Estimação de regressões aditivas via backfitting e integração marginal: performance em pequenas amostras

Nesta dissertação realizou-se um experimento de Monte Carlo para re- velar algumas características das distribuições em amostras finitas dos estimadores Backfitting (B) e de Integração Marginal(MI) para uma regressão aditiva bivariada. Está-se particularmente interessado em fornecer alguma evidência de como os diferentes métodos de seleção da janela hn, tais co- mo os métodos plug-in, impactam as propriedades em pequenas amostras dos estimadores. Está-se interessado, também, em fornecer evidência do comportamento de diferentes estimadores de hn relativamente a seqüência ótima de hn que minimiza uma função perda escolhida. O impacto de ignorar a dependência entre os regressores na estimação da janela é tam- bém investigado. Esta é uma prática comum e deve ter impacto sobre o desempenho dos estimadores. Além disso, não há nenhuma rotina atual- mente disponível nos pacotes estatísticos/econométricos para a estimação de regressões aditivas via os métodos de Backfitting e Integração Marginal. É um dos objetivos a criação de rotinas em Gauss para a implementação prática destes estimadores. Por fim, diferentemente do que ocorre atual- mente, quando a utilização dos estimadores-B e MI é feita de maneira completamente ad-hoc, há o objetivo de fornecer a usuários informação que permita uma escolha mais objetiva de qual estimador usar quando se está trabalhando com uma amostra finita.

Mensuração de Capacidade Tecnológica no Contexto de Industrialização Recente: Uma Breve Reflexão Crítica Sobre Taxonomias e Evidências de Pesquisas Recentes

This dissertation aims at examining empirical evidences obtained in the light of taxonomies and strategies for measuring firms technological capabilities and innovation in the context of developing countries, motivated by the fact that debates and studies directed to innovation has been intensified, for the last thirty years, by the recognition of its vital and growing importance to the technological, economic, competitive and industrial development of firms and countries. Two main tendencies can be identified on this debate. At one side, it¿s the literature related to the developed countries logic, whose companies are, in majority, positioned at the technological frontier, characterized by the domain of innovative advanced capabilities, directed to its sustaining, deepening and renewal. At the other side, there are the perspectives directed to the developing countries reality, where there is a prevalence of companies with deficiency of resources, still in process of accumulating basic and intermediate technological capabilities, with characteristics and technological development trajectories distinct or even reverse from those of developing countries. From this last tradition of studies, the measuring approaches based in C&T indicators and in types and levels of technological capabilities stand out. The first offers a macro level, aggregated perspective, through the analysis of a representative sample of firms, seeking to the generation of internationally comparable data, without addressing the intraorganizational specificities and nuances of the paths of technological accumulation developed by the firms, using, mostly, R&D statistics, patents, individual qualifications, indicators that carry their own limitations. On the other hand, studies that examine types and levels of technological capabilities are scarce, usually directed to a small sample of firms and/or industrial sectors. Therefore, in the light of the focus and potentialities of each of the perspectives, this scenario exposes a lack of studies that examine, in a parallel and complementary way, both types of strategies, seeking to offer more realistic, consistent and concrete information about the technological reality of developing countries. In order to close this gap, this dissertation examines (i) strategies of innovation measurement in the contexts of developing countries based on traditional approaches and C&T indicators, represented by four innovation surveys - ECIB, PINTEC, PAEP and EAI, and, (ii) from the perspective of technological capabilities as an intrinsic resource of the firm, the development of which occurs in a cumulative way and based on learning, presents and extracts generalizations of empirical applications of a metric that identifies types and levels of technological capabilities, through a dynamic and intra-firm perspective. The exam of the empirical evidences of the two approaches showed what each one of the metrics are capable to offer and the way they can contribute to the generation of information that reflect the technological development of specific industrial sectors in developing countries. In spite of the fact that the focus, objective, perspective, inclusion, scope and lens used are substantially distinct, generating, on a side, an aggregated view, and of other, an intra-sector, intra-organizational and specific view, the results suggest that the use of one doesn't implicate discarding or abdicating the other. On the contrary, using both in a complementary way means the generation of more complete, rich and relevant evidences and analysis that offer a realistic notion of the industrial development and contribute in a more direct way to the design of corporate strategies and government policies, including those directed to the macro level aspects just as those more specific and focused, designed to increment and foment firms in-house innovative efforts.

