Forecasting accuracy and estimation uncertainty using VAR models with short- and long-term economic restrictions: a Monte-Carlo study

Using vector autoregressive (VAR) models and Monte-Carlo simulation methods we investigate the potential gains for forecasting accuracy and estimation uncertainty of two commonly used restrictions arising from economic relationships. The Örst reduces parameter space by imposing long-term restrictions on the behavior of economic variables as discussed by the literature on cointegration, and the second reduces parameter space by imposing short-term restrictions as discussed by the literature on serial-correlation common features (SCCF). Our simulations cover three important issues on model building, estimation, and forecasting. First, we examine the performance of standard and modiÖed information criteria in choosing lag length for cointegrated VARs with SCCF restrictions. Second, we provide a comparison of forecasting accuracy of Ötted VARs when only cointegration restrictions are imposed and when cointegration and SCCF restrictions are jointly imposed. Third, we propose a new estimation algorithm where short- and long-term restrictions interact to estimate the cointegrating and the cofeature spaces respectively. We have three basic results. First, ignoring SCCF restrictions has a high cost in terms of model selection, because standard information criteria chooses too frequently inconsistent models, with too small a lag length. Criteria selecting lag and rank simultaneously have a superior performance in this case. Second, this translates into a superior forecasting performance of the restricted VECM over the VECM, with important improvements in forecasting accuracy ñreaching more than 100% in extreme cases. Third, the new algorithm proposed here fares very well in terms of parameter estimation, even when we consider the estimation of long-term parameters, opening up the discussion of joint estimation of short- and long-term parameters in VAR models.

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 for a lack of parsimony, as well as the traditional ones. We suggest a new procedure which is a hybrid of traditional criteria and criteria with data-dependant penalties. In order to compute the fit of each model, we propose an iterative procedure to compute the maximum likelihood estimates of parameters of a VAR model with short-run and long-run restrictions. Our Monte Carlo simulations measure the improvements in forecasting accuracy that can arise from the joint determination of lag-length and rank, relative to the commonly used procedure of selecting the lag-length only and then testing for cointegration.

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.

The effects of tax incentives for small firms on employment levels

This paper will examine the effects of tax incentives for small businesses on employment level evaluating a program with this purpose implemented in Brazil in the 1990s. We first develop a theoretical framework which guides both the de nition of the parameters of interest and their identi cation. Selection problems both into the treatment group and into the data sample are tackled by combining fixed effects methods and regression discontinuity design on alternative sub-samples of a longitudinal database of manufacturing firms. The results show that on the one hand the size composition of the treated fi rms may be changed due to the survival of some smaller firms that would have exited had it not been eligible to the program. On the other hand, the treated firms who do not depend on the program to survive do employ more workers.

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.

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 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. A Monte Carlo study explores the finite sample performance of this procedure and evaluates the forecasting accuracy of models selected by this procedure. Two empirical applications confirm the usefulness of the model selection procedure proposed here for forecasting.

A Common-feature approach for testing present-value restrictions with financial data

It is well known that cointegration between the level of two variables (labeled Yt and yt in this paper) is a necessary condition to assess the empirical validity of a present-value model (PV and PVM, respectively, hereafter) linking them. The work on cointegration has been so prevalent that it is often overlooked that another necessary condition for the PVM to hold is that the forecast error entailed by the model is orthogonal to the past. The basis of this result is the use of rational expectations in forecasting future values of variables in the PVM. If this condition fails, the present-value equation will not be valid, since it will contain an additional term capturing the (non-zero) conditional expected value of future error terms. Our article has a few novel contributions, but two stand out. First, in testing for PVMs, we advise to split the restrictions implied by PV relationships into orthogonality conditions (or reduced rank restrictions) before additional tests on the value of parameters. We show that PV relationships entail a weak-form common feature relationship as in Hecq, Palm, and Urbain (2006) and in Athanasopoulos, Guillén, Issler and Vahid (2011) and also a polynomial serial-correlation common feature relationship as in Cubadda and Hecq (2001), which represent restrictions on dynamic models which allow several tests for the existence of PV relationships to be used. Because these relationships occur mostly with nancial data, we propose tests based on generalized method of moment (GMM) estimates, where it is straightforward to propose robust tests in the presence of heteroskedasticity. We also propose a robust Wald test developed to investigate the presence of reduced rank models. Their performance is evaluated in a Monte-Carlo exercise. Second, in the context of asset pricing, we propose applying a permanent-transitory (PT) decomposition based on Beveridge and Nelson (1981), which focus on extracting the long-run component of asset prices, a key concept in modern nancial theory as discussed in Alvarez and Jermann (2005), Hansen and Scheinkman (2009), and Nieuwerburgh, Lustig, Verdelhan (2010). Here again we can exploit the results developed in the common cycle literature to easily extract permament and transitory components under both long and also short-run restrictions. The techniques discussed herein are applied to long span annual data on long- and short-term interest rates and on price and dividend for the U.S. economy. In both applications we do not reject the existence of a common cyclical feature vector linking these two series. Extracting the long-run component shows the usefulness of our approach and highlights the presence of asset-pricing bubbles.

