Many panel data sets encountered in macroeconomics, international economics, regional science, and finance are characterized by cross-sectional or “spatial” dependence. Standard techniques that fail to account for this dependence will result in inconsistently estimated standard errors. In this paper we present conditions under which a simple extension of common nonparametric covariance matrix estimation techniques yields standard error estimates that are robust to very general forms of spatial and temporal dependence as the time dimension becomes large. We illustrate the relevance of this approach using Monte Carlo simulations and a number of empirical examples.

Macroeconomists have for some time been aware that the New Keynesian Phillips curve, though highly popular in the literature, cannot explain the persistence observed in actual inflation. We argue that one of the more prominent alternative formulations, the Fuhrer and Moore (1995) relative contracting model, is highly problematic. Fuhrer and Moore's 1995 formulation generates inflation persistence, but this is a consequence of their assuming that workers care about the past real wages of other workers. Making the more reasonable assumption that workers care about the current real wages of other workers, one obtains the standard formulation with no inflation persistence.

We examine the real effects of changes in bank mortgage loan underwriting standards by combining responses to the Federal Reserve’s Senior Loan Officer Opinion Survey, application information from the Home Mortgage Disclosure Act, and local housing market measures over 1990 to 2013. Tightened standards are associated with a 1 percentage point increase in denial rates and a 5% fall in loan issuance, controlling for applicant pool changes, but no change for predominantly-securitizing banks. In areas with more exposure to banks that have tightened standards, mortgage delinquency rates, house prices, new home sales, and residential construction employment fall substantially.

The increasing average distance between small businesses and their lenders has been used to argue that technological changes have allowed banks to lend at longer distances. Generally, studies assume that distance changes are uniform across loans and lenders. Our paper shows that, while average distance has increased substantially over the past two decades, banks themselves have not materially increased their lending distances. Instead, longer average distance was caused by a small number of banks that specialize in originating very small loans nationwide quadrupling their share of lending. Outside of these very small loans, small businesses remain dependent on local banks.