Acumulação tecnológica e aprimoramento de performance competitiva: evidências de diferenças e similaridades e médias empresas do setor metal-mecânico no estado do rio de janeiro

The main objective of this dissertation is to examine the implications of technological capacities in the improvement of technical performance indexes, specifically at the company level. These relationships were examined in a small sample of metal-working enterprises in the state of Rio de Janeiro (1960 to 2006). Although diverse studies on technological competences have been carried out in the last twenty years, a gap in empirical studies still exist that correlate the performance of companies in the context of developing countries, especially in Brazil. Aiming to contribute to a reduction of these gaps, this dissertation examines the questions by the light of available models in literature, which opting themselves to using operational indexes of companies. For drawing the accumulation of technological competences in this study, the metric proposal by Figueiredo (2000) shall be used indicating the levels of technological qualification in process, product, and equipment functions. The empirical evidence examined in this dissertation is both qualitative and quantitative in nature and were collected, first hand, through extensive field research involving informal interviews, meetings, direct-site observation and document analysis. In relation to the results, the evidence suggests that: - In terms of technological accumulation, a company reached Level 5 of technological capacity in process and organization of production as well as product and equipment. Three companies obtained Level 4 in the function process function while two others had reached the same technological level in the functions of product and equipment. Two companies had reached Level 3 in the product and equipment functions and one remained this level in the function of process; - In terms of the rate of accumulation of technological capacities, the observed companies had reached Level 4 needs 29 years in process function, 32 years in product function and 29 years in equipment function; - In terms of improvement performance pointers, a company which reached Level 5 of technological capacity improved in 70% of its indicators of performance, while the company that had achieved Level 4 had raised its pointers 60% and the other companies had gotten improved in the order of 40%. It was evidenced that the majority of the pointers of the companies with higher levels of technological capacities had obtained better performance. This dissertation contributes to advancing the strategic management of companies in metal-working segment to understanding internal accumulation of technological capacity and indicators of performance especially in the field of empirical context studied. This information offers management examples of how to improve competitive performance through the accumulation of technological capacities in the process, product and equipment functions.

Infrastructure and productivity in Latin America: is there a relationship in the long run?

This article analyses the relationship between infrastructure and total factor productivity (TFP) in the four major Latin American economies: Argentina, Brazil, Chile and Mexico. We hypothesise that an increase in infrastructure has an indirect effect on long-term economic growth by raising productivity. To assess this theory, we use the traditional Johansen methodology for testing the cointegration between TFP and physical measures of infrastructure stock, such as energy, roads, and telephones. We then apply the Lütkepohl, Saikkonen and Trenkler Test, which considers a possible level shift in the series and has better small sample properties, to the same data set and compare the two tests. The results do not support a robust long-term relationship between the series; we do not find strong evidence that cuts in infrastructure investment in some Latin American countries were the main reason for the fall in TFP during the 1970s and 1980s.

Optimal IV estimation of systems with stochastic regressors and var disturbances with applications to dynamic systems

This paper considers the general problem of Feasible Generalized Least Squares Instrumental Variables (FG LS IV) estimation using optimal instruments. First we summarize the sufficient conditions for the FG LS IV estimator to be asymptotic ally equivalent to an optimal G LS IV estimator. Then we specialize to stationary dynamic systems with stationary VAR errors, and use the sufficient conditions to derive new moment conditions for these models. These moment conditions produce useful IVs from the lagged endogenous variables, despite the correlation between errors and endogenous variables. This use of the information contained in the lagged endogenous variables expands the class of IV estimators under consideration and there by potentially improves both asymptotic and small-sample efficiency of the optimal IV estimator in the class. Some Monte Carlo experiments compare the new methods with those of Hatanaka [1976]. For the DG P used in the Monte Carlo experiments, asymptotic efficiency is strictly improved by the new IVs, and experimental small-sample efficiency is improved as well.

