Selecting statistical models to study the relationship between soybean yield and soil physical properties

Statistical models allow the representation of data sets and the estimation and/or prediction of the behavior of a given variable through its interaction with the other variables involved in a phenomenon. Among other different statistical models, are the autoregressive state-space models (ARSS) and the linear regression models (LR), which allow the quantification of the relationships among soil-plant-atmosphere system variables. To compare the quality of the ARSS and LR models for the modeling of the relationships between soybean yield and soil physical properties, Akaike's Information Criterion, which provides a coefficient for the selection of the best model, was used in this study. The data sets were sampled in a Rhodic Acrudox soil, along a spatial transect with 84 points spaced 3 m apart. At each sampling point, soybean samples were collected for yield quantification. At the same site, soil penetration resistance was also measured and soil samples were collected to measure soil bulk density in the 0-0.10 m and 0.10-0.20 m layers. Results showed autocorrelation and a cross correlation structure of soybean yield and soil penetration resistance data. Soil bulk density data, however, were only autocorrelated in the 0-0.10 m layer and not cross correlated with soybean yield. The results showed the higher efficiency of the autoregressive space-state models in relation to the equivalent simple and multiple linear regression models using Akaike's Information Criterion. The resulting values were comparatively lower than the values obtained by the regression models, for all combinations of explanatory variables.

Class of correlated random networks with hidden variables

We study a class of models of correlated random networks in which vertices are characterized by hidden variables controlling the establishment of edges between pairs of vertices. We find analytical expressions for the main topological properties of these models as a function of the distribution of hidden variables and the probability of connecting vertices. The expressions obtained are checked by means of numerical simulations in a particular example. The general model is extended to describe a practical algorithm to generate random networks with an a priori specified correlation structure. We also present an extension of the class, to map nonequilibrium growing networks to networks with hidden variables that represent the time at which each vertex was introduced in the system.

Outcome of smoking cessation counselling of HIV-positive persons by HIV care physicians.

OBJECTIVES: Smoking is the most prevalent modifiable risk factor for cardiovascular diseases among HIV-positive persons. We assessed the effect on smoking cessation of training HIV care physicians in counselling. METHODS: The Swiss HIV Cohort Study (SHCS) is a multicentre prospective observational database. Our single-centre intervention at the Zurich centre included a half day of standardized training for physicians in counselling and in the pharmacotherapy of smokers, and a physicians' checklist for semi-annual documentation of their counselling. Smoking status was then compared between participants at the Zurich centre and other institutions. We used marginal logistic regression models with exchangeable correlation structure and robust standard errors to estimate the odds of smoking cessation and relapse. RESULTS: Between April 2000 and December 2010, 11 056 SHCS participants had 121 238 semi-annual visits and 64 118 person-years of follow-up. The prevalence of smoking decreased from 60 to 43%. During the intervention at the Zurich centre from November 2007 to December 2009, 1689 participants in this centre had 6068 cohort visits. These participants were more likely to stop smoking [odds ratio (OR) 1.23; 95% confidence interval (CI) 1.07-1.42; P=0.004] and had fewer relapses (OR 0.75; 95% CI 0.61-0.92; P=0.007) than participants at other SHCS institutions. The effect of the intervention was stronger than the calendar time effect (OR 1.19 vs. 1.04 per year, respectively). Middle-aged participants, injecting drug users, and participants with psychiatric problems or with higher alcohol consumption were less likely to stop smoking, whereas persons with a prior cardiovascular event were more likely to stop smoking. CONCLUSIONS: An institution-wide training programme for HIV care physicians in smoking cessation counselling led to increased smoking cessation and fewer relapses.

Low adiponectin is associated with increased ambulatory pulse pressure and activation of the renin-angiotensin system in subjects of African descent

Purpose: Adiponectin, arterial stiffness, as well components of the renin-angiotensin system are associated with cardiovascular risk. This study was aimed to investigate whether plasma adiponectin was directly linked with pulse pressure (PP), as a marker for arterial stiffness, and the renin-angiotensin system (RAS). Methods and materials: A family-based study in subjects of African descent enriched with hypertensive patients was carried out in the Seychelles. Fasting plasma adiponectin was determined by ELISA, plasma renin activity according to the antibody-trapping principle and plasma aldosterone by radioimmunoassay. Daytime ambulatory blood pressure (BP) was measured using Diasys Integra devices. PP was calculated as the difference between systolic and diastolic BP. The association of adiponectin with PP, plasma renin activity and plasma aldosterone were analyzed using generalized estimating equations with a gaussian family link and an exchangeable correlation structure to account for familial aggregation. Results: Data from 335 subjects from 73 families (152 men, 183 women) were available. Men and women had mean (SD) age of 45.4 ± 11.1 and 47.3 ± 12.4 years, BMI of 26.3 ± 4.4 and 27.8 ± 5.1 kg/m2, daytime systolic/diastolic BP of 132.6 ± 15.4 / 86.1 ± 10.9 and 130 ± 17.6 / 83.4 ± 11.1 mmHg, and daytime PP of 46.5 ± 9.9 and 46.7 ± 10.7 mmHg, respectively. Plasma adiponectin was 4.4± 3.04 ng/ml in men and 7.39 ± 5.44 ng/ml in women (P <0.001). After adjustment for age, sex and BMI, log-transformed adiponectin was negatively associated with daytime PP (-0.009 ± 0.003, P = 0.004), plasma renin activity (-0.248 ± 0.080, P = 0.002) and plasma aldosterone (-0.004 ± 0.002, P = 0.014). Conclusion: Low adiponectin is associated with increased ambulatory PP and RAS activation in subjects of African descent. Our data are consistent with the observation that angiotensin II receptor blockers increase adiponectin in humans.

