Why is it so difficult to identify a single indicator of water stress in plants? A proposal for a multivariate analysis to assess emergent properties

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

A Multivariate Calibration Procedure for UV/VIS Spectrometric Monitoring of BHK-21 Cell Metabolism and Growth

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Multivariate Development and Validation of a Stability-Indicating HPLC Method for the Determination of Glimepiride in Tablets

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Multivariate analysis for animal selection in experimental research

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Multivariate morphometrics and allometry and allometry in a polymorphic ant

In this paper we describe how morphological castes can be distinguished using multivariate statistical methods combined with jackknife estimators of the allometric coefficients. Data from the polymorphic ant, Camponotus rufipes, produced two distinct patterns of allometric variation, and thus two morphological castes. Morphometric analysis distinguished different allometric patterns within the two castes, with overall variability being greater in the major workers. Caste-specific scaling variabilities were associated with the relative importance of first principal component. The static multivariate allometric coefficients for each of 10 measured characters were different between castes, but their relative magnitudes within castes were similar. Multivariate statistical analysis of worker polymorphism in ants is a more complete descriptor of shape variation than, and provides statistical and conceptual advantages over, the standard bivariate techniques commonly used.

Multivariate analysis for selecting animals for experimental research

Background Several researchers seek methods for the selection of homogeneous groups of animals in experimental studies, a fact justified because homogeneity is an indispensable prerequisite for casualization of treatments. The lack of robust methods that comply with statistical and biological principles is the reason why researchers use empirical or subjective methods, influencing their results. Objective To develop a multivariate statistical model for the selection of a homogeneous group of animals for experimental research and to elaborate a computational package to use it. Methods The set of echocardiographic data of 115 male Wistar rats with supravalvular aortic stenosis (AoS) was used as an example of model development. Initially, the data were standardized, and became dimensionless. Then, the variance matrix of the set was submitted to principal components analysis (PCA), aiming at reducing the parametric space and at retaining the relevant variability. That technique established a new Cartesian system into which the animals were allocated, and finally the confidence region (ellipsoid) was built for the profile of the animals’ homogeneous responses. The animals located inside the ellipsoid were considered as belonging to the homogeneous batch; those outside the ellipsoid were considered spurious. Results The PCA established eight descriptive axes that represented the accumulated variance of the data set in 88.71%. The allocation of the animals in the new system and the construction of the confidence region revealed six spurious animals as compared to the homogeneous batch of 109 animals. Conclusion The biometric criterion presented proved to be effective, because it considers the animal as a whole, analyzing jointly all parameters measured, in addition to having a small discard rate.

Improved Regression Estimation of a Multivariate Relationship with Population Data on the Bivariate Relationship

Regression coefficients specify the partial effect of a regressor on the dependent variable. Sometimes the bivariate or limited multivariate relationship of that regressor variable with the dependent variable is known from population-level data. We show here that such population- level data can be used to reduce variance and bias about estimates of those regression coefficients from sample survey data. The method of constrained MLE is used to achieve these improvements. Its statistical properties are first described. The method constrains the weighted sum of all the covariate-specific associations (partial effects) of the regressors on the dependent variable to equal the overall association of one or more regressors, where the latter is known exactly from the population data. We refer to those regressors whose bivariate or limited multivariate relationships with the dependent variable are constrained by population data as being ‘‘directly constrained.’’ Our study investigates the improvements in the estimation of directly constrained variables as well as the improvements in the estimation of other regressor variables that may be correlated with the directly constrained variables, and thus ‘‘indirectly constrained’’ by the population data. The example application is to the marital fertility of black versus white women. The difference between white and black women’s rates of marital fertility, available from population-level data, gives the overall association of race with fertility. We show that the constrained MLE technique both provides a far more powerful statistical test of the partial effect of being black and purges the test of a bias that would otherwise distort the estimated magnitude of this effect. We find only trivial reductions, however, in the standard errors of the parameters for indirectly constrained regressors.

Petroleum contamination impact on macrobenthic communities under the influence of an oil refinery: Integrating chemical and biological multivariate data