Estimation of DSGE Models: A Monte Carlo Analysis

Neste trabalho investigamos as propriedades em pequena amostra e a robustez das estimativas dos parâmetros de modelos DSGE. Tomamos o modelo de Smets and Wouters (2007) como base e avaliamos a performance de dois procedimentos de estimação: Método dos Momentos Simulados (MMS) e Máxima Verossimilhança (MV). Examinamos a distribuição empírica das estimativas dos parâmetros e sua implicação para as análises de impulso-resposta e decomposição de variância nos casos de especificação correta e má especificação. Nossos resultados apontam para um desempenho ruim de MMS e alguns padrões de viés nas análises de impulso-resposta e decomposição de variância com estimativas de MV nos casos de má especificação considerados.

Essays on Spatial Econometrics

Esta dissertação concentra-se nos processos estocásticos espaciais definidos em um reticulado, os chamados modelos do tipo Cliff & Ord. Minha contribuição nesta tese consiste em utilizar aproximações de Edgeworth e saddlepoint para investigar as propriedades em amostras finitas do teste para detectar a presença de dependência espacial em modelos SAR (autoregressivo espacial), e propor uma nova classe de modelos econométricos espaciais na qual os parâmetros que afetam a estrutura da média são distintos dos parâmetros presentes na estrutura da variância do processo. Isto permite uma interpretação mais clara dos parâmetros do modelo, além de generalizar uma proposta de taxonomia feita por Anselin (2003). Eu proponho um estimador para os parâmetros do modelo e derivo a distribuição assintótica do estimador. O modelo sugerido na dissertação fornece uma interpretação interessante ao modelo SARAR, bastante comum na literatura. A investigação das propriedades em amostras finitas dos testes expande com relação a literatura permitindo que a matriz de vizinhança do processo espacial seja uma função não-linear do parâmetro de dependência espacial. A utilização de aproximações ao invés de simulações (mais comum na literatura), permite uma maneira fácil de comparar as propriedades dos testes com diferentes matrizes de vizinhança e corrigir o tamanho ao comparar a potência dos testes. Eu obtenho teste invariante ótimo que é também localmente uniformemente mais potente (LUMPI). Construo o envelope de potência para o teste LUMPI e mostro que ele é virtualmente UMP, pois a potência do teste está muito próxima ao envelope (considerando as estruturas espaciais definidas na dissertação). Eu sugiro um procedimento prático para construir um teste que tem boa potência em uma gama de situações onde talvez o teste LUMPI não tenha boas propriedades. Eu concluo que a potência do teste aumenta com o tamanho da amostra e com o parâmetro de dependência espacial (o que está de acordo com a literatura). Entretanto, disputo a visão consensual que a potência do teste diminui a medida que a matriz de vizinhança fica mais densa. Isto reflete um erro de medida comum na literatura, pois a distância estatística entre a hipótese nula e a alternativa varia muito com a estrutura da matriz. Fazendo a correção, concluo que a potência do teste aumenta com a distância da alternativa à nula, como esperado.

A class of improved heteroskedasticity-consistent covariance matrix estimators

The heteroskedasticity-consistent covariance matrix estimator proposed by White (1980), also known as HC0, is commonly used in practical applications and is implemented into a number of statistical software. Cribari–Neto, Ferrari & Cordeiro (2000) have developed a bias-adjustment scheme that delivers bias-corrected White estimators. There are several variants of the original White estimator that also commonly used by practitioners. These include the HC1, HC2 and HC3 estimators, which have proven to have superior small-sample behavior relative to White’s estimator. This paper defines a general bias-correction mechamism that can be applied not only to White’s estimator, but to variants of this estimator as well, such as HC1, HC2 and HC3. Numerical evidence on the usefulness of the proposed corrections is also presented. Overall, the results favor the sequence of improved HC2 estimators.

Testing for super-exogeneity in the presence of common deterministic shifts

This paper introduces the concept of common deterministic shifts (CDS). This concept is simple, intuitive and relates to the common structure of shifts or policy interventions. We propose a Reduced Rank technique to investigate the presence of CDS. The proposed testing procedure has standard asymptotics and good small-sample properties. We further link the concept of CDS to that of superexogeneity. It is shown that CDS tests can be constructed which allow to test for super-exogeneity. The Monte Carlo evidence indicates that the CDS test for super-exogeneity dominates testing procedures proposed in the literature.

