Forecasting with Medium and Large Bayesian VARs

This paper is motivated by the recent interest in the use of Bayesian VARs for forecasting, even in cases where the number of dependent variables is large. In such cases, factor methods have been traditionally used but recent work using a particular prior suggests that Bayesian VAR methods can forecast better. In this paper, we consider a range of alternative priors which have been used with small VARs, discuss the issues which arise when they are used with medium and large VARs and examine their forecast performance using a US macroeconomic data set containing 168 variables. We nd that Bayesian VARs do tend to forecast better than factor methods and provide an extensive comparison of the strengths and weaknesses of various approaches. Our empirical results show the importance of using forecast metrics which use the entire predictive density, instead of using only point forecasts.

What drives urban consumption in mainland china? The role of property price dynamics

This paper adds to the literature on wealth effects on consumption by disentangling house price effects on consumption for mainland China. In a stochastic modelling framework, the riskiness, rate of increase and persistence of house price movements have different implications for the consumption/housing ratio. We exploit the geographical variation in property prices by using a quarterly city-level panel dataset for the period 1998Q1 – 2009Q4 and rely on a panel error correction model. Overall, the results suggest a significant long run impact of property prices on consumption. They also broadly confirm the predictions from the theoretical model.

A Producer Theory with Business Risks

In this paper, we consider a producer who faces uninsurable business risks due to incomplete spanning of asset markets over stochastic goods market outcomes, and examine how the presence of the uninsurable business risks affects the producer's optimal pricing and production behaviours. Three key (inter-related) results we find are: (1) optimal prices in goods markets comprise ‘markup’ to the extent of market power and ‘premium’ by shadow price of the risks; (2) price inertia as we observe in data can be explained by a joint work of risk neutralization motive and marginal cost equalization condition; (3) the relative responsiveness of risk neutralization motive and marginal cost equalization at optimum is central to the cyclical variation of markups, providing a consistent explanation for procyclical and countercyclical movements. By these results, the proposed theory of producer leaves important implications both micro and macro, and both empirical and theoretical.

A New Model Of Trend Inflation

This paper introduces a new model of trend (or underlying) inflation. In contrast to many earlier approaches, which allow for trend inflation to evolve according to a random walk, ours is a bounded model which ensures that trend inflation is constrained to lie in an interval. The bounds of this interval can either be fixed or estimated from the data. Our model also allows for a time-varying degree of persistence in the transitory component of inflation. The bounds placed on trend inflation mean that standard econometric methods for estimating linear Gaussian state space models cannot be used and we develop a posterior simulation algorithm for estimating the bounded trend inflation model. In an empirical exercise with CPI inflation we find the model to work well, yielding more sensible measures of trend inflation and forecasting better than popular alternatives such as the unobserved components stochastic volatility model.

Marriage as a Rat Race: Noisy Pre-Marital Investments with Assortative Matching

We study the incentive to invest to improve marriage prospects, in a frictionless marriage market with non-transferable utility. Stochastic returns to investment eliminate the multiplicity of equilibria in models with deterministic returns, and a unique equilibrium exists under reasonable conditions. Equilibrium investment is efficient when the sexes are symmetric. However, when there is any asymmetry, including an unbalanced sex ratio, investments are generically excessive. For example, if there is an excess of boys, then there is parental over-investment in boys and under-investment in girls, and total investment will be excessive.

Pecuniary Externality through Credit Constraints: Two Examples without Uncertainty

This paper is a contribution to the growing literature on constrained inefficiencies in economies with financial frictions. The purpose is to present two simple examples, inspired by the stochastic models in Gersbach-Rochet (2012) and Lorenzoni (2008), of deterministic environments in which such inefficiencies arise through credit constraints. Common to both examples is a pecuniary externality, which operates through an asset price. In the second example, a simple transfer between two groups of agents can bring about a Pareto improvement. In a first best economy, there are no pecuniary externalities because marginal productivities are equalised. But when agents face credit constraints, there is a wedge between their marginal productivities and those of the non-credit-constrained agents. The wedge is the source of the pecuniary externality: economies with these kinds of imperfections in credit markets are not second-best efficient. This is akin to the constrained inefficiency of an economy with incomplete markets, as in Geanakoplos and Polemarchakis (1986).

Asset Prices, Business Cycles, and Markov-Perfect Fiscal Policy when Agents are Risk-Sensitive

We study a business cycle model in which a benevolent fiscal authority must determine the optimal provision of government services, while lacking credibility, lump-sum taxes, and the ability to bond finance deficits. Households and the fiscal authority have risk sensitive preferences. We find that outcomes are affected importantly by the household's risk sensitivity, but not by the fiscal authority's. Further, while household risk-sensitivity induces a strong precautionary saving motive, which raises capital and lowers the return on assets, its effects on fluctuations and the business cycle are generally small, although more pronounced for negative shocks. Holding the stochastic steady state constant, increases in household risk-sensitivity lower the risk-free rate and raise the return on equity, increasing the equity premium. Finally, although risk-sensitivity has little effect on the provision of government services, it does cause the fiscal authority to lower the income tax rate. An additional contribution of this paper is to present a method for computing Markov-perfect equilibria in models where private agents and the government are risk-sensitive decisionmakers.