Petroleum contamination impact on macrobenthic communities in the northeast portion of Todos os Santos Bay was assessed combining in multivariate analyses, chemical parameters such as aliphatic and polycyclic aromatic hydrocarbon indices and concentration ratios with benthic ecological parameters. Sediment samples were taken in August 2000 with a 0.05 m(2) van Veen grab at 28 sampling locations. The predominance of n-alkanes with more than 24 carbons, together with CPI values close to one, and the fact that most of the stations showed UCM/resolved aliphatic hydrocarbons ratios (UCM:R) higher than two, indicated a high degree of anthropogenic contribution, the presence of terrestrial plant detritus, petroleum products and evidence of chronic oil pollution. The indices used to determine the origin of PAH indicated the occurrence of a petrogenic contribution. A pyrolytic contribution constituted mainly by fossil fuel combustion derived PAH was also observed. The results of the stepwise multiple regression analysis performed with chemical data and benthic ecological descriptors demonstrated that not only total PAH concentrations but also specific concentration ratios or indices such as >= C24:< C24, An/178 and Fl/Fl + Py, are determining the structure of benthic communities within the study area. According to the BIO-ENV results petroleum related variables seemed to have a main influence on macrofauna community structure. The PCA ordination performed with the chemical data resulted in the formation of three groups of stations. The decrease in macrofauna density, number of species and diversity from groups III to I seemed to be related to the occurrence of high aliphatic hydrocarbon and PAH concentrations associated with fine sediments. Our results showed that macrobenthic communities in the northeast portion of Todos os Santos Bay are subjected to the impact of chronic oil pollution as was reflected by the reduction in the number of species and diversity. These results emphasise the importance to combine in multivariate approaches not only total hydrocarbon concentrations but also indices, isomer pair ratios and specific compound concentrations with biological data to improve the assessment of anthropogenic impact on marine ecosystems. (c) 2008 Elsevier Ltd. All rights reserved.

Detecting an abnormality in a recovery boiler using dynamic multivariate data analysis with parallel coordinate plots

Data visualization techniques are powerful in the handling and analysis of multivariate systems. One such technique known as parallel coordinates was used to support the diagnosis of an event, detected by a neural network-based monitoring system, in a boiler at a Brazilian Kraft pulp mill. Its attractiveness is the possibility of the visualization of several variables simultaneously. The diagnostic procedure was carried out step-by-step going through exploratory, explanatory, confirmatory, and communicative goals. This tool allowed the visualization of the boiler dynamics in an easier way, compared to commonly used univariate trend plots. In addition it facilitated analysis of other aspects, namely relationships among process variables, distinct modes of operation and discrepant data. The whole analysis revealed firstly that the period involving the detected event was associated with a transition between two distinct normal modes of operation, and secondly the presence of unusual changes in process variables at this time.

Atmospheric conditions, lunar phases, and childbirth: a multivariate analysis

Our objective was to assess extrinsic influences upon childbirth. In a cohort of 1,826 days containing 17,417 childbirths among them 13,252 spontaneous labor admissions, we studied the influence of environment upon the high incidence of labor (defined by 75th percentile or higher), analyzed by logistic regression. The predictors of high labor admission included increases in outdoor temperature (odds ratio: 1.742, P = 0.045, 95%CI: 1.011 to 3.001), and decreases in atmospheric pressure (odds ratio: 1.269, P = 0.029, 95%CI: 1.055 to 1.483). In contrast, increases in tidal range were associated with a lower probability of high admission (odds ratio: 0.762, P = 0.030, 95%CI: 0.515 to 0.999). Lunar phase was not a predictor of high labor admission (P = 0.339). Using multivariate analysis, increases in temperature and decreases in atmospheric pressure predicted high labor admission, and increases of tidal range, as a measurement of the lunar gravitational force, predicted a lower probability of high admission.

Quantitative Chemical Profile and Multivariate Statistical Analysis of Alembic Distilled Sugarcane Spirit Fractions

Concentrations of 39 organic compounds were determined in three fractions (head, heart and tail) obtained from the pot still distillation of fermented sugarcane juice. The results were evaluated using analysis of variance (ANOVA), Tukey's test, principal component analysis (PCA), hierarchical cluster analysis (HCA) and linear discriminant analysis (LDA). According to PCA and HCA, the experimental data lead to the formation of three clusters. The head fractions give rise to a more defined group. The heart and tail fractions showed some overlap consistent with its acid composition. The predictive ability of calibration and validation of the model generated by LDA for the three fractions classification were 90.5 and 100%, respectively. This model recognized as the heart twelve of the thirteen commercial cachacas (92.3%) with good sensory characteristics, thus showing potential for guiding the process of cuts.

IDENTIFICATION OF ETHANOLIC WOOD EXTRACTS USING ELECTRONIC ABSORPTION SPECTRUM AND MULTIVARIATE ANALYSIS

IDENTIFICATION OF ETHANOLIC WOOD EXTRACTS USING ELECTRONIC ABSORPTION SPECTRUM AND MULTIVARIATE ANALYSIS. The application of multivariate analysis to spectrophotometric (UV) data was explored for distinguishing extracts of cachaca woods commonly used in the manufacture of casks for aging cachacas (oak, cabretiva-parda, jatoba, amendoim and canela-sassafras). Absorbances close to 280 nm were more strongly correlated with oak and jatoba woods, whereas absorbances near 230 nm were more correlated with canela-sassafras and cabretiva-parda. A comparison between the spectrophotometric model and the model based on chromatographic (HPLC-DAD) data was carried out. The spectrophotometric model better explained the variance data (PC1 + PC2 = 91%) exhibiting potential as a routine method for checking aged spirits.

