Measurement error and panel data1

The underidentification of linear models with measurement error does not necessarily extend to panel data models, as has been shown by GAiliches and Hausman (1986). We discuss and extend some of their results for a simple case and address particular issues concerning identification and asymptotic variances.     

A note on securities market response to pension fund termination*

Abstract. A recent article in this journal (Hsieh, Ferris, and Chen, 1990) presents evidence demonstrating that financially distressed firms that terminate overfunded pension plans experience significantly positive abnormal returns, while nondistressed terminating firms experience returns not different from zero. The article concludes from this evidence that the market regards the property rights to excess assets as residing fully with the sponsoring firm prior to termination, particularly when the sponsoring firm is not financially distressed. Accordingly, the reporting requirements of Statement of Financial Accounting Standards (SFAS) No. 88, which require immediate recognition of gains resulting from termination, are inconsistent with the market's view of the ownership rights to excess plan assets. Similarly, the article suggests that the excise tax imposed on asset reversions is “punitive” because property rights to fund assets resided with the company prior to termination. This paper questions three aspects of the Hsieh, Ferris, and Chen article: (1) the plausibility of the theory explaining differential reaction to the announcement to terminate for distressed and nondistressed firms; (2) the effect of the distressed/nondistressed classification criteria, event date specification, and event window length on the results; and (3) the appropriateness of using the empirical results, if reliable, to evaluate accounting treatment or federal tax policy. Résumé. Dans un récent article paru dans cette même publication, Hsieh, Ferris et Chen (1990) soumettaient des faits démontrant que les entreprises en difficulté financière qui mettent fin à un régime de retraite surprovisionné enregistrent des rendements anormaux positifs importants, tandis que les entreprises qui mettent fin à un régime de retraite sans être en difficulté financière enregistrent des rendements qui ne sont pas différents de zéro. De là, les auteurs concluaient que le marché estime que les droits à l'excédent d'actif appartiennent exclusivement à l'entreprise responsable du régime avant la cessation, en particulier lorsque cette dernière n'est pas en difficulté financière. Par conséquent, les exigences de la norme SFAS No. 88 en matière d'information à fournir, qui prévoient la constatation immédiate du produit de la cessation du régime, ne sont pas conformes à la façon de voir du marché relativement aux droits à l'excédent d'actif du régime. De la même façon, selon les auteurs, la taxe d'accise imposée en cas de retour de l'actif est “punitive”, étant donné que les droits à l'actif du régime appartenaient à l'entreprise avant la cessation du régime. Les auteurs s'interrogent ici sur trois aspects de l'article de Hsieh, Ferris, et Chen: 1) la pertinence de la théorie expliquant la réaction marginale à l'annonce de la cessation d'un régime pour les entreprise qui sont en difficulté financière et celles qui ne le sont pas; 2) l'incidence sur les résultats des critères permettant de classer les entreprises comme étant en difficulté financière ou ne l‘étant pas, de la précision de la date de l’événement et de la longueur de la période pré-post relative à l‘événement; et 3) l'opportunité de l'utilisation des résultats empiriques, s'ils sont fiables, pour évaluer le traitement comptable ou la politique fiscale fédérale.     

VARIANCE BOUND TESTS OF BOND MARKET EFFICIENCY

In this paper we examine variance bound tests of the joint hypothesis that (1) bond markets are efficient and (2) the term structure is determined by the expectations hypothesis. Both the Singleton and Shiller tests are shown to be seriously biased toward rejecting the joint hypothesis in finite samples. Flavin's test is unbiased but has a very high variance leading to many false rejections of the joint hypothesis. When corrected as suggested by Flavin, Shiller's test is unbiased and has a relatively low variance. Unfortunately, it is also sensitive to measurement error.     

THE EFFECTS OF THE INSIDER TRADING SANCTIONS ACT OF 1984: THE CASE OF SEASONED EQUITY OFFERINGS

Previous empirical research indicates that corporate insiders tend to increase (decrease) their shareholdings before events that increase (decrease) firm value. More recent evidence suggests, however, that passage of the Insider Trading Sanctions Act of 1984 (ITSA) may have deterred this behavior. Our results indicate that before passage of the ITSA, insiders exploited their access to nonpublic information by selling shares before the announcement of equity issues. However, after passage of the ITSA insiders no longer displayed this behavior. We conclude the ITSA has a deterrent effect, which is more heavily concentrated on insiders at the highest level of the firm who are most visible to regulators and other market participants.     

Improved estimation of portfolio value‐at‐risk under copula models with mixed marginals

Portfolio value‐at‐risk (PVAR) is widely used in practice, but recent criticisms have focused on risks arising from biased PVAR estimates due to model specification errors and other problems. The PVAR estimation method proposed in this article combines generalized Pareto distribution tails with the empirical density function to model the marginal distributions for each asset in the portfolio, and a copula model is used to form a joint distribution from the fitted marginals. The copula–mixed distribution (CMX) approach converges in probability to the true marginal return distribution but is based on weaker assumptions that may be appropriate for the returns data found in practice. CMX is used to estimate the joint distribution of log returns for the Taiwan Stock Exchange (TSE) index and the associated futures contracts on SGX and TAIFEX. The PVAR estimates for various hedge portfolios are computed from the fitted CMX model, and backtesting diagnostics indicate that CMX outperforms the alternative PVAR estimators. © 2006 Wiley Periodicals, Inc. Jrl Fut Mark 26:997–1018, 2006     

Adjustment costs and time-to-build in factor demand in the U.S. manufacturing industry

In order to explain cyclical behavior of factor demand, the static neoclassical model of the firm has been extended to include either adjustment costs (e.g. Lucas (1967)) or time-to-build considerations as in Kydland and Prescott (1982). This paper presents an intertemporal factor demand model which accounts for adjustment costs and gestation lags. The closed form solution of the model is a highly restricted vector ARMA-process that is estimated using quarterly data for the manufacturing industry in the U.S., 1960–1988. The main conclusion is that both sources of dynamics of factor demand are identifiable and found to be empirically of importance.     

Empirical Implications of Equilibrium Bidding in First-Price, Symmetric, Common Value Auctions

This paper studies federal auctions for wildcat leases on the Outer Continental Shelf from 1954 to 1970. These are leases where bidders privately acquire (at some cost) noisy, but equally informative, signals about the amount of oil and gas that may be present. We develop tests of rational and equilibrium bidding in a common values model that are implemented using data on bids and ex post values. We also use data on tract location and ex post values to test the comparative static prediction that bidders may bid less aggressively in common value auctions when they expect more competition. We find that bidders are aware of the "winner's curse" and their bidding is largely consistent with equilibrium.