In this paper we survey the most recent advances in supervised machine learning and highdimensional models for time series forecasting. We consider both linear and nonlinear alternatives. Among the linear methods we pay special attention to penalized regressions and ensemble of models. The nonlinear methods considered in the paper include shallow and deep neural networks, in their feed-forward and recurrent versions, and tree-based  methods, such as random forests and boosted trees. We also consider ensemble and hybrid models by combining ingredients from different alternatives. Tests for superior predictive ability are briefly  reviewed. Finally, we discuss application of machine learning in economics and finance and provide an illustration with high-frequency financial data

There has been considerable advance in understanding the properties of sparse regularization procedures in high-dimensional models. In time series context, it is mostly restricted to Gaussian autoregressions or mixing sequences. We study oracle properties of LASSO estimation of weakly sparse vector-autoregressive models with heavy tailed, weakly dependent innovations with virtually no assumption on the conditional heteroskedasticity. In contrast to current literature, our innovation process satisfy an L1 mixingale type condition on the centered conditional covariance matrices. This condition covers L1-NED sequences and strong mixing sequences as particular examples. From a modeling perspective, it covers several multivariate-GARCH specifications, such as the BEKK model, and other factor stochastic volatility specifications that were ruled out by assumption in previous studies.

Recently, there has been growing interest in developing econometric tools to conduct counterfactual analysis with aggregate data when a single “treated” unit suffers an intervention, such as a policy change, and there is no obvious control group. Usually, the proposed methods are based on the construction of an artificial/synthetic counterfactual from a pool of “untreated” peers, organized in a panel data structure. In this article, we investigate the consequences of applying such methodologies when the data comprise integrated processes of order 1, I(1), or are trend-stationary. We find that for I(1) processes without a cointegrating relationship (spurious case) the estimator of the effects of the intervention diverges, regardless of its existence. Although spurious regression is a well-known concept in time-series econometrics, they have been ignored in most of the literature on counterfactual estimation based on artificial/synthetic controls. For the case when at least one cointegration relationship exists, we have consistent estimators for the intervention effect albeit with a nonstandard distribution. Finally, we discuss a test based on resampling which can be applied when there is at least one cointegration relationship or when the data are trend-stationary.

We estimate a macroeconomic model on US data where banks lend to households and businesses and simultaneously adjust lending requirements on the two types of loans. We find that the collateral shock, a change in the ability of the financial sector to redeploy collateral, is the most important force driving the business cycle. Hit by this unique disturbance, our model quantitatively replicates the joint dynamics of output, consumption, investment, employment, and both household and business credit quantities and spreads. The estimated collateral shock generates accurate movements in lending standards and tracks measures of market sentiment.

The paper proposes a quantile-regression inference framework for first-price auctions with symmetric risk-neutral bidders under the independent private-value paradigm. It is first shown that a private-value quantile regression generates a quantile regression for the bids. The private-value quantile regression can be easily estimated from the bid quantile regression and its derivative with respect to the quantile level. This also allows to test for various specification or exogeneity null hypothesis using the observed bids in a simple way. A new local polynomial technique is proposed to estimate the latter over the whole quantile level interval. Plug-in estimation of functionals is also considered, as needed for the expected revenue or the case of CRRA risk-averse bidders, which is amenable to our framework. A quantile-regression analysis to USFS timber is found more appropriate than the homogenized-bid methodology and illustrates the contribution of each explanatory variables to the private-value distribution. Linear interactive sieve extensions are proposed and studied in the Appendices. 

This paper provides a game-theoretic model of network formation with a continuous effort choice. Efforts are strategic complements for direct neighbors in the network and display global substitution/competition effects. We show that if the parameter governing local strategic complements is larger than the one governing global strategic substitutes, then all pairwise Nash equilibrium networks are nested split graphs. We also consider the problem of a planner, who can choose effort levels and place links according to a network cost function. Again all socially optimal configurations are such that the network is a nested split graph. However, the socially optimal network may be different from equilibrium networks and efficient effort levels do not coincide with Nash equilibrium effort levels. In the presence of strategic substitutes, Nash equilibrium effort levels may be too high or too low relative to efficient effort levels. The relevant applications are crime networks and R&D collaborations among firms, but also interbank lending and trade.

