Lorenzo Camponovo

The Finite Sample Performance of Inference Methods for Propensity Score Matching and Weighting Estimators

ABSTRACT This article investigates the finite sample properties of a range of inference methods for propensity score-based matching and weighting estimators frequently applied to evaluate the average treatment effect on the treated. We analyze both asymptotic approximations and bootstrap methods for computing variances and confidence intervals in our simulation designs, which are based on German register data and U.S. survey data. We vary the design w.r.t. treatment selectivity, effect heterogeneity, share of treated, and sample size. The results suggest that in general, theoretically justified bootstrap procedures (i.e., wild bootstrapping for pair matching and standard bootstrapping for “smoother” treatment effect estimators) dominate the asymptotic approximations in terms of coverage rates for both matching and weighting estimators. Most findings are robust across simulation designs and estimators.

Robust Resampling Methods for Time Series

We study the robustness of block resampling procedures for time series. We first derive a set of formulas to characterize their quantile breakdown point. For the moving block bootstrap and the subsampling, we find a very low quantile breakdown point. A similar robustness problem arises in relation to data-driven methods for selecting the block size in applications. This renders inference based on standard resampling methods useless already in simple estimation and testing settings. To solve this problem, we introduce a robust fast resampling scheme that is applicable to a wide class of time series settings. Monte Carlo simulations and sensitivity analysis for the simple AR(1) model confirm the dramatic fragility of classical resampling procedures in presence of contaminations by outliers. They also show the better accuracy and efficiency of the robust resampling approach under di®erent types of data constellations. A real data application to testing for stock return predictability shows that our robust approach can detect predictability structures more consistently than classical methods.

Breakdown Point Theory for Implied Probability Bootstrap

This paper studies robustness of bootstrap inference methods under moment conditions. In particular, we compare the uniform weight and implied probability bootstraps by analyzing behaviors of the bootstrap quantiles when outliers take arbitrarily large values, and derive the breakdown points for those bootstrap quantiles. The breakdown point properties characterize the situation where the implied probability bootstrap is more robust than the uniform weight bootstrap against outliers. Simulation studies illustrate our theoretical findings.

On Bartlett Correctability of Empirical Likelihood in Generalized Power Divergence Family

Baggerly (1998) showed that empirical likelihood is the only member in the Cressie-Read power divergence family to be Bartlett correctable. This paper strengthens Baggerlys result by showing that in a generalized class of the power divergence family, which includes the Cressie-Read family and other nonparametric likelihood such as Schennachs (2005, 2007) exponentially tilted empirical likelihood, empirical likelihood is still the only member to be Bartlett correctable.

Predictive Regression and Robust Hypothesis Testing: Predictability Hidden by Anomalous Observations

Testing procedures for predictive regressions with lagged autoregressive variables imply a suboptimal inference in presence of small violations of ideal assumptions. We propose a novel testing framework resistant to such violations, which is consistent with nearly integrated regressors and applicable to multi-predictor settings, when the data may only approximately follow a predictive regression model. The Monte Carlo evidence demonstrates large improvements of our approach, while the empirical analysis produces a strong robust evidence of market return predictability, using predictive variables such as the dividend yield, the volatility risk premium or labor income.

Predictability Hidden by Anomalous Observations

Testing procedures for predictive regressions with lagged autoregressive variables imply a suboptimal inference in presence of small violations of ideal assumptions. We propose a novel testing framework resistant to such violations, which is consistent with nearly integrated regressors and applicable to multi-predictor settings, when the data may only approximately follow a predictive regression model. The Monte Carlo evidence demonstrates large improvements of our approach, while the empirical analysis produces a strong robust evidence of market return predictability hidden by anomalous observations, both in- and out-of-sample, using predictive variables such as the dividend yield or the volatility risk premium.