The effects of adult literacy on earnings and employment

This paper provides evidence of the effects of adult literacy on individuals’ income and employability in Brazil based on information obtained from the monthly employment survey (PME). The OLS results indicate that after controlling for observable characteristics, there is a 21.25% increase in wages for individuals who become literate; however, there is no significant impact on employability. Moreover, the findings show an 8.1% increase in the probability of being employed in the formal sector. We also explore the longitudinal structure of the dataset to control for unobservable fixed characteristics of individuals. The fixed-effects estimators show smaller effects compared to the OLS estimators. We find that literacy has a 4.4% effect on wages and a 4.3% impact on the probability of being formally employed. The effects are significantly different from zero.

Antecedentes à transição de carreira na área de tecnologia da informação

A falta de profissionais com perfil e qualificação em tecnologia da informação (TI) é uma dificuldade enfrentada pelas empresas em geral, as quais investem crescentemente em TI e cada vez mais são dependentes e influenciadas pela tecnologia. Além dessa questão, observa-se que apesar das boas oportunidades de emprego no setor, a evasão nos cursos superiores de TI tem atingido patamares altíssimos, agravando ainda mais o problema da escassez por talentos qualificados. Assim, esta pesquisa estuda a migração dos profissionais de TI para outras áreas, fenômeno denominado turnaway, problema que agrava ainda mais a situação em que se encontra o setor de tecnologia da informação no mercado brasileiro, requerendo uma solução a curto prazo e merecendo uma exploração e discussão em profundidade. O objetivo principal deste estudo é, portanto, identificar as principais razões que explicam a intenção dos profissionais de TI em abandonar a área. Assim, foi realizada uma pesquisa explanatória, por meio de pesquisa bibliográfica e investigação empírica, aplicando-se questionários disponibilizados eletronicamente a profissionais de TI de diferentes empresas e áreas de atuação. A amostra utilizada teve 323 respondentes e os dados obtidos foram analisados estatisticamente via modelagem de equações estruturais. Como resultado, esta pesquisa mostrou que a transição de carreira na área de tecnologia da informação está intimamente associada ao dinamismo natural da área, às condições de trabalho que geram fadiga física e mental, e às restrições de crescimento profissional na área técnica, levando os profissionais de TI a uma insatisfação com a área que os faz buscar capacitação gerencial e novas experiências de trabalho, de modo a ampliar sua rede de relacionamento interpessoal e abrir oportunidades em diferentes campos de trabalho, possibilitando, desta forma, a migração dos mesmos para outras áreas que oferecem melhores condições de trabalho, maior reconhecimento e possibilidade de crescimento profissional.

Forecasting multivariate time series under present-value-model short- and long-run co-movement restrictions

It is well known that cointegration between the level of two variables (e.g. prices and dividends) is a necessary condition to assess the empirical validity of a present-value model (PVM) linking them. The work on cointegration,namelyon long-run co-movements, has been so prevalent that it is often over-looked that another necessary condition for the PVM to hold is that the forecast error entailed by the model is orthogonal to the past. This amounts to investigate whether short-run co-movememts steming from common cyclical feature restrictions are also present in such a system. In this paper we test for the presence of such co-movement on long- and short-term interest rates and on price and dividend for the U.S. economy. We focuss on the potential improvement in forecasting accuracies when imposing those two types of restrictions coming from economic theory.

Uma técnica para modelagem de cenários consistentes na previsão da demanda por energia elétrica

As técnicas qualitativas disponiveis para a modelagem de cenários têm sido reconhecidas pela extrema limitação, evidenciada no principio das atividades do processo, como a fase inicial de concepção. As principais restrições têm sido: • inexistência de uma ferramenta que teste a consistência estrutural interna do modelo, ou pela utilização de relações econômicas com fundamentação teórica mas sem interface perfeita com o ambiente, ou pela adoção de variações binárias para testes de validação; • fixação "a priori" dos possíveis cenários, geralmente classificados sob três adjetivos - otimista, mais provável e pessimista - enviesados exatamente pelos atributos das pessoas que fornecem esta informação. o trabalho trata da utilização de uma ferramenta para a interação entre uma técnica que auxilia a geração de modelos, suportada pela lógica relacional com variações a quatro valores e expectativas fundamentadas no conhecimento do decisor acerca do mundo real. Tem em vista a construção de um sistema qualitativo de previsão exploratória, no qual os cenários são obtidos por procedimento essencialmente intuitivo e descritivos, para a demanda regional por eletricidade. Este tipo de abordagem - apresentada por J. Gershuny - visa principalmente ao fornecimento de suporte metodológico para a consistência dos cenários gerados qualitativamente. Desenvolvimento e estruturação do modelo são realizados em etapas, partindo-se de uma relação simples e prosseguindo com a inclusão de variáveis e efeitos que melhoram a explicação do modelo. o trabalho apresenta um conjunto de relações para a demanda regional de eletricidade nos principais setores de consumo residencial, comercial e industrial bem como os cenários resultantes das variações mais prováveis das suas componentes exógenas. Ao final conclui-se que esta técnica é útil em modelos que: • incluem variáveis sociais relevantes e de dificil mensuração; • acreditam na importância da consistência externa entre os resultados gerados pelo modelo e aqueles esperados para a tomada de decisões; • atribuem ao decisor a responsabilidade de compreender a fundamentação da estrutura conceitual do modelo. Adotado este procedimento, o autor aqui recomenda que o modelo seja validado através de um procedimento iterativo de ajustes com a participação do decisor. As técnicas quantitativas poderão ser adotadas em seguida, tendo o modelo como elemento de consistência.