The article proposes a parsimonious and flexible semiparametric quantile regression specification for asymmetric bidders within the independent private value framework. Asymmetry is parameterized using powers of a parent private value distribution, which is generated by a quantile regression specification. As noted in Cantillon, this covers and extends models used for efficient collusion, joint bidding and mergers among homogeneous bidders. The specification can be estimated for ascending auctions using the winning bids and the winner’s identity. The estimation is in two stage. The asymmetry parameters are estimated from the winner’s identity using a simple maximum likelihood procedure. The parent quantile regression specification can be estimated using simple modifications of Gimenes. Specification testing procedures are also considered. A timber application reveals that weaker bidders have 30% less chances to win the auction than stronger ones. It is also found that increasing participation in an asymmetric ascending auction may not be as beneficial as using an optimal reserve price as would have been expected from a result of Bulow and Klemperer valid under symmetry.

Using rich administrative and household survey data spanning 34 years from 1985 to 2018, we document a series of new facts on earnings inequality and dynamics in a developing country with a large informal sector: Brazil. Since the mid-1990s, both inequality and volatility of earnings have declined significantly in Brazil’s formal sector. Higher-order moments of the distribution of earnings changes show cyclical movements in Brazil that are similar to those in developed countries like the US. Relative to the formal sector, the informal sector is associated with a significant earnings penalty and higher earnings volatility for identical workers. Earnings changes of workers who switch from formal to informal (from informal to formal) employment are relatively negative (positive) and large in magnitude, dispersed, negatively (positively) skewed, and less leptokurtic. Our results suggest that informal employment is an imperfect insurance mechanism

This paper adds to the scant literature on the impact of terrorism on consumer behaviour, focusing on household spending on goods that are sensitive to brain-stress neurocircuitry. These include sweet- and fat-rich foods but also home necessities and female-personal-hygiene products, the only female-targeted good in our data. We examine unique continuous in-home-scanner expenditure data for a representative sample of about 15,000 French households, observed in the days before and after the terrorist attack at the Bataclan concert-hall. We find that the attack increased expenditure on sugar-rich food by over 5% but not that on salty food or soda drinks. Spending on home maintenance products went up by almost 9%. We detect an increase of 23.5% in expenditure on women’s personal hygiene products. We conclude that these effects are short-lived and driven by the responses of households with children, youths, and those residing within a few-hours ride of the place of the attack.

Ordinary Least Squares (OLS) estimation of monetary policy rules produces potentially inconsistent estimates of policy parameters. The reason is that central banks react to variables, such as inflation and the output gap, that are endogenous to monetary policy shocks. Endogeneity implies a correlation between regressors and the error term – hence, an asymptotic bias. In principle, Instrumental Variables (IV) estimation can solve this endogeneity problem. In practice, however, IV estimation poses challenges, as the validity of potential instruments depends on various unobserved features of the economic environment. We argue in favor of OLS estimation of monetary policy rules. To that end, we show analytically in the three-equation New Keynesian model that the asymptotic OLS bias is proportional to the fraction of the variance of regressors due to monetary policy shocks. Using Monte Carlo simulations, we then show that this relationship also holds in a quantitative model of the U.S. economy. Since monetary policy shocks explain only a small fraction of the variance of regressors typically included in monetary policy rules, the endogeneity bias tends to be small. For realistic sample sizes, OLS outperforms IV. Finally, we estimate a standard Taylor rule on different subsamples of U.S. data and find that OLS and IV estimates are quite similar.

t is widely believed that the presence of a large informal sector increases the efficiency cost of social programs in developing countries. We evaluate such claims for the case of Unemployment Insurance (UI) by combining an optimal UI framework with comprehensive data from Brazil. Using quasi-experimental variation in potential UI duration, we find clear evidence for the usual moral hazard problem that UI reduces incentives to return to a formal job. Yet, the associated efficiency cost is lower than in the U.S., and is lower in labor markets with higher informality within Brazil. This is because formal reemployment rates are lower to begin with where informality is higher, so that a larger share of workers would draw UI benefits absent any moral hazard. In sum, efficiency concerns may actually become more relevant as an economy formalizes.

What determines whether or not multinational firms transplant the mode of organisation to other countries? We embed the theory of knowledge hierarchies in an industry equilibrium model of monopolistic competition to examine how the economic environment may affect the decision of multinational firms about transplanting the mode of organization to other countries. We test the theory with original and matched parent and affiliate data on the level of decentralization of 660 Austrian and German multinational firms and 2200 of their affiliate firms in Eastern Europe. We find that market competition in both home and host markets is an important driver of organizational transfer to host countries: An increase in competition in the home (host) market by 10 percentage points lowers (increases) the probability of transplanting by 9 (7) percentage points.