Coordenação no sistema agroindustrial da borracha natural : um estudo das relações entre produtores rurais e usinas beneficiadoras paulistas

O enfoque da Nova Economia Institucional é utilizado no estudo de sistemas agroindustriais brasileiros, mas ainda há poucos trabalhos sobre as relações entre produtores rurais e indústrias processadoras. O objetivo deste estudo é aferir o alinhamento das características das transações com os modos de governança adotados na comercialização de borracha natural entre produtores rurais e indústrias de beneficiamento primário. Busca-se confrontar os resultados com as previsões da teoria da Economia dos Custos de Transação, que prevê a adoção da governança mais eficiente, contingenciada ao ambiente transacional. Esta pesquisa utiliza um enfoque pioneiro para o setor. A primeira parte consiste na exploração qualitativa das transações entre produtores rurais e usinas beneficiadoras e na descrição dos elementos que compõe o sistema agroindustrial da borracha natural no Estado de São Paulo. Os resultados desta etapa são utilizados para refinar as hipóteses da etapa quantitativa, que relacionam os modos de governança adotados aos investimentos em ativos específicos, como o plantio de seringueiras, à frequência, à incerteza e à assistência técnica associadas à transação. Os resultados, apesar das limitações devido ao tamanho pequeno da amostra, sugerem que a quantidade de borracha comercializada influi positivamente na adoção de modos de governança mais coordenados e que a recorrência das transações provavelmente está associada a contratos relacionais. A hipótese da endogeneidade é rejeitada.

New method for determination of (E)resveratrol in wine based on microextraction using packed sorbent and ultra-performance liquid chromatography

An ultra-fast and improved analytical methodology based on microextraction by packed sorbent (MEPS) combined with ultra-performance LC (UPLC) was developed and validated for determination of (E)-resveratrol in wines. Important factors affecting the performance of MEPS such as the type of sorbent material (C2, C8, C18, SIL, and M1), number of extraction cycles, and sample volume were studied. The optimal conditions of MEPS extraction were obtained using C8 sorbent and small sample volumes (50–250mL) in one extraction cycle (extract–discard) and in a short time period (about 3 min for the entire sample preparation step). (E)-Resveratrol was eluted by 1 250mL of the mixture containing 95% methanol and 5% water, and the separation was carried out on a highstrength silica HSS T3 analytical column (100 mm 2.1 mm, 1.8mm particle size) using a binary mobile phase composed of aqueous 0.1% formic acid (eluent A) and methanol (eluent B) in the gradient elution mode (10 min of total analysis). The method was fully validated in terms of linearity, detection (LOD) and quantification (LOQ) limits, extraction yield, accuracy, and inter/intra-day precision, using a Madeira wine sample (ET) spiked with (E)-resveratrol at concentration levels ranging from 5 to 60mg/mL. Validation experiments revealed very good recovery rate of 9575.8% RSD, good linearity with r2 values 40.999 within the established concentration range, excellent repeatability (0.52%), and reproducibility (1.67%) values (expressed as RSD), thus demonstrating the robustness and accuracy of the MEPSC8/UPLC-photodiode array (PDA) method. The LOD of the method was 0.21mg/mL, whereas the LOQ was 0.68mg/mL. The validated methodology was applied to 30 commercial wines (24 red wines and six white wines) from different grape varieties, vintages, and regions. On the basis of the analytical validation, the MEPSC8/UPLC-PDA methodology shows to be an improved, sensitive, and ultra-fast approach for determination of (E)-resveratrol in wines with high resolving power within 6 min.

A sensitive microextraction by packed sorbent-based methodology combined with ultra-high pressure liquid chromatography as a powerful technique for analysis of biologically active flavonols in wines

