Showing papers in "Journal of Econometrics in 2020"

TL;DR: This article proposes doubly robust estimators for the average treatment effect on the treated (ATT) in difference-in-differences (DID) research designs and quantifies the potential efficiency gains of having access to panel data instead of repeated cross-section data.

TL;DR: In this paper, the authors evaluate the dynamic impact of various policies adopted by US states on the growth rates of confirmed Covid-19 cases and deaths as well as social distancing behavior measured by Google Mobility Reports, where they take into consideration people's voluntarily behavioral response to new information of transmission risks.

TL;DR: It is found that the infection rate in the untested population and on the accuracy of the tests that appear credible in the current context might be substantially higher than reported and the infection fatality rate in Illinois, New York, and Italy is substantially lower than reported.

TL;DR: In this paper, the authors developed an estimator for latent factors in a large-dimensional panel of financial data that can explain expected excess returns. But their estimator cannot find asset-pricing factors, which cannot be detected with PCA, even if a large amount of data is available.

TL;DR: In this paper, the authors study two randomization inference (RI) procedures, i.e., the wild cluster bootstrap and the cluster robust variance estimator (CRVE), and show that RI procedures can yield inferences that differ dramatically from those of other methods.

TL;DR: This article employed non-orthogonality conditions for linear multiple cross-section simultaneous regression models to avoid the adoption of often incredible and unverifiable strictly zero correlation assumptions and imprecise inference due to possibly weak or invalid external instruments.

TL;DR: A specification is proposed that uses an empirical feature of TVP-(S)VARs to develop a factor-like structure to estimate a TVP-SVAR for many variables and retains a formal inferential framework such that it can propose formal inference on impulse responses, variance decompositions and, important for the model, the rank of the state equation covariance matrix.

TL;DR: This paper considers the case where covariate dependence can be reduced through the factor model, and proposes a consistency strategy named Factor-Adjusted Regularized Model Selection (FarmSelect), which transforms the problem from model selection with highly correlated covariates to that with weakly correlated ones via lifting.

TL;DR: Under certain sparsity assumptions on the precision matrix, estimators of the MVP are proposed and it is proved that the portfolios asymptotically achieve the minimum variance in a sharp sense.

TL;DR: This paper model the trajectory of the cumulative confirmed cases and deaths of COVID-19 via a piecewise linear trend model, and designs a simple two-stage forecasting scheme based on the change-point detection algorithm and a flexible extrapolation function that demonstrates its promising performance in predicting cumulative deaths in the U.S.

TL;DR: In this paper, the term structure of variance swaps, equity and variance risk premia is studied and a model-free analysis reveals that investors' willingness to ensure against volatility risk increases after a market drop.

TL;DR: A benchmark model is used to predict when the peak of the epidemic will arise in terms of new cases or new deaths in each country and the peak level, and how long the number of new daily cases in each countries will fall by an order of magnitude.

TL;DR: In this article, the authors proposed a consistent and asymptotically normal estimator for such ATEs when heterogeneity follows a non-parametric function of cutoff characteristics in the sharp case, which converges at the minimax optimal rate of root n for a specific choice of tuning parameters.

TL;DR: In this article, the authors developed an analytically tractable method to estimate the fraction of unreported infections in epidemics with a known epicenter and estimate the number of reported COVID-19 infections in the US during the first half of March 2020.

TL;DR: To statistically model such type of data, the multivariate spatial autoregressive (MSAR) model is studied and a least squares estimator (LSE) is developed.

TL;DR: In this paper, a nonparametric time series regression model is used to estimate the risk of individual stocks in the high-frequency stock market, including idiosyncratic volatility and idiosyncratic jumps, without the usual assumption of betas being piecewise constant.

TL;DR: In this article, the authors show that energy-balance models of climate are equivalent to an econometric cointegrated system and can be estimated in discrete time, which provides a basis for the use of cointegration methods to estimate climate responses and test their feedback.

TL;DR: In this article, a simple and fast approach to identify and estimate the unknown group structure in panel models by adapting the M-estimation method is proposed, where the regression coefficients are heterogeneous across groups but homogeneous within a group and the group membership is unknown to researchers.

TL;DR: This article developed Bayesian econometric methods for posterior inference in non-parametric mixed frequency VARs using additive regression trees, which is suitable for macroeconomic nowcasting in the face of extreme observations, for instance those produced by the COVID-19 pandemic of 2020.

TL;DR: This paper shows that posterior median (or mean) response functions in applied VAR analysis can be misleading because in empirically relevant settings there need not exist a posterior draw for the impulse response function that matches the posterior median or mean response function, even as the number of posterior draws approaches infinity.

TL;DR: In this article, the authors employ a formal test for the existence of functional unit roots in the time series of these densities, and develop a new test to distinguish functional unit root from functional deterministic trends or explosive behavior.

TL;DR: In this article, the first result for the uniform inference based on nonparametric series estimators in general time-series setting was provided, and a strong approximation theory for sample averages of mixingales with dimensions growing with the sample size was developed.

TL;DR: A novel adaptation of the parametric one-step update to a generic second-stage estimator is developed and conditions under which the scaled update is asymptotically normal are provided, which construct asymPTotically valid confidence intervals for the components of thesecond-stage regression coefficients.

TL;DR: In this paper, the authors use the over-identified instrumental variable-based predictability test statistics of Breitung and Demetrescu (2015) to avoid the problem of endogenously-determined sample splits and propose new tests derived from sequences of predictability statistics calculated over subsamples of the data.

TL;DR: In this paper, the cross-sectional dependent (CSD) bootstrap is proposed for factor-augmented regressions with cross-sectional dependence among idiosyncratic errors, where the covariance matrix estimator is consistent in the spectral norm.

TL;DR: A generic method for building dependency graphs without Gaussian assumption using the new test using the superiority of the new method, implemented in the R package pgraph, through simulation and real data studies.

TL;DR: It is shown that the conditional likelihood approach undermines theoretical underpinnings of Dic, and a new version of DIC, namely DICL, is proposed to compare latent variable models and it can be regarded as a Bayesian version of TIC.

TL;DR: In this article, the authors proposed a new dynamic model in which the conditional distribution of the observations is constructed by shifting a distribution for non-zero observations to the left and censoring negative values.

TL;DR: A procedure to fit Dynamic Factor Models with Cluster Structure (DFMCS) to heterogeneous data that may include multivariate additive outliers and level shifts is presented and it is shown in a Monte Carlo study that the procedure works well and seems to be better than other alternatives in terms of estimation of factors and loadings.

TL;DR: In this paper, the authors elicit parental beliefs about the returns and the persistence of a healthy diet and exercise routine in childhood and find that these beliefs contribute to the socioeconomic inequality in health outcomes and the intergenerational transmission of obesity.