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 long run economic impact of AIDS

This paper studies the long-run impact of HIV/AIDS on per capita income and education. We introduce a channel from HIV/AIDS to long-run income that has been overlooked by the literature, the reduction of the incentives to study due to shorter expected longevity. We work with a continuous time overlapping generations mo deI in which life cycle features of savings and education decision play key roles. The simulations predict that the most affected countries in Sub-Saharan Africa will be in the future, on average, a quarter poorer than they would be without AIDS, due only to the direct (human capital reduction) and indirect (decline in savings and investment) effects of life-expectancy reductions. Schooling will decline on average by half. These findings are well above previous results in the literature and indicate that, as pessimistic as they may be, at least in economic terms the worst could be yet to come.

On the long run effects of barriers to trade

We study the macroeconomic effects of international trade policy by integrating a Hecksher-Ohlin trade model into an optimal-growth framework. The model predicts that a more open economy will have higher factor productivity. Furthermore, there is a "selective development trap," an additional steady state with low income, to which countries may or may not converge, depending on policy. Income at the development trap falls as trade barriers increase. Hence, cross-country differences in barriers to trade may help explain the dispersion of per-capita income observed across countries. The effects are quantified and we show that protectionism can explain a relevant fraction of TFP and long-run income differentials across countries.

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.

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.

The long-run properties of a dynamic Mirrlees' model with aggregate shocks

Nós abordamos a existência de distribuições estacionárias de promessas de utilidade em um modelo Mirrlees dinâmico quando o governo tem record keeping imperfeito e a economia é sujeita a choques agregados. Quando esses choques são iid, provamos a existência de um estado estacionário não degenerado e caracterizamos parcialmente as alocações estacionárias. Mostramos que a proporção do consumo agregado é invariante ao estado agregado. Quando os choques agregados apresentam persistência, porém, alocações eficientes apresentam dependência da história de choques e, em geral, uma distribuição invariante não existe.

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.

Convergence in Brazil: recent trends and long run prospects

This paper applies to the analysis of the interstate income distribution in BraziI a set of techniques that have been widely used in the current empirical literature on growth and convergence. Usual measures of dispersion in the interstate income distribution (the coefficient of variation and Theil' s index) suggest that cr-convergence was an unequivoca1 feature of the regional growth experience in BraziI, between 1970 and 1986. After 1986, the process of convergence seems, however, to have sIowed down almost to a halt. A standard growth modeI is shown to fit the regional data well and to expIain a substantial amount of the variation in growth rates, providing estimates of the speed of (conditional) J3-convergence of approximateIy 3% p.a .. Different estimates of the long run distribution implied by the recent growth trends point towards further reductions in the interstate income inequality, but also suggest that the relative per capita incomes of a significant number of states and the number of ''very poor" and "poor" states were, in 1995, already quite c10se to their steady-state values.

International integration and long- run persistence of the GNP distribution

We use the Ramsey model of g,Towth elaborated by Bliss [1995] and Ventlira [1997] to show how international integration results in long-nm persistellce Df GNPs distribution, while allowing, under certain conditions on parameters, for convergellce during the transition. First, we pi·ovide relationships which explicitly relate, in the neighborhood of the steady-state, the magnitude of conditional convergence or divergence to the fundamentaIs of the economies. Second, we present ali analysis of the Cobb Douglas case with a broad dass of utility functions and show that there is always transitional convergenee with this technology. Third, directions for testing the Illodel against the traditional dosed-ecollomy setting are proposed. These lead to adding specific and world-wide regTessors to traditional growth regressions.

The long-run economic impact of AIDS

This paper studies the long-run impact of HIV / AIDS on per capita income and education. We introduce a channel from HIV / AIDS to long-run income that has been overlooked by the literature, the reduction of the incentives to study due to shorter expected longevity. We work with a continuous time overlapping generations mo deI in which life cycle features of savings and education decision play key roles. The simulations predict that the most affected countries in Sub-Saharan Africa will be in the future, on average, a quarter poorer than they would be without AIDS, due only to the direct (human capital reduction) and indirect (decline in savings and investment) effects of life-expectancy reductions. Schooling will decline on average by half. These findings are well above previous results in the literature and indicate that, as pessimistic as they may be, at least in economic terms the worst could be yet to come.

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

Using a sequence of nested multivariate models that are VAR-based, we discuss different layers of restrictions imposed by present-value models (PVM hereafter) on the VAR in levels for series that are subject to present-value restrictions. Our focus is novel - we are interested in the short-run restrictions entailed by PVMs (Vahid and Engle, 1993, 1997) and their implications for forecasting. Using a well-known database, kept by Robert Shiller, we implement a forecasting competition that imposes different layers of PVM restrictions. Our exhaustive investigation of several different multivariate models reveals that better forecasts can be achieved when restrictions are applied to the unrestricted VAR. Moreover, imposing short-run restrictions produces forecast winners 70% of the time for the target variables of PVMs and 63.33% of the time when all variables in the system are considered.

International migration, capital flows and the global economy: a long run view

Includes bibliography

Long run economic development in Latin America in a comparative perspective: proximate and ultimate causes

Includes bibliography