Testing the Lag Structure of Assets' Realized Volatility Dynamics

A (conservative) test is constructed to investigate the optimal lag structure for forecasting realized volatility dynamics. The testing procedure relies on the recent theoretical results that show the ability of the adaptive least absolute shrinkage and selection operator (adaptive lasso) to combine efficient parameter estimation, variable selection, and valid inference for time series processes. In an application to several constituents of the SP (ii) in many cases the relevant information for prediction is included in the first 22 lags, corroborating previous results concerning the accuracy and the difficulty of outperforming out-of-sample the heterogeneous autoregressive (HAR) model; and (iii) some common features of the optimal lag structure can be identified across assets belonging to the same market segment or showing a similar beta with respect to the market index.

Oracle Properties, Bias Correction, and Inference of the Adaptive Lasso for Time Series Extremum Estimators

We derive new theoretical results on the properties of the adaptive least absolute shrinkage and selection operator (adaptive lasso) for time series regression models. In particular we investigate the question of how to conduct finite sample inference on the parameters given an adaptive lasso model for some fixed value of the shrinkage parameter. Central in this study is the test of the hypothesis that a given adaptive lasso parameter equals zero, which therefore tests for a false positive. To this end we construct a simple (conservative) testing procedure and show, theoretically and empirically through extensive Monte Carlo simulations, that the adaptive lasso combines efficient parameter estimation, variable selection, and valid finite sample inference in one step. Moreover, we analytically derive a bias correction factor that is able to significantly improve the empirical coverage of the test on the active variables. Finally, we apply the introduced testing procedure to investigate the relation between the short rate dynamics and the economy, thereby providing a statistical foundation (from a model choice perspective) to the classic Taylor rule monetary policy model.We derive new theoretical results on the properties of the adaptive least absolute shrinkage and selection operator (adaptive lasso) for time series regression models. In particular we investigate the question of how to conduct finite sample inference on the parameters given an adaptive lasso model for some fixed value of the shrinkage parameter. Central in this study is the test of the hypothesis that a given adaptive lasso parameter equals zero, which therefore tests for a false positive. To this end we construct a simple (conservative) testing procedure and show, theoretically and empirically through extensive Monte Carlo simulations, that the adaptive lasso combines efficient parameter estimation, variable selection, and valid finite sample inference in one step. Moreover, we analytically derive a bias correction factor that is able to significantly improve the empirical coverage of the test on the active variables. Finally, we apply the introduced testing procedure to investigate the relation between the short rate dynamics and the economy, thereby providing a statistical foundation (from a model choice perspective) to the classic Taylor rule monetary policy model.

Robustness of Bootstrap in Instrumental Variable Regression

This paper studies robustness of bootstrap inference methods for instrumental variable (IV) regression models. We consider test statistics for parameter hypotheses based on the IV estimator and generalized method of trimmed moments (GMTM) estimator introduced by Čížek (2008, 2009), and compare the pairs and implied probability bootstrap approximations for these statistics by applying the finite sample breakdown point theory. In particular, we study limiting behaviors of the bootstrap quantiles when the values of outliers diverge to infinity but the sample size is held fixed. The outliers are defined as anomalous observations that can arbitrarily change the value of the statistic of interest. We analyze both just- and overidentified cases and discuss implications of the breakdown point analysis to the size and power properties of bootstrap tests. We conclude that the implied probability bootstrap test using the statistic based on the GMTM estimator shows desirable robustness properties. Simulation studies endorse this conclusion. An empirical example based on Romers (1993) study on the effect of openness of countries to inflation rates is presented. Several extensions including the analysis for the residual bootstrap are provided.

Robust heart rate variability analysis by generalized entropy minimization

Typical heart rate variability (HRV) times series are cluttered with outliers generated by measurement errors, artifacts and ectopic beats. Robust estimation is an important tool in HRV analysis, since it allows clinicians to detect arrhythmia and other anomalous patterns by reducing the impact of outliers. A robust estimator for a flexible class of time series models is proposed and its empirical performance in the context of HRV data analysis is studied. The methodology entails the minimization of a pseudo-likelihood criterion function based on a generalized measure of information. The resulting estimating functions are typically re-descending, which enable reliable detection of anomalous HRV patterns and stable estimates in the presence of outliers. The infinitesimal robustness and the stability properties of the new method are illustrated through numerical simulations and two case studies from the Massachusetts Institute of Technology and Bostons Beth Israel Hospital data, an important benchmark data set in HRV analysis.