Factor and sparse models are two widely used methods to impose a low-dimensional structure in high dimension. They are seemingly mutually exclusive. In this paper, we propose a simple lifting method that combines the merits of these two models in a supervised learning methodology that allows to efficiently explore all the information in high-dimensional datasets. The method is based on a very flexible linear model for panel data, called factor-augmented regression model with both observable, latent common factors, as well as idiosyncratic components as high-dimensional covariate variables. This model not only includes both factor regression and sparse regression as specific models but also significantly weakens the cross-sectional dependence and hence facilitates model selection and interpretability. The methodology consists of three steps. At each step, remaining cross-section dependence can be inferred by a novel test for covariance structure in high-dimensions. We developed asymptotic theory for the factoraugmented sparse regression model and demonstrated the validity of the multiplier bootstrap for testing high-dimensional covariance structure. This is further extended to testing highdimensional partial covariance structures. The theory and methods are further supported by an extensive simulation study and applications to the construction of a partial covariance network of the financial returns for the constituents of the S&P500 index and prediction exercise for a large panel of macroeconomic time series from FRED-MD database

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.

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 nance and provide an illustration with high-frequency nancial data

The measurement of treatment (intervention) effects on a single (or just a few) treated unit(s) based on counterfactuals constructed from artificial controls has become a popular practice in applied statistics and economics since the proposal of the synthetic control method. In high-dimensional setting, we often use principal component or (weakly) sparse regression to estimate counterfactuals. Do we use enough data information? To better estimate the effects of price changes on the sales in our case study, we propose a general framework on counterfactual analysis for high dimensional dependent data. The framework includes both principal component regression and sparse linear regression as specific cases. It uses both factor and idiosyncratic components as predictors for improved counterfactual analysis, resulting a method called Factor-Adjusted Regularized Method for Treatment (FarmTreat) evaluation. We demonstrate convincingly that using either factors or sparse regression is inadequate for counterfactual analysis in many applications and the case for information gain can be made through the use of idiosyncratic  components. We also develop theory and methods to formally answer the question if common factors are adequate for estimating counterfactuals. Furthermore, we consider a simple resampling approach to conduct inference on the treatment effect as well as bootstrap test to access the relevance of the idiosyncratic components. We apply the proposed method to evaluate the effects of price changes on the sales of a set of products based on a novel large panel of sale data from a major retail chain in Brazil and demonstrate the benefits  of using additional idiosyncratic components in the treatment effect evaluations.

This paper studies optimal targeting policies, consisting of eliminating (preserving) a set of agents in a network and aimed at minimizing (maximizing) aggregate effort levels. Different from the existing literature, we allow the equilibrium network to adapt after a network intervention and consider targeting of multiple agents. A simple and tractable adjustment process is introduced. We find that allowing the network to adapt may overturn optimal targeting results for a fixed network and that congestion/competition effects are crucial to understanding differences between the two settings

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/congestion 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.

In product markets, there exists substantial dispersion in prices for transactions of physically identical goods, and incumbent sellers sell at higher prices than entrants. This study develops a theory of dynamic pricing that explains these facts as results from the same fundamental friction: Buyers are imperfectly aware of which sellers are operating, and the degree of awareness about a seller is  ndogenous. The equilibrium is unique and efficient, and features randomized pricing strategies where incumbents post higher prices than entrants. If buyers' memory depreciation is low, then the equilibrium of the industry tends to approximate perfectly competitive conditions over time.

We study a unique dataset with comprehensive coverage of daily prices in large multi-product retailers in Israel. Retail stores synchronize price changes around occasional "peak" days when they reprice around 10% of their products. To assess aggregate implications of partial price synchronization, we develop a new model in which multi-product firms face economies of scope in price adjustment, and synchronization is endogenous. Synchronization of price changes attenuates the average price response to monetary shocks, but only high degrees of synchronization can substantially strengthen monetary non-neutrality. Our calibrated model generates as little monetary non-neutrality as in Golosov and Lucas (2007).

