[New evidence is provided on the determinants of stock-return variances. First, when the Tokyo Stock Exchange is open on Saturday, the weekend variance increases; weekly variance is unaffected, however, despite an increase in weekly volume. Second, the listing of U.S. stocks in Tokyo substantially increases the number of trading hours, but Tokyo volume is negligible for these U.S. stocks and their 24-hour variance is unaffected. The overall results are consistent with the predictions of private-information-based rational trading models, but inconsistent with both the irrational trading noise and public-information hypotheses.]

[In a model of takeovers under asymmetric information, we identify a separating equilibrium in which the value of the bidder firm is revealed by the mix of cash and securities used as payment for the target. The model predicts that the revealed bidder value is monotonically increasing and convex in the fraction of the total offer that consists of cash. We examine the model restrictions using data from Canada, where mixed offers are both relatively frequent and free of the confounding tax-related options characterizing mixed offers in the United States. We find that the average announcement-month bidder abnormal return in mixed offers is large and significant. However, maximum likelihood estimates of parameters in both linear and nonlinear cross-sectional regressions fail to support the model predictions.]

New evidence is provided on the determinants of stock-return variances. First, when the Tokyo Stock Exchange is open on Saturday, the weekend variance increases; weekly variance is unaffected, however, despite an increase in weekly volume. Second, the listing of U.S. stocks in Tokyo substantially increases the number of trading hours, but Tokyo volume is negligible for these U.S. stocks and their 24-hour variance is unaffected. The overall results are consistent with the predictions of private-information-based rational trading models, but inconsistent with both the irrational trading noise and public-information hypotheses.

This paper studies the asymptotic properties of instrumental variable (IV) estimates of multivariate cointegrating regressions and allows for deterministic and stochastic regressors as well as quite general deterministic processes in the data-generating mechanism. It is found that IV regressions are consistent even when the instruments are stochastically independent of the regressors. This phenomenon, which contrasts with traditional theory for stationary time series, is a beneficial artifact of spurious regression theory whereby stochastic trends in the instruments ensure their relevance asymptotically. Problems of inference are also addressed and some promising new theoretical results are reported. These involve a class of Wald tests which are modified by semiparametric corrections for serial correlation and for endogeneity. The resulting test statistics which we term fully-modified Wald tests have limiting X2 distributions, thereby removing the obstacles to inference in cointegrated systems that were presented by the nuisance parameter dependencies in earlier work. Some simulation results are reported which seek to explore the sampling behaviour of our suggested procedures. These simulations compare our fully modified (semiparametric) methods with the parametric error-correction methodology that has been extensively used in recent empirical research and with conventional least squares regression. Both the fully-modified and errorcorrection methods work well in finite samples and the sampling performance of each procedure confirms the relevance of asymptotic distribution theory, as distinct from super-consistency results, in discriminating between statistical methods.

[Previous research suggests that certain benefits may derive from the method used to account for business combinations and may affect how bidding firms structure and classify corporate acquisitions. This paper investigates whether benefits derived from accounting method are reflected in bid premia for target firms. Three estimates of bid premia are examined in 95 stock-for-stock acquisitions, 59 accounted for as poolings, and 36 accounted for as purchases. Sampling restrictions, covariance analysis, and a nonparametric matched pair comparison control for potentially confounding variables identified from prior research on bid premia determinants. The results show an association between acquisition accounting method and bid premia for target firms.]

Richard J. Butler, James B. McDonald, Ray D. Nelson, Steven B. White, Robust and Partially Adaptive Estimation of Regression Models, The Review of Economics and Statistics, Vol. 72, No. 2 (May, 1990), pp. 321-327