The error structure of time series cross-section hedonic models with sporadic event timing and serial correlation

When estimating hedonic models of housing prices, the use of time series cr oss-section repeat sales data can provide improvements in estimator efficie ncy and correct for unobserved characteristics. However, in cases where ser ial correlation is present, the irregular timing of sales should also be co nsidered. In this paper we develop a model that uses information on the tim ing of events to account for the sporadic occurrence of events. The model p resumes that the serial correlation process can be decomposed into a time-i ndependent (event-wise) component and a time-dependent (time-wise) componen t. Empirical tests cannot reject the presence of sporadic correlation patte rns, while simulations show that the failure to account for sporadic correl ation leads to significant losses in efficiency, and that the losses from i gnoring sporadic correlation when it exists are larger than losses when spo radic correlation is falsely assumed. Copyright (C) 1999 John Wiley & Sons, Ltd.