Model selection, estimation and forecasting in VAR models with short-run and long-run restrictions

We study the joint determination of the lag length, the dimension of the cointegrating space and the rank of the matrix of short-run parameters of a vector autoregressive (VAR) model using model selection criteria. We consider model selection criteria which have data-dependent penalties as well as the traditional ones. We suggest a new two-step model selection procedure which is a hybrid of traditional criteria and criteria with data-dependant penalties and we prove its consistency. Our Monte Carlo simulations measure the improvements in forecasting accuracy that can arise from the joint determination of lag-length and rank using our proposed procedure, relative to an unrestricted VAR or a cointegrated VAR estimated by the commonly used procedure of selecting the lag-length only and then testing for cointegration. Two empirical applications forecasting Brazilian inflation and U.S. macroeconomic aggregates growth rates respectively show the usefulness of the model-selection strategy proposed here. The gains in different measures of forecasting accuracy are substantial, especially for short horizons.

Model selection, estimation and forecasting in VAR models with short-run and long-run restrictions

We study the joint determination of the lag length, the dimension of the cointegrating space and the rank of the matrix of short-run parameters of a vector autoregressive (VAR) model using model selection criteria. We consider model selection criteria which have data-dependent penalties as well as the traditional ones. We suggest a new two-step model selection procedure which is a hybrid of traditional criteria and criteria with data-dependant penalties and we prove its consistency. Our Monte Carlo simulations measure the improvements in forecasting accuracy that can arise from the joint determination of lag-length and rank using our proposed procedure, relative to an unrestricted VAR or a cointegrated VAR estimated by the commonly used procedure of selecting the lag-length only and then testing for cointegration. Two empirical applications forecasting Brazilian in ation and U.S. macroeconomic aggregates growth rates respectively show the usefulness of the model-selection strategy proposed here. The gains in di¤erent measures of forecasting accuracy are substantial, especially for short horizons.

Essays on the general equilibrium effects of barriers to trade on economic growth, foreign trade and the location of economic activity in Brazil

This work presents a fully operational interstate CGE model implemented for the Brazilian economy that tries to quantify both the role of barriers to trade on economic growth and foreign trade performance and how the distribution of the economic activity may change as the country opens up to foreign trade. Among the distinctive features embedded in the model, modeling of external scale economies, port efficiency and land-maritime transport costs provides an innovative way of dealing explicitly with theoretical issues related to integrated regional systems. In order to illustrate the role played by the quality of infrastructure and geography on the country‟s foreign and interregional trade performance, a set of simulations is presented where barriers to trade are significantly reduced. The relative importance of trade policy, port efficiency and land-maritime transport costs for the country trade relations and regional growth is then detailed and quantified, considering both short run as well as long run scenarios. A final set of simulations shed some light on the effects of liberal trade policies on regional inequality, where the manufacturing sector in the state of São Paulo, taken as the core of industrial activity in the country, is subjected to different levels of external economies of scale. Short-run core-periphery effects are then traced out suggesting the prevalence of agglomeration forces over diversion forces could rather exacerbate regional inequality as import barriers are removed up to a certain level. Further removals can reverse this balance in favor of diversion forces, implying de-concentration of economic activity. In the long run, factor mobility allows a better characterization of the balance between agglomeration and diversion forces among regions. Regional dispersion effects are then clearly traced-out, suggesting horizontal liberal trade policies to benefit both the poorest regions in the country as well as the state of São Paulo. This long run dispersion pattern, on one hand seems to unravel the fragility of simple theoretical results from recent New Economic Geography models, once they get confronted with more complex spatially heterogeneous (real) systems. On the other hand, it seems to capture the literature‟s main insight: the possible role of horizontal liberal trade policies as diversion forces leading to a more homogeneous pattern of interregional economic growth.

Human growth, biological maturation, motor performance and contextual factors in Madeira children

The central aims of this study were: (1) to construct age- and gender-specific percentiles for motor coordination (MC), (2) to analyze the change, stability, and prediction of MC, (3) to investigate the relationship between motor performance and body fatness, and (4) to evaluate the relationships between skeletal maturation and fundamental motor skills (FMS) and MC. The data collected was from the ‘Healthy Growth of Madeira Children Study’ and from the ‘Madeira Child Growth Study’. In these studies, MC, FMS, skeletal age, growth characteristics, motor performance, physical activity, socioeconomic status, and geographical area were assessed/measured. Generalized additive models for location, scale and shape, mixed between-within subjects ANOVA, multilevel models, and hierarchical regression (blocks) were some of the statistical procedures used in the analyses. Scores on walking backwards and moving sideways improved with age. It was also found that boys performed better than girls on moving sideways. Normal-weight children outperformed obese peers in almost all gross MC tests. Inter-age correlations were calculated to be between 0.15 and 0.60. Age was associated with a better performance in catching, scramble, speed run, standing long jump, balance, and tennis ball throwing. Body mass index was positively associated with scramble and speed run, and negatively related to the standing long jump. Physical activity was negatively associated with scramble. Semi-urban children displayed better catching skills relative to their urban peers. The standardized residual of skeletal age on chronological age (SAsr) and its interaction with stature and/or body mass accounted for the maximum of 7.0% of variance in FMS and MC over that attributed to body size per se. SAsr alone accounted for a maximum of 9.0% variance in FMS and MC over that attributed to body size per se and interactions between SAsr and body size. This study demonstrates the need to promote FMS, MC, motor performance, and physical activity in children.

