contribución específica de la memoria de trabajo y la planificación en el desarrollo de competencias matemáticas tempranas. El objetivo de este estudio fue determinar la capacidad predictiva de estos dos dominios ejecutivos sobre las competencias matemáticas de preescolares. Método: Se implementó un diseño no experimental ex post facto, con una muestra de 104 niños/as chilenos/as. La evaluación de sus funciones ejecutivas se realizó con la tarea "inversión de números" de la Batería IV Woodcock-Muñoz para evaluar la memoria de trabajo verbal, la subprueba "Torpo, el topo torpe" del Test de Evaluación Neuropsicológica Infantil (TENI) para evaluar la memoria de trabajo visoespacial y el Test de Laberintos de Porteus para evaluar la planificación. Con el fin de evaluar las habilidades matemáticas se utilizó el Test de Evaluación Matemática Temprana Utrecht (TEMT-U), versión chilena. Se realizaron análisis descriptivos, correlaciones y modelos de regresión múltiple. Resultados: La memoria de trabajo verbal seguida por la memoria de trabajo visoespacial y la planificación fueron los mejores predictores de las competencias matemáticas de los/as niños/as. Conclusiones: Estos resultados sugieren que estas funciones ejecutivas desempeñan un papel clave en el aprendizaje de las matemáticas y aportan información específica a las/os educadoras/es para que puedan planificar sus estrategias de enseñanza en función de las demandas cognitivas que requiere cada habilidad matemática, lo que puede ser una vía potencial para promover mejores logros de aprendizaje en esta importante disciplina.

Introduction: The relationship between executive functions and mathematical skills has been extensively studied. However, there is no consensus regarding the specific contribution of working memory and planning in the development of early mathematical skills. The aim of this study was to determine the predictive capacity of these two executive domains on preschoolers' mathematical skills. Method: A non-experimental ex post facto design was implemented with a sample of 104 Chilean children. The evaluation of their executive functions was performed with the "number inversion" task of the Woodcock-Muñoz IV Battery to assess verbal working memory, the "Clumsy Mole the Clumsy Mole" subtest of the TENI Child Neuropsychological Evaluation Test to assess visuospatial working memory, and the Porteus Maze Test to assess planning. To assess mathematical skills, the Test de Evaluación Matemática Temprana Utretch TEMT-U, Chilean version, was used. Descriptive analyses, correlations and multiple regression models were performed. Results: Verbal working memory followed by visuospatial working memory and planning were the best predictors of children's mathematical skills. Conclusions: These results suggest that these executive functions play a key role in mathematics learning and provide specific information to educators so that they can plan their teaching strategies according to the cognitive demands required by each mathematical skill, which may be a potential way to promote better learning achievements in this important discipline.