Motivated by prediction problems for time series with heavy-tailed marginal distributions, we consider methods based on 'local least absolute deviations' for estimating a regression median from dependent data. Unlike more conventional 'local median' methods, which are in effect based on locally...

Commercial real estate represents a significant fraction of total U.S. wealth, but its risk and returns at the property level are largely unknown. This paper utilizes detailed cash flow information of 2,845 commercial properties acquired for about $89 billion by institutional investors of NCREIF...

This paper develops a novel empirical method that uses property level cash flow information to estimate the risk and return characteristics of private commercial real estate. Monte Carlo simulations suggest that this method is more accurate than the conventional index-based approach. Applying...

For an AR(1) process with ARCH(1) errors, we propose empirical likelihood tests for testing whether the sequence is strictly stationary but has infinte variance, or the sequence is an ARCH(1) sequence or the sequence is an iid sequence. Moreover, an empirical likelihood based confidence interval...