Multivariate analysis in the maximum strength performance

This study performed an exploratory analysis of the anthropometrical and morphological muscle variables related to the one-repetition maximum (1RM) performance. In addition, the capacity of these variables to predict the force production was analyzed. 50 active males were submitted to the experimental procedures: vastus lateralis muscle biopsy, quadriceps magnetic resonance imaging, body mass assessment and 1RM test in the leg-press exercise. K-means cluster analysis was performed after obtaining the body mass, sum of the left and right quadriceps muscle cross-sectional area (Sigma CSA), percentage of the type II fibers and the 1RM performance. The number of clusters was defined a priori and then were labeled as high strength performance (HSP1RM) group and low strength performance (LSP1RM) group. Stepwise multiple regressions were performed by means of body mass, Sigma CSA, percentage of the type II fibers and clusters as predictors' variables and 1RM performance as response variable. The clusters mean +/- SD were: 292.8 +/- 52.1 kg, 84.7 +/- 17.9 kg, 19249.7 +/- 1645.5 mm(2) and 50.8 +/- 7.2% for the HSP1RM and 254.0 +/- 51.1 kg, 69.2 +/- 8.1 kg, 15483.1 +/- 1 104.8 mm(2) and 51.7 +/- 6.2 %, for the LSP1RM in the 1RM, body mass, Sigma CSA and muscle fiber type II percentage, respectively. The most important variable in the clusters division was the Sigma CSA. In addition, the Sigma CSA and muscle fiber type II percentage explained the variance in the 1RM performance (Adj R-2 = 0.35, p = 0.0001) for all participants and for the LSP1RM (Adj R-2 = 0.25, p = 0.002). For the HSP1RM, only the Sigma CSA was entered in the model and showed the highest capacity to explain the variance in the 1RM performance (Adj R-2 = 0.38, p = 0.01). As a conclusion, the muscle CSA was the most relevant variable to predict force production in individuals with no strength training background.

Understanding the correlates of adolescents' dietary intake patterns. A multivariate analysis

We investigated dietary intake patterns (DIP) in adolescents (14-18 year-olds) and the association with demographic and socioeconomic characteristics and lifestyle variables. This school-based survey was carried out among high school students from the city of Maringa in the state of Parana (PR), Brazil (2007). The sample included 991 students (54.5% girls) from high schools. DIPs were investigated by the frequency of weekly consumption of each food group: vegetables, fruit, rice, beans, fried food, sweet food, milk, soda, meat, eggs, alcoholic drinks. Independent variables were: demographic and socioeconomic characteristics and lifestyle variables. DIPS were identified using principal component analysis with orthogonal rotation (varimax). Three components were extracted. Component 1 (fried foods, sweets and soft drinks) was positively associated with not having breakfast for girls and dinner for boys. Moreover, component 2 (consumption of fruit and vegetables) was positively associated with having breakfast at home for boys and number of meals for girls. Component 3 (beans, eggs and meat) was positively associated with having lunch, employment and sedentary behavior level for girls. However, it was negatively associated with having lunch and dinner for boys. Adolescents who have healthier eating patterns also had other healthier behaviors regardless of gender. However, factors associated with dietary patterns differ between boys and girls. (C) 2012 Elsevier Ltd. All rights reserved.

Signal propagation in Bayesian networks and its relationship with intrinsically multivariate predictive variables

A set of predictor variables is said to be intrinsically multivariate predictive (IMP) for a target variable if all properly contained subsets of the predictor set are poor predictors of the. target but the full set predicts the target with great accuracy. In a previous article, the main properties of IMP Boolean variables have been analytically described, including the introduction of the IMP score, a metric based on the coefficient of determination (CoD) as a measure of predictiveness with respect to the target variable. It was shown that the IMP score depends on four main properties: logic of connection, predictive power, covariance between predictors and marginal predictor probabilities (biases). This paper extends that work to a broader context, in an attempt to characterize properties of discrete Bayesian networks that contribute to the presence of variables (network nodes) with high IMP scores. We have found that there is a relationship between the IMP score of a node and its territory size, i.e., its position along a pathway with one source: nodes far from the source display larger IMP scores than those closer to the source, and longer pathways display larger maximum IMP scores. This appears to be a consequence of the fact that nodes with small territory have larger probability of having highly covariate predictors, which leads to smaller IMP scores. In addition, a larger number of XOR and NXOR predictive logic relationships has positive influence over the maximum IMP score found in the pathway. This work presents analytical results based on a simple structure network and an analysis involving random networks constructed by computational simulations. Finally, results from a real Bayesian network application are provided. (C) 2012 Elsevier Inc. All rights reserved.