Cointegration Vector Estimation by Panel DOLS and Long‐run Money Demand*

We study the panel dynamic ordinary least square (DOLS) estimator of a homogeneous cointegration vector for a balanced panel of N individuals observed over T time periods. Allowable heterogeneity across individuals include individual‐specific time trends, individual‐specific fixed effects and time‐specific effects. The estimator is fully parametric, computationally convenient, and more precise than the single equation estimator. For fixed N as T→∞, the estimator converges to a function of Brownian motions and the Wald statistic for testing a set of s linear constraints has a limiting χ²(s) distribution. The estimator also has a Gaussian sequential limit distribution that is obtained first by letting T→∞ and then letting N→∞. In a series of Monte‐Carlo experiments, we find that the asymptotic distribution theory provides a reasonably close approximation to the exact finite sample distribution. We use panel DOLS to estimate coefficients of the long‐run money demand function from a panel of 19 countries with annual observations that span from 1957 to 1996. The estimated income elasticity is 1.08 (asymptotic s.e. = 0.26) and the estimated interest rate semi‐elasticity is ?0.02 (asymptotic s.e. = 0.01).     

Initial Public Offerings: CFO Perceptions

We examine four issues pertaining to initial public offerings (IPOs) using a survey of 438 chief financial officers (CFOs). First, why do firms go public? Second, is CFO sentiment stationary across bear and bull markets? Third, what concerns CFOs about going public? Fourth, do CFO perceptions correlate with returns? Results support funding for growth and liquidity as the primary reasons for IPOs. CFO sentiment is generally stationary in pre‐ and post‐bubble years. Managers are concerned with the direct costs of going public, such as underwriting fees, as well as indirect costs. We find a negative relation between a focus on immediate growth and long‐term abnormal returns.     

Are differences in firm size transitory or permanent?

An Erratum for this article has been published in Journal of Applied Econometrics 18(2) 2003, 249 Previous empirical work on corporate growth rates using cross‐section or short‐panel econometric techniques suggests that growth rates are random but that some degree of mean reversion exists. This means that size differences between firms are transitory. Another, more natural way to explore the long‐run distribution of firm sizes is to examine data on the growth of particular firms over long periods of time. Using a sample of 147 UK firms observed continually for more than 30 years, our conclusions are that growth rates are highly variable over time and that differences in growth rates between firms do not persist for very long. Further, firms show no tendency to converge to either a common size or to a pattern of stable size differences over time. These results are compared and contrasted with standard approaches that suggest that firms reach and maintain stable positions in a skewed size distribution. Copyright © 2002 John Wiley & Sons, Ltd.     

Liquidity, Labels and Medium-Term Notes

We suggest that the medium-term note market provides an excellent laboratory for exploring the relationships between yield, liquidity, and the label affixed to a financial instrument. Crabbe and Turner (1995) examined the liquidity issue and uncovered the counter-intuitive result that issue size is unrelated to liquidity. Their study failed to examine a potential channel for a liquidity effect, however, in the form of multiple issues from a single, typically large, MTN registration filing. We find evidence that file size is significantly related to yield in a number of instances. Several other proxies for liquidity, such as frequency of issue, are also sometimes significantly related to yields. Contrary to Crabbe and Turner (1995) , we find that labeling a security an MTN can have an impact on its yield. The label "note" also appears to matter for yield in some instances.     

Long- and short-term interest rates in 19 countries: Tests of cointegration and parameter instability

This paper examines the long-run relationship between short-term and long-term interest rates (both nominal and real) in 19 countries, and explores the possibility that the relationship is statistically stable using Lc, MeanF, and SupF statistics suggested by Hansen [1992]. Empirical results obtained from various cointegration techniques (Johansen, Phillips and Hansen, Stock and Watson, and Park) and quarterly data (1973–1998) show considerable support for the expectations hypothesis in all countries (except the United Kingdom). In a majority of cases, it is also found that a stable relationship exists between the short-term and long-term interest rates.