The effects of small firm tax incentives on employment levels

This paper aims to evaluate the impact on employment growth of a tax incentive program targeting Brazilian manufacturing small businesses (SIMPLES). This evaluation is conducted for two distinct periods: for the year 1997, when the program was first implemented, and for the year 1999, when the eligibility rule was modified to allow the eligibility of a broader group of firms. The evaluation takes into account two distinct channels through which the charted effects operate. The first is the employment variation in the firms that became eligible for the incentives, and the second is the change in the survival probability experienced by the same group of firms. Moreover, each of these channels can be activated either by the tax reduction dimension of the program or by its dimension of red tape simplification. Our results identify positive effects on employment growth for the tax incentive program only in the dimension of red tape simplification and its effects on the 1997 sample.

Forecasting Multivariate Time Series under Present-Value-Model Short- and Long-run Co-movement Restrictions

This paper has two original contributions. First, we show that the present value model (PVM hereafter), which has a wide application in macroeconomics and fi nance, entails common cyclical feature restrictions in the dynamics of the vector error-correction representation (Vahid and Engle, 1993); something that has been already investigated in that VECM context by Johansen and Swensen (1999, 2011) but has not been discussed before with this new emphasis. We also provide the present value reduced rank constraints to be tested within the log-linear model. Our second contribution relates to forecasting time series that are subject to those long and short-run reduced rank restrictions. The reason why appropriate common cyclical feature restrictions might improve forecasting is because it finds natural exclusion restrictions preventing the estimation of useless parameters, which would otherwise contribute to the increase of forecast variance with no expected reduction in bias. We applied the techniques discussed in this paper to data known to be subject to present value restrictions, i.e. the online series maintained and up-dated by Shiller. We focus on three different data sets. The fi rst includes the levels of interest rates with long and short maturities, the second includes the level of real price and dividend for the S&P composite index, and the third includes the logarithmic transformation of prices and dividends. Our exhaustive investigation of several different multivariate models reveals that better forecasts can be achieved when restrictions are applied to them. Moreover, imposing short-run restrictions produce forecast winners 70% of the time for target variables of PVMs and 63.33% of the time when all variables in the system are considered.

The effects of openness on industrial employment in Brazil

Este artigo tem dois objetivos principais. Primeiramente, apresentamos as pnnClpms evidências de que a baixa qualidade do emprego é o maior problema do mercado de trabalho brasileiro. Mostra-se que o país tem absorvido um crescimento da oferta de trabalho significativo ao longo dos últimos anos sem registrar um aumento da taxa de desemprego. No entanto, os postos de trabalho no Brasil são, em média, extremamente precários. Em grande medida, a precariedade do emprego no Brasil está relacionada à alta rotatividade da mão-de-obra, que desincentiva o investimento em treinamento, impedindo o crescimento da produtivid::;de do trabalho. De acordo com os indicadores passíveis de comparação internacional, o Brasil apresenta uma das maiores taxas de rotatividade do mundo. Em segundo lugar, estuda-se a evolução recente do emprego industrial, uma vez que o setor industrial está tradicionalmente associado à geração de bons empregos no Brasil. Mostra-se que o nível de emprego industrial tem se reduzido de forma praticamente contínua desde o início desta década. A estimação de um modelo de ajustamento parcial do emprego nos permite explicar este fenômeno. Mudanças estruturais significativas na elasticidade custo salarial do emprego e no coeficiente de tendência são detectadas a partir do início da década de 90. Um simples modelo teórico é usado de forma a interpretar estas mudanças estruturais como a resposta ótima das empresas industriais ao ambiente de maior competição externa, devido à abertura comercial. Isto, junto com o uso crescente de tecnologias poupadoras de mão-de-obra, são suficientes para explicar a brutal queda do emprego industrial no Brasil ao longo dos últimos seis anos.