Association of an insulin-like growth factor 1 gene microsatellite with phenotypic variation and estimated breeding values of growth traits in Canchim cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Growth analysis of sweet pepper cultivated in coconut fiber in a greenhouse

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

Models for genetic evaluation of Nelore cattle mature body weight

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Genetic associations of sexual precocity with growth traits and visual scores of conformation, finishing, and muscling in Nelore cattle

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

Genetic associations between carcass traits measured by real-time ultrasound and scrotal circumference and growth traits in Nelore cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Evaluation of an average numerator relationship matrix model and a Bayesian hierarchical model for growth traits in Nellore cattle with uncertain paternity

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

Comparison of different nonlinear functions to describe Nelore cattle growth

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Estimativas de herdabilidade e tendências genéticas para características de crescimento e reprodutivas em bovinos da raça Nelore: Estimates of heritability and genetic trends for growth and reproduction traits in Nelore cattle

Foram estimados os coeficientes de herdabilidade e a mudança genética para peso à desmama (PD), peso ao sobreano (PS), ganho de peso do nascimento à desmama (GND), ganho de peso da desmama ao sobreano (GDS), perímetro escrotal (PE) e idade ao primeiro parto (IPP) em animais da raça Nelore. Foram utilizados dados de 128.148 animais nascidos entre 1984 e 2006. Os componentes de variância foram estimados pelo método da máxima verossimilhança restrita, e os valores genéticos foram preditos por modelos mistos aplicando-se modelo animal bicaracterística, incluindo peso à desmama em todas as análises. As tendências genéticas foram estimadas pela regressão dos valores genéticos sobre o ano de nascimento dos animais. Os coeficientes de herdabilidade do efeito direto estimados foram de 0,23 (0,07) (PD); 0,24 (0,02) (PS); 0,21 (0,01) (GND); 0,23 (0,01) (GDS); 0,46 (0,02) (PE) e 0,15 (0,01) (IPP). As tendências genéticas diretas estimadas foram de 0,171 (0,01); 0,219 (0,02); 0,186 (0,03) e 0,224 (0,02) kg/ano para PD, PS, GND e GDS, respectivamente, o que representa incrementos de 0,10; 0,08; 0,13 e 0,22% nas médias das mesmas características ao ano, respectivamente. Para o PE e a IPP no período de 1984 a 1995, as tendências genéticas foram nulas, com valores de 0,011 (0,03) cm/ano e -0,003 (0,06) dias/ano, respectivamente. No segundo período considerado (1996 a 2006), as tendências genéticas para PE e IPP foram de 0,069 (0,01) cm/ano e -3,024 (0,04) dias/ano, respectivamente, indicando melhorias consideráveis em tais características. Esses valores sugerem que características produtivas e reprodutivas, quando utilizadas como critério de seleção, proporcionam progresso genético no rebanho, sendo indicadas para seleção de animais da raça Nelore.

Influence of data structure on the estimation of the additive genetic direct and maternal covariance for early growth traits in Nellore cattle

The objective of the present study was to investigate the effect of data structure on estimated genetic parameters and predicted breeding values of direct and maternal genetic effects for weaning weight (WW) and weight gain from birth to weaning (BWG), including or not the genetic covariance between direct and maternal effects. Records of 97,490 Nellore animals born between 1993 and 2006, from the Jacarezinho cattle raising farm, were used. Two different data sets were analyzed: DI_all, which included all available progenies of dams without their own performance; DII_all, which included DI_all + 20% of recorded progenies with maternal phenotypes. Two subsets were obtained from each data set (DI_all and DII_all): DI_1 and DII_1, which included only dams with three or fewer progenies; DI_5 and DII_5, which included only dams with five or more progenies. (Co)variance components and heritabilities were estimated by Bayesian inference through Gibbs sampling using univariate animal models. In general, for the population and traits studied, the proportion of dams with known phenotypic information and the number of progenies per dam influenced direct and maternal heritabilities, as well as the contribution of maternal permanent environmental variance to phenotypic variance. Only small differences were observed in the genetic and environmental parameters when the genetic covariance between direct and maternal effects was set to zero in the data sets studied. Thus, the inclusion or not of the genetic covariance between direct and maternal effects had little effect on the ranking of animals according to their breeding values for WW and BWG. Accurate estimation of genetic correlations between direct and maternal genetic effects depends on the data structure. Thus, this covariance should be set to zero in Nellore data sets in which the proportion of dams with phenotypic information is low, the number of progenies per dam is small, and pedigree relationships are poorly known. (c) 2012 Elsevier B.V. All rights reserved.

Random regression analyses using B-splines functions to model growth from birth to adult age in Canchim cattle

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)