A new approach based on microextraction by packed sorbent (MEPS) and reversed-phase high-throughput ultra high pressure liquid chromatography (UHPLC) method that uses a gradient elution and diode array detection to quantitate three biologically active flavonols in wines, myricetin, quercetin, and kaempferol, is described. In addition to performing routine experiments to establish the validity of the assay to internationally accepted criteria (selectivity, linearity, sensitivity, precision, accuracy), experiments are included to assess the effect of the important experimental parameters such as the type of sorbent material (C2, C8, C18, SIL, and C8/SCX), number of extraction cycles (extract-discard), elution volume, sample volume, and ethanol content, on the MEPS performance. The optimal conditions of MEPS extraction were obtained using C8 sorbent and small sample volumes (250 μL) in five extraction cycle and in a short time period (about 5 min for the entire sample preparation step). Under optimized conditions, excellent linearity View the MathML source(Rvalues2>0.9963), limits of detection of 0.006 μg mL−1 (quercetin) to 0.013 μg mL−1 (myricetin) and precision within 0.5–3.1% were observed for the target flavonols. The average recoveries of myricetin, quercetin and kaempferol for real samples were 83.0–97.7% with relative standard deviation (RSD, %) lower than 1.6%. The results obtained showed that the most abundant flavonol in the analyzed samples was myricetin (5.8 ± 3.7 μg mL−1). Quercetin (0.97 ± 0.41 μg mL−1) and kaempferol (0.66 ± 0.24 μg mL−1) were found in a lower concentration. The optimized MEPSC8 method was compared with a reverse-phase solid-phase extraction (SPE) procedure using as sorbent a macroporous copolymer made from a balanced ratio of two monomers, the lipophilic divinylbenzene and the hydrophilic N-vinylpyrrolidone (Oasis HLB) were used as reference. MEPSC8 approach offers an attractive alternative for analysis of flavonols in wines, providing a number of advantages including highest extraction efficiency (from 85.9 ± 0.9% to 92.1 ± 0.5%) in the shortest extraction time with low solvent consumption, fast sample throughput, more environmentally friendly and easy to perform.

Development of a novel microextraction by packed sorbent-based approach followed by ultrahigh pressure liquid chromatography as a powerful technique for quantification phenolic constituents of biological interest in wines

A novel analytical approach, based on a miniaturized extraction technique, the microextraction by packed sorbent (MEPS), followed by ultrahigh pressure liquid chromatography (UHPLC) separation combined with a photodiode array (PDA) detection, has been developed and validated for the quantitative determination of sixteen biologically active phenolic constituents of wine. In addition to performing routine experiments to establish the validity of the assay to internationally accepted criteria (linearity, sensitivity, selectivity, precision, accuracy), experiments are included to assess the effect of the important experimental parameters on the MEPS performance such as the type of sorbent material (C2, C8, C18, SIL, and M1), number of extraction cycles (extract-discard), elution volume, sample volume, and ethanol content, were studied. The optimal conditions of MEPS extraction were obtained using C8 sorbent and small sample volumes (250 μL) in five extraction cycle and in a short time period (about 5 min for the entire sample preparation step). The wine bioactive phenolics were eluted by 250 μL of the mixture containing 95% methanol and 5% water, and the separation was carried out on a HSS T3 analytical column (100 mm × 2.1 mm, 1.8 μm particle size) using a binary mobile phase composed of aqueous 0.1% formic acid (eluent A) and methanol (eluent B) in the gradient elution mode (10 min of total analysis). The method gave satisfactory results in terms of linearity with r2-values > 0.9986 within the established concentration range. The LOD varied from 85 ng mL−1 (ferulic acid) to 0.32 μg mL−1 ((+)-catechin), whereas the LOQ values from 0.028 μg mL−1 (ferulic acid) to 1.08 μg mL−1 ((+)-catechin). Typical recoveries ranged between 81.1 and 99.6% for red wines and between 77.1 and 99.3% for white wines, with relative standard deviations (RSD) no larger than 10%. The extraction yields of the MEPSC8/UHPLC–PDA methodology were found between 78.1 (syringic acid) and 99.6% (o-coumaric acid) for red wines and between 76.2 and 99.1% for white wines. The inter-day precision, expressed as the relative standard deviation (RSD%), varied between 0.2% (p-coumaric and o-coumaric acids) and 7.5% (gentisic acid) while the intra-day precision between 0.2% (o-coumaric and cinnamic acids) and 4.7% (gallic acid and (−)-epicatechin). On the basis of analytical validation, it is shown that the MEPSC8/UHPLC–PDA methodology proves to be an improved, reliable, and ultra-fast approach for wine bioactive phenolics analysis, because of its capability for determining simultaneously in a single chromatographic run several bioactive metabolites with high sensitivity, selectivity and resolving power within only 10 min. Preliminary studies have been carried out on 34 real whole wine samples, in order to assess the performance of the described procedure. The new approach offers decreased sample preparation and analysis time, and moreover is cheaper, more environmentally friendly and easier to perform as compared to traditional methodologies.