Bandit problems are pervasive in various fields of research and are also present in  several practical applications. Examples, including dynamic pricing and assortment and the design of auctions and incentives, permeate a large number of sequential treat- ment experiments. Different applications impose distinct levels of restrictions on viable actions. Some favor diversity of outcomes, while others require harmful actions to be closely monitored or mainly avoided. In this paper, we extend one of the most popular bandit solutions, the original et-greedy heuristics, to high-dimensional contexts. Moreover, we introduce a competing exploration mechanism that counts with searching sets based on order statistics. We view our proposals as alternatives for cases where pluralism is valued or, in the opposite direction, cases where the end-user should carefully tune the range of exploration of new actions. We find reasonable bounds for the cumulative regret of a decaying et-greedy heuristic in both cases, and we provide an upper bound for the initialization phase that implies the regret bounds when order statistics are considered to be at most equal but mostly better than the case when random searching is the sole exploration mechanism. Additionally, we show that endusers have sufficient  exibility to avoid harmful actions since any cardinality for the higher-order statistics can be used to achieve stricter upper bound. In a simulation exercise, we show that the algorithms proposed in this paper outperform simple and adapted counterparts.

The Covid-19 crisis has lead to a reduction in the demand and supply of sectors that produce goods that need social interaction to be produced or consumed. We interpret the Covid-19 shock as a shock that reduces utility stemming from “social” goods in a two-sector economy with incomplete markets. We compare the advantages of lump-sum transfers versus a credit policy. For the same path of government debt, transfers are preferable when debt limits are tight, whereas credit policy is preferable when they are slack. A credit policy has the advantage of targeting fiscal resources toward  agents that matter most for stabilizing demand. We illustrate this result with a calibrated model. We discuss various shortcomings and possible extensions to the model.

Publicado como  NBER Working paper no. 27118 

Speculation, in the spirit of Harrison and Kreps [1978], is introduced into a standard real business cycle model. Investors (speculators) hold heterogeneous beliefs about firm growth. Firm ownership, and thus, the firm’s discount factor varies with waves of optimism and leverage. These waves ripple into firm investments in hours. The firm’s discount discount factor links the equity premium and labor volatility puzzles. We obtain an upper bound to the amplification that can be generated by speculation for any model of beliefs -- a factor of 1.5. A calibration based on diagnostic beliefs amplifies hours volatility by a factor of 1.15 and produces a bubble component of 20 percent.

We use data from polling stations and public primary schools to estimate the electoral effects of making school quality information available to voters. We exploit the introduction of a school-level accountability system in Brazil that provides, for the first time, information about school quality and exploit variation in schools affected by the policy. We find that incumbent vote shares are 2.14 percentage points higher for schools in the top 20% of our sample’s distribution of school quality and 1.54 percentage points lower for schools in the bottom 20% of the distribution. These effects are mostly driven by the unpredicted component of school quality and are larger for more educated voters.

O objetivo do presente trabalho é examinar a situação fundiária no Brasil Imperial nos seus aspectos econômicos, mas também sociais e legais, a partir de seus antecedentes coloniais, e examinar criticamente a questão tradicionalmente enfatizada na historiografia da onipresença e predominância de latifúndios no período imperial. 

We augment a standard dynamic general equilibrium model with financial frictions, in order to quantify the macroeconomic effects of the credit deepening process observed in Latin America in the last decade - most notably in Brazil. In the model, a stylized banking sector intermediates credit from patient households to impatient households and entrepreneurs. Motivated by the Brazilian experience, we allow the credit constraint faced by households to depend on labor income. Our model is designed to isolate the effects of credit deepening through demand-side channels, and abstracts from potential effects of credit supply on total factor productivity. In the calibrated model, credit deepening generates only modest above-trend growth in consumption, investment, and GDP. Since Brazil has experienced one of the most intense credit deepening processes in Latin America, we argue that the quantitative effects that hinge on the channels captured by the model are unlikely to be sizable elsewhere

(revisto em Junho de 2017)

Since the mid 1990s, theories of speculative attacks have argued that fixed exchange rate regimes induce excessive borrowing in foreign currency as an optimal response to implicit guarantees that the government will not devalue the domestic currency. Using data on Brazilian  firms before and after the end of the fixed exchange rate regime in 1999, we estimate the relevance of the government guarantees by comparing the changes in foreign debt of two groups of firms: those that hedged their foreign currency debt prior to the exchange rate float and those that did not. Using the difference-in-differences approach, in which firm-specific characteristics are introduced as control variables, we exclude the macroeconomic effects of the change in the exchange rate regime and the possible differences in foreign debt trends of the two groups of firms, thus obtaining an estimate of the impact of the government guarantees on borrowing in foreign currency. The results suggest that the guarantees do not induce  excessive borrowing in foreign currency