Coordination in Public Good Provision: How Individual Volunteering is Impacted by the Volunteering of Others

In this analysis, we examine the relationship between an individual's decision to volunteer and the average level of volunteering in the community where the individual resides. Our theoretical model is based on a coordination game , in which volunteering by others is informative regarding the benefit from volunteering. We demonstrate that the interaction between this information and one's private information makes it more likely that he or she will volunteer, given a higher level of contributions by his or her peers. We complement this theoretical work with an empirical analysis using Census 2000 Summary File 3 and Current Population Survey (CPS) 2004-2007 September supplement file data. We control for various individual and community characteristics, and employ robustness checks to verify the results of the baseline analysis. We additionally use an innovative instrumental variables strategy to account for reflection bias and endogeneity caused by selective sorting by individuals into neighborhoods, which allows us to argue for a causal interpretation. The empirical results in the baseline, as well as all robustness analyses, verify the main result of our theoretical model, and we employ a more general structure to further strengthen our results.

Imperfect Attention and Menu Evaluation

We model the choice behaviour of an agent who suffers from imperfect attention. We define inattention axiomatically through preference over menus and endowed alternatives: an agent is inattentive if it is better to be endowed with an alternative a than to be allowed to pick a from a menu in which a is is the best alternative. This property and vNM rationality on the domain of menus and alternatives imply that the agent notices each alternative with a given menu-dependent probability (attention parameter) and maximises a menu independent utility function over the alternatives he notices. Preference for flexibility restricts the model to menu independent attention parameters as in Manzini and Mariotti [19]. Our theory explains anomalies (e.g. the attraction and compromise effect) that the Random Utility Model cannot accommodate.

Coordination in Public Good Provision: How Individual Volunteering is Impacted by the Volunteering of Others

In this analysis, we examine the relationship between an individual’s decision to volunteer and the average level of volunteering in the community where the individual resides. Our theoretical model is based on a coordination game , in which volunteering by others is informative regarding the benefit from volunteering. We demonstrate that the interaction between this information and one’s private information makes it more likely that he or she will volunteer, given a higher level of contributions by his or her peers. We complement this theoretical work with an empirical analysis using Census 2000 Summary File 3 and Current Population Survey (CPS) 2004-2007 September supplement file data. We control for various individual and community characteristics, and employ robustness checks to verify the results of the baseline analysis. We additionally use an innovative instrumental variables strategy to account for reflection bias and endogeneity caused by selective sorting by individuals into neighbourhoods, which allows us to argue for a causal interpretation. The empirical results in the baseline, as well as all robustness analyses, verify the main result of our theoretical model, and we employ a more general structure to further strengthen our results.

Competing for Attention: Is the Showiest also the Best?

We introduce attention games. Alternatives ranked by quality (producers, politicians, sexual partners...) desire to be chosen and compete for the imperfect attention of a chooser by investing in their own salience. We prove that if alternatives can control the attention they get, then ”the showiest is the best”: the equilibrium ordering of salience (weakly) reproduces the quality ranking and the best alternative is the one that gets picked most often. This result also holds under more general conditions. However, if those conditions fail, then even the worst alternative can be picked most often.

Tax smoothing in a business cycle model with capital-skill complementarity

This paper undertakes a normative investigation of the quantitative properties of optimal tax smoothing in a business cycle model with state contingent debt, capital-skill complementarity, endogenous skill formation and stochastic shocks to public consumption as well as total factor and capital equipment productivity. Our main finding is that an empirically relevant restriction which does not allow the relative supply of skilled labour to adjust in response to aggregate shocks, signi cantly changes the cyclical properties of optimal labour taxes. Under a restricted relative skill supply, the government fi nds it optimal to adjust labour income tax rates so that the average net returns to skilled and unskilled labour hours exhibit the same dynamic behaviour as under fl exible skill supply.

Model Uncertainty in Panel Vector Autoregressive Models.

We develop methods for Bayesian model averaging (BMA) or selection (BMS) in Panel Vector Autoregressions (PVARs). Our approach allows us to select between or average over all possible combinations of restricted PVARs where the restrictions involve interdependencies between and heterogeneities across cross-sectional units. The resulting BMA framework can find a parsimonious PVAR specification, thus dealing with overparameterization concerns. We use these methods in an application involving the euro area sovereign debt crisis and show that our methods perform better than alternatives. Our findings contradict a simple view of the sovereign debt crisis which divides the euro zone into groups of core and peripheral countries and worries about financial contagion within the latter group.

Model Uncertainty in Panel Vector Autoregressive Models.

We develop methods for Bayesian model averaging (BMA) or selection (BMS) in Panel Vector Autoregressions (PVARs). Our approach allows us to select between or average over all possible combinations of restricted PVARs where the restrictions involve interdependencies between and heterogeneities across cross-sectional units. The resulting BMA framework can find a parsimonious PVAR specification, thus dealing with overparameterization concerns. We use these methods in an application involving the euro area sovereign debt crisis and show that our methods perform better than alternatives. Our findings contradict a simple view of the sovereign debt crisis which divides the euro zone into groups of core and peripheral countries and worries about financial contagion within the latter group.

Large Bayesian VARMAs

Vector Autoregressive Moving Average (VARMA) models have many theoretical properties which should make them popular among empirical macroeconomists. However, they are rarely used in practice due to over-parameterization concerns, difficulties in ensuring identification and computational challenges. With the growing interest in multivariate time series models of high dimension, these problems with VARMAs become even more acute, accounting for the dominance of VARs in this field. In this paper, we develop a Bayesian approach for inference in VARMAs which surmounts these problems. It jointly ensures identification and parsimony in the context of an efficient Markov chain Monte Carlo (MCMC) algorithm. We use this approach in a macroeconomic application involving up to twelve dependent variables. We find our algorithm to work successfully and provide insights beyond those provided by VARs.