This paper is concerned with evaluating value at risk estimates. It is well known that using only binary variables, such as whether or not there was an exception, sacrifices too much information. However, most of the specification tests (also called backtests) available in the literature, such as Christoffersen (1998) and Engle and Maganelli (2004) are based on such variables. In this paper we propose a new backtest that does not rely solely on binary variables. It is shown that the new backtest provides a sufficient condition to assess the finite sample performance of a quantile model whereas the existing ones do not. The proposed methodology allows us to identify periods of an increased risk exposure based on a quantile regression model (Koenker & Xiao, 2002). Our theoretical findings are corroborated through a Monte Carlo simulation and an empirical exercise with daily S&P500 time series.

This article investigates estimation of censored quantile regression (QR) models with fixed effects. Standard available methods are not appropriate for estimation of a censored QR model with a large number of parameters or with covariates correlated with unobserved individual heterogeneity. Motivated by these limitations, the article proposes estimators that are obtained by applying fixed effects QR to subsets of observations selected either parametrically or nonparametrically. We derive the limiting distribution of the new estimators under joint limits, and conduct Monte Carlo simulations to assess their small sample performance. An empirical application of the method to study the impact of the 1964 Civil Rights Act on the black-white earnings gap is considered. Supplementary materials for this article are available online.

a b s t r a c tIn this paper, we propose a novel approach to econometric forecasting of stationary and ergodic time series within a panel-data framework. Our key element is to employ the (feasible) bias-corrected average forecast. Using panel-data sequential asymptotics we show that it is potentially superior to other techniques in several contexts. In particular, it is asymptotically equivalent to the conditional expectation, i.e., has an optimal limiting mean-squared error. We also develop a zero-mean test for the average bias and discuss the forecast-combination puzzle in small and large samples. Monte-Carlo simulations are conducted to evaluate the performance of the feasible bias-corrected average forecast in finite samples. An empirical exercise, based upon data from a well known survey is also presented. Overall, these results show promise for the feasible bias-corrected average forecast.