Aspectos da biologia reprodutiva de Eretmochelys imbricata (testudines, cheloniidae) no litoral sul do Rio Grande do Norte, Brasil

Female hawksbill turtles (Eretmochelys imbricata) nesting along the southeastcoastline of Rio Grande do Norte State, Brazil (6º13'40"S, 35º03'05"W) were captured and weighed during the four months from January to April 2007, in the course of the annual egglaying season, which extended from 06 rd November 2006 to 30 rd May 2007. In all, 99 weight measurements were performed. On first contact the females exhibited an average post-oviposition weight of 79.1 kg (range 56.2-98.9 kg, SD = 10.9 kg, n = 44 females). Those individuals which were subsequently recaptured showed a mean weight loss of 1.7 kg (range 0.7-4.5 kg, SD = 1.0 kg, n = 39 sets of measurements on 20 females) in the interval between two consecutive post-ovipositions, separated by a maximum time interval of 17 days. In the cases where the female aborted the nesting process, the pre-oviposition weight was measured. The clutch weight, that is to say, the weight loss between consecutive pre-oviposition and post-oviposition measurements (separated by a maximum time interval of 3 days), was found to be 5.2 kg (range 4.3-6.0 kg, SD = 0.9 kg, n = 6 sets of measurements). This value is significantly higher (t-test, p<0.001) than the loss between two consecutive post-oviposition measurements with the same female. The mean recovery in body weight, that is to say, the average gain in weight between successive post-oviposition and pre-oviposition captures of the same individual (separated by a time interval of 12 to 17 days), was found to be 3.0 kg (range 1.9-4.3 kg, SD = 1.0 kg, n = 4 sets of measurements) Although the small sample size makes it unwise to generalise, the recovery in body weight was found to be always significantly lower (t-test, p<0.005) than the clutch weight. This fact is in agreement with the observed weight loss tendency throughout the breeding season for this species. Considering the clutch weight and the internidal recovery in body weight we found that the total weight loss of the adult hawksbill females after three to five nesting events varied from 10.4% (range 8.7-11.9%, SD = 1.6%, n = 3) to 14.1% (range 11.8-15.4%, SD = 1.3%, n = 6) in relation to their initial pre-oviposition weight. If there were no body weight recovery during the internesting interval we estimate that a female that nests three to five times in the course of the season would lose from 19% to 31% of its initial weight. We emphasise that our clutch weight estimate was performed by weighing the females and not by multiplying the number of eggs in the nest by their average unit weight. In this way, our measurements take into account the loss of liquid during the oviposition. Despite the unequivocal evidence of body weight recovery during the internidal interval, it is not clear if the cause of this process is rehydration or feeding

Proposta de Intervenção para Auxiliar a Reabilitação Motora e Cognitiva de Pacientes com Acidente Vascular Cerebral

Stroke is the leading cause of combined motor and cognitive disability worldwide. The rehabilitation of stroke patients is mostly directed towards motor recovery through the training of the affected member under supervision of a Physical Therapist. In the present study we introduce a new approach for both cognitive and motor therapy, which relies on motor imagery of the upper limbs and working memory training. This therapy should be utilized as an adjuvant to physical therapy. Ten individuals (5 men and 5 women) were selected for the pilot study, all of them in the acute phase of the first ischemic stroke episode. The control group had 5 individuals who were submitted to physical therapy only, whilst the other 5 patients in the experimental group also performed the cognitive and motor training with a video game specially built for this study. Two patients left the experimental group before the end. Total training lasted for 9 weeks, 2 times a week, for half an hour. Patients reported they enjoyed playing the game, even though it required a lot of mental effort, according to them. Plus, they considered it had a beneficial influence in their activities of daily living. No side effects were reported. Preliminary results suggest there is a difference between groups in cognitive and upper limb motor evaluation following the intervention. It is important to notice that our conclusions are limited due the small sample number. Overall, this work is supported by other studies in literature focused in rehabilitation with motor imagery and working memory and indicate a continuity of the research, increasing total training hours