How countercyclical macroprudential credit policies affect the loan spread?   To answer this question, we propose a microeconomic model of bank competition  that contemplates differences in the behavior of public and private banks and  the peculiarities of the market for corporate loans vis-a-vis the market for consumer loans. We solve the model and calibrate it using parameters of the Brazilian economy, where government-owned banks not only account for almost half of the outstanding loans in the credit market but also have played a strong countercyclical role in the economy. Subsequently, we use the equilibrium conditions of the model to study the effects of macroprudential credit policies on loan  preads. The results indicate that credit expansion by public banks is more effective to reduce loans interest rates during recession periods than during periods of economic expansion

Este trabalho investiga os efeitos da incerteza sobre a atividade econômica no Brasil. Para isso, são construídas diversas proxies que buscam capturar o nível de incerteza vigente na economia brasileira (incerteza doméstica) e em vários de seus principais parceiros comerciais (incerteza externa). Em seguida, são estimados modelos de vetores autorregressivos (VAR) estruturais, cujas funções de resposta ao impulso sugerem efeitos contracionistas significativos da incerteza sobre a atividade, em particular sobre o investimento. Além disso, as estimativas indicam que os efeitos da incerteza doméstica são mais acentuados do que os da incerteza externa. Pode-se afirmar, portanto, que os níveis de incerteza vigentes no Brasil desde as eleições presidenciais de 2014 representam importante fator por trás da recessão subsequente. Estima-se que caso não houvesse a expansão de incerteza doméstica observada a partir do segundo semestre de 2014, a produção industrial em 2015 teria sido, em média, entre 0,9% e 3,9% maior, dependendo da variável proxy de incerteza utilizada. No caso do IBC-Br, este teria sido entre 0,4% e 1,3% maior. Os resultados encontrados são robustos para diversas alterações no modelo.

Revisto em fevereiro de 2018

The objective of this paper is to evaluate the Brazilian Apprenticeship program (Lei do Aprendiz). This program is a youth-targeted ALMP that has been adopted at a large scale since 2000 in Brazil. The program concedes payroll subsidies to firms that hire and train young workers under special temporary contracts aiming to help them successfully complete the transition from school to work. We make use of a very rich longitudinal matched employee-employer dataset covering the universe of formally employed workers in Brazil, including apprentices. Our identification strategy exploits a discontinuity by age in the eligibility to enter the program in the early 2000’s, when 17 was the age limit to take part in the program. We examine the impacts on employability, wage growth and attachment to the formal labor market using other temporary workers as a control group. We find that the program increases the probability of employment in permanent jobs in 2-3- and 4-5-year horizons. We also find a positive impact on real wages that increases over time. These results hold when we isolate the effects of the training dimension of the program by using an alternative control group composed of subsidized temporary workers. We show evidence that the positive effects of the program are much larger for less-educated workers and for workers who had their first jobs in large firms. These results are robust to other choices of methods to address selection into the program based on unobservables.

Revisto em fevereiro de 2018

A measure of the propensity to gamble in casinos constructed without any asset price data provides relevant information for asset pricing. This measure of risk appetite improves the fit of conditional asset pricing models such as the conditional CAPM, explains cross-sectional differences in future returns for portfolios sorted on various characteristics, and helps forecast market and portfolio excess returns. The relationship between risk appetite and asset prices appears to be mainly explained by simultaneous changes in risk and risk premia

In a repeated unobserved endowment economy in which agents negotiate long-term contracts with a financial intermediary, we study the risk-sharing implications of the interaction between incentive compatibility constraints (due to private information) and participation constraints (due to one-sided commitment). In particular, we assume that after a default episode, agents consume their endowment and remain in autarky forever. We find that once they are away from autarky today, if the probability of drawing the highest possible endowment shock is sufficiently small, the optimal contract prevents agents from reaching autarky tomorrow and, thus, from being "impoverished". Moreover, an invariant cross-sectional distribution of life-time utilities (or values) exists. A numerical example shows that the mass of agents living in autarky can be zero in the limit.

Revisto em março de 2018