963 resultados para STATISTICAL MODELS
Resumo:
O objetivo deste trabalho foi testar a aplicação de modelos da geoestatística para estimar o volume de resíduos lenhosos de madeira em uma área de floresta manejada no município de Paragominas, estado do Pará. Os métodos de Warren e Olsen e da Krigagem Ordinária foram utilizados para estimar o volume dos resíduos florestais em pontos amostrados e não amostrados. Os resultados confirmam que a aplicação dos métodos foi adequada, uma vez que a estimativa para o volume dos resíduos, da área em estudo, apresentou uma pequena diferença 5,2%, em relação ao valor real obtido.
Resumo:
The purpose of this article is to demonstrate an application of the design of block experiments via analysis and multiple linear regression in the investigation of a steel thermal treatment process with multiple responses. The study aimed to design statistical models to predict the mechanical properties in SAE 9254 draw steel wires, with diameters of 2.00 mm and 6.50 mm, after quench hardening and tempering. For this purpose, process input variables (wire diameter, processing speed, tempering temperature and polymer concentration) were investigated regarding their influence on the material tensile strength, yield point and hardness. The results revealed that the mechanical properties of the steel wire are significantly influenced by the selected variables, and analysis of variance (ANOVA) was employed to validate the design of the statistical models. Multiple linear regression allowed for an appropriate representation of the process, and graphical analysis was found to be very useful in displaying the behavior of the multiple responses.
Resumo:
Pós-graduação em Engenharia Elétrica - FEIS
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Pós-graduação em Engenharia Mecânica - FEG
Resumo:
Employing the method of least squares and quadratic B-spline polynomials, different statistical models were tested to identify the most appropriate to model the mean trajectories of live weight and carcass yield of Nile tilapia (Oreochromis niloticus). Data of live weight (8,758) and carcass yield (2,042) of tilapias with ages between 106 and 245 days were obtained from 72 families derived from 36 males and 72 females. The sex and tank variables were considered as classificatory and the coefficients of quadratic polynomials B-spline of two to five intervals of the same size were used as covariables. According to most fit criteria used, the models with quadratic B-spline polynomial with five intervals of the same size presented the best adjustments. The increase in number of intervals of B-spline polynomial improved the fit of the polynomials to the data. The inclusion of classificatory effects from sex, tank, the interaction of these effects and the quadratic polynomial B-spline nested in this interaction indicated that, over time, each sex, grown in different tank, presented different mean trajectory, necessitating the inclusion of nesting time in the interaction sex x tank in order to avoid the under or overestimation of breeding values of the selection candidates in breeding programs of this species.
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
Resumo:
Reaction norm models have been widely used to study genotype by environment interaction (G × E) in animal breeding. The objective of this study was to describe environmental sensitivity across first lactation in Brazilian Holstein cows using a reaction norm approach. A total of 50,168 individual monthly test day (TD) milk yields (10 test days) from 7476 complete first lactations of Holstein cattle were analyzed. The statistical models for all traits (10 TDs and for 305-day milk yield) included the fixed effects of contemporary group, age of cow (linear and quadratic effects), and days in milk (linear effect), except for 305-day milk yield. A hierarchical reaction norm model (HRNM) based on the unknown covariate was used. The present study showed the presence of G × E in milk yield across first lactation of Holstein cows. The variation in the heritability estimates implies differences in the response to selection depending on the environment where the animals of this population are evaluated. In the average environment, the heritabilities for all traits were rather similar, in range from 0.02 to 0.63. The scaling effect of G × E predominated throughout most of lactation. Particularly during the first 2 months of lactation, G × E caused reranking of breeding values. It is therefore important to include the environmental sensitivity of animals according to the phase of lactation in the genetic evaluations of Holstein cattle in tropical environments.
Resumo:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Resumo:
Osmotic potentials on water uptake and germination of Guazuma Ulmifolia Lam. (Sterculiaceae) seeds. This work was carried out in the Germination Lab. of the Department of Botany, Institute of Biosciences, São Paulo State University (UNESP), Botucatu, São Paulo State, Brazil. The aims of this work were to determine the water uptake curve and to evaluate the germination of Guazuma ulmifolia seeds subjected to different water potentials. For the water uptake curve, seven replicates of 50 pre-scarified seeds were placed onto paper moistened with 15 mL PEG 6000 solution under the potentials 0 (control), -0.3 and -0.6 MPa at 25o C in the darkness. For the germination assay, four replicates of 50 seeds were subjected to the same above-described conditions; however, one lot of seeds was modified when there was variation in the refractometric index, whereas the remaining ones were kept in the same solutions until the end of the experiment. All three phases of water uptake were detected under 0 and -0.3 MPa; however, phase II was prolonged under -0.6 MPa and germination was not observed. For 0 and -0.3 MPa, the adopted statistical models consisted of asymptotic (phases I and II) and exponential (phase III) functions, y = a*[1 - b*exp (-c*t) + exp (-d + e*(t - t0)]. For -0.6MPa, only the asymptotic function y = a* [1 - b* exp (-c*t)] was used since there was no evidence of germination. The germination final percentage and speed index were lower under -0.3 MPa, mainly when solutions were not replaced; besides, germination was not detected under -0.6 MPa, with or without solution replacement.
Resumo:
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)