Étude des maxima de champs gaussiens corrélés.

Ce mémoire porte sur l’étude des maxima de champs gaussiens. Plus précisément, l’étude portera sur la convergence en loi, la convergence du premier ordre et la convergence du deuxième ordre du maximum d’une collection de variables aléatoires gaussiennes. Les modèles de champs gaussiens présentés sont le modèle i.i.d., le modèle hiérarchique et le champ libre gaussien. Ces champs gaussiens diffèrent par le degré de corrélation entre les variables aléatoires. Le résultat principal de ce mémoire sera que la convergence en probabilité du premier ordre du maximum est la même pour les trois modèles. Quelques résultats de simulations seront présentés afin de corroborer les résultats théoriques obtenus.

Stochastic modelling of rainfall from satellite data

Satellite-based rainfall monitoring is widely used for climatological studies because of its full global coverage but it is also of great importance for operational purposes especially in areas such as Africa where there is a lack of ground-based rainfall data. Satellite rainfall estimates have enormous potential benefits as input to hydrological and agricultural models because of their real time availability, low cost and full spatial coverage. One issue that needs to be addressed is the uncertainty on these estimates. This is particularly important in assessing the likely errors on the output from non-linear models (rainfall-runoff or crop yield) which make use of the rainfall estimates, aggregated over an area, as input. Correct assessment of the uncertainty on the rainfall is non-trivial as it must take account of • the difference in spatial support of the satellite information and independent data used for calibration • uncertainties on the independent calibration data • the non-Gaussian distribution of rainfall amount • the spatial intermittency of rainfall • the spatial correlation of the rainfall field This paper describes a method for estimating the uncertainty on satellite-based rainfall values taking account of these factors. The method involves firstly a stochastic calibration which completely describes the probability of rainfall occurrence and the pdf of rainfall amount for a given satellite value, and secondly the generation of ensemble of rainfall fields based on the stochastic calibration but with the correct spatial correlation structure within each ensemble member. This is achieved by the use of geostatistical sequential simulation. The ensemble generated in this way may be used to estimate uncertainty at larger spatial scales. A case study of daily rainfall monitoring in the Gambia, west Africa for the purpose of crop yield forecasting is presented to illustrate the method.

Quantifying uncertainty in critical loads: (B) acidity mass balance critical loads on a sensitive site

This paper reports an uncertainty analysis of critical loads for acid deposition for a site in southern England, using the Steady State Mass Balance Model. The uncertainty bounds, distribution type and correlation structure for each of the 18 input parameters was considered explicitly, and overall uncertainty estimated by Monte Carlo methods. Estimates of deposition uncertainty were made from measured data and an atmospheric dispersion model, and hence the uncertainty in exceedance could also be calculated. The uncertainties of the calculated critical loads were generally much lower than those of the input parameters due to a "compensation of errors" mechanism - coefficients of variation ranged from 13% for CLmaxN to 37% for CL(A). With 1990 deposition, the probability that the critical load was exceeded was > 0.99; to reduce this probability to 0.50, a 63% reduction in deposition is required; to 0.05, an 82% reduction. With 1997 deposition, which was lower than that in 1990, exceedance probabilities declined and uncertainties in exceedance narrowed as deposition uncertainty had less effect. The parameters contributing most to the uncertainty in critical loads were weathering rates, base cation uptake rates, and choice of critical chemical value, indicating possible research priorities. However, the different critical load parameters were to some extent sensitive to different input parameters. The application of such probabilistic results to environmental regulation is discussed.