Price selection is a simple, model-free measure of selection in price setting and its contribution to inflation dynamics. It exploits comovement between inflation and the level from which adjusting prices departed. Prices that increase from lower-than-usual levels tend to push inflation above average. Using detailed micro-level consumer price data for the United Kingdom, the United States, and Canada, we find robust evidence of strong price selection across goods and services. At a disaggregate level, price selection accounts for 37% of inflation variance inflthe United Kingdom, 36% in the United States, and 28% in Canada. Price selection is stronger for goods with less frequent price changes or with larger average price changes. Aggregate price selection is considerably weaker. A multisector sticky-price model accounts well for this evidence and demonstrates a monotone relationship between price selection and monetary non-neutrality.

Revisão em maio de 2021

Recently, there has been growing interest in developing econometric tools to conduct counterfactual analysis with aggregate data when a “treated” unit suffers an intervention, such as a policy change, and there is no obvious control group. Usually, the proposed methods are based on the construction of an artificial counterfactual from a pool of “untreated” peers, organized in a panel data structure. In this paper, we consider a general framework for counterfactual analysis in high dimensions with potentially non-stationary data and either deterministic and/or stochastic trends, which nests well-established methods, such as the synthetic control. Furthermore, we propose a resampling procedure to test intervention effects that does not rely on post-intervention asymptotics and that can be used even if there is only a single observation after the intervention. A simulation study is provided as well as an empirical application where the effects of price changes on the sales of a product is measured.

Inflation forecasting is an important but difficult task. Here, we explore advances in machine learning (ML) methods and the availability of new datasets to forecast U.S. inflation. Despite the skepticism in the previous literature, we show that ML models with a large number of covariates are systematically more accurate than the benchmarks. The ML method that deserves more attention is the random forest model, which dominates all other models. Its good performance is due not only to its specific method of variable selection but also the potential nonlinearities between past key macroeconomic variables and inflation. Supplementary materials for this article are available online.

In third generation currency crises models, balance sheet losses from currency depreciations propagate the crises into the real sector of the economy. To test these models, we built a firm-level database that allowed us to measure currency mismatches around the 2002 Brazilian currency crisis. We found that between 2001 and 2003, firms with large currency mismatches just before the crisis reduced their investment rates 8.1 percentage points more than other publicly held firms. We also showed that the currency depreciation increased exporters revenue, but those with currency mismatches reduced investments 12.5 percentage points more than other exporters. These estimated reductions in investment are economically very significant, underscoring the importance of negative balance sheet effects in currency crises.

n order to elucidate the revival of religion in the Muslim countries, we must not only understand the spread of puritan interpretations of the faith (as they have permeated movements running from Muslim Brothers to violent Islamist movements), but also comprehend the process whereby these more radical ideologies have been accommodated by the (autocratic) Muslim states. This necessitates that we explore the internal political economy of Muslim countries without neglecting the possible influence of international forces. The theory used as a background to the present work has precisely allowed us to achieve that objective. It works out the strategic interactions between three key players: the ruler, the clerics, and the military, in the context of an autocracy; moreover, it highlights the channels through which external events and shocks make themselves felt through the local political and social fabrics. Among these shocks, military defeats by powers considered as imperialist, and the declaration of a world war against terrorism seem to have played a more important role than the end of the Cold War.

We develop a multisector sticky-price DSGE model that can endogenously deliver differential responses of prices to aggregate and sectoral shocks. Input-output production linkages and a (standard) monetary policy rule contribute to a slow response of prices to aggregate shocks. In turn, labor market segmentation at the sectoral level induces withinsector strategic substitutability in price-setting decisions, which helps the model deliver a fast response of prices to sector-specific shocks. We estimate the model using aggregate and sectoral price and quantity data for the U.S., and find that it accounts well for a range of sectoral price facts.

This paper introduces a version of the interdependent value model of Milgrom and Weber (1982), where the signals are given by an index gathering signal shifters observed by the econometrician and private ones specific to each bidders. The model primitives are shown to be nonparametrically identified from first-price auction bids under a testable mild rank condition. Identification holds for all possible signal values. This allows to consider a wide range of counterfactuals where this is important, as expected revenue in second-price auction. An estimation procedure is briefly discussed.