The interannual variability of energy transports within and over the Atlantic Ocean in a coupled climate model

To gain a new perspective on the interaction of the Atlantic Ocean and the atmosphere, the relationship between the atmospheric and oceanic meridional energy transports is studied in a version of HadCM3, the U.K. Hadley Centre's coupled climate model. The correlation structure of the energy transports in the atmosphere and Atlantic Ocean as a function of latitude, and the cross correlation between the two systems are analyzed. The processes that give rise to the correlations are then elucidated using regression analyses. In northern midlatitudes, the interannual variability of the Atlantic Ocean energy transport is dominated by Ekman processes. Anticorrelated zonal winds in the subtropics and midlatitudes, particularly associated with the North Atlantic Oscillation (NAO), drive anticorrelated meridional Ekman transports. Variability in the atmospheric energy transport is associated with changes in the stationary waves, but is only weakly related to the NAO. Nevertheless, atmospheric driving of the oceanic Ekman transports is responsible for a bipolar pattern in the correlation between the atmosphere and Atlantic Ocean energy transports. In the Tropics, the interannual variability of the Atlantic Ocean energy transport is dominated by an adjustment of the tropical ocean to coastal upwelling induced along the Venezuelan coast by a strengthening of the easterly trade winds. Variability in the atmospheric energy transport is associated with a cross-equatorial meridional overturning circulation that is only weakly associated with variability in the trade winds along the Venezuelan coast. In consequence, there is only very limited correlation between the atmosphere and Atlantic Ocean energy transports in the Tropics of HadCM3

O_3-N_2O correlations from the Atmospheric Chemistry Experiment: revisiting a diagnostic of transport and chemistry in the stratosphere

Our knowledge of stratospheric O3-N2O correlations is extended, and their potential for model-measurement comparison assessed, using data from the Atmospheric Chemistry Experiment (ACE) satellite and the Canadian Middle Atmosphere Model (CMAM). ACE provides the first comprehensive data set for the investigation of interhemispheric, interseasonal, and height-resolved differences of the O_3-N_2O correlation structure. By subsampling the CMAM data, the representativeness of the ACE data is evaluated. In the middle stratosphere, where the correlations are not compact and therefore mainly reflect the data sampling, joint probability density functions provide a detailed picture of key aspects of transport and mixing, but also trace polar ozone loss. CMAM captures these important features, but exhibits a displacement of the tropical pipe into the Southern Hemisphere (SH). Below about 21 km, the ACE data generally confirm the compactness of the correlations, although chemical ozone loss tends to destroy the compactness during late winter/spring, especially in the SH. This allows a quantitative comparison of the correlation slopes in the lower and lowermost stratosphere (LMS), which exhibit distinct seasonal cycles that reveal the different balances between diabatic descent and horizontal mixing in these two regions in the Northern Hemisphere (NH), reconciling differences found in aircraft measurements, and the strong role of chemical ozone loss in the SH. The seasonal cycles are qualitatively well reproduced by CMAM, although their amplitude is too weak in the NH LMS. The correlation slopes allow a "chemical" definition of the LMS, which is found to vary substantially in vertical extent with season.

Data assimilation with correlated observation errors: experiments with a 1-D shallow water model

Remote sensing observations often have correlated errors, but the correlations are typically ignored in data assimilation for numerical weather prediction. The assumption of zero correlations is often used with data thinning methods, resulting in a loss of information. As operational centres move towards higher-resolution forecasting, there is a requirement to retain data providing detail on appropriate scales. Thus an alternative approach to dealing with observation error correlations is needed. In this article, we consider several approaches to approximating observation error correlation matrices: diagonal approximations, eigendecomposition approximations and Markov matrices. These approximations are applied in incremental variational assimilation experiments with a 1-D shallow water model using synthetic observations. Our experiments quantify analysis accuracy in comparison with a reference or ‘truth’ trajectory, as well as with analyses using the ‘true’ observation error covariance matrix. We show that it is often better to include an approximate correlation structure in the observation error covariance matrix than to incorrectly assume error independence. Furthermore, by choosing a suitable matrix approximation, it is feasible and computationally cheap to include error correlation structure in a variational data assimilation algorithm.

Evaluating multivariate forecast densities: a comparison of two approaches

We consider methods of evaluating multivariate density forecasts. A recently proposed method is found to lack power when the correlation structure is mis-specified. Tests that have good power to detect mis-specifications of this sort are described. We also consider the properties of the tests in the presence of more general mis-specifications.

Comparações entre os valores genéticos para características de crescimento de bovinos da raça Nelore preditos com modelos de dimensão finita ou infinita

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Geochemical characterization of heavy metal contaminated area using multivariate factorial kriging

This paper describes a geostatistical method, known as factorial kriging analysis, which is well suited for analyzing multivariate spatial information. The method involves multivariate variogram modeling, principal component analysis, and cokriging. It uses several separate correlation structures, each corresponding to a specific spatial scale, and yields a set of regionalized factors summarizing the main features of the data for each spatial scale. This method is applied to an area of high manganese-ore mining activity in Amapa State, North Brazil. Two scales of spatial variation (0.33 and 2.0 km) are identified and interpreted. The results indicate that, for the short-range structure, manganese, arsenic, iron, and cadmium are associated with human activities due to the mining work, while for the long-range structure, the high aluminum, selenium, copper, and lead concentrations, seem to be related to the natural environment. At each scale, the correlation structure is analyzed, and regionalized factors are estimated by cokriging and then mapped.

Dinâmica de correlações no mercado financeiro Bovespa&BMF

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Indicador multivariado policórico: proposta de indicador para o diagnóstico da aprendizagem organizacional

Pós-graduação em Engenharia Mecânica - FEG