This paper hypothesizes that the quit propensity of married men rises with an increase in their wives' income. Assuming that individuals are risk averse and that quitting is risky, the wife's income increases the husband's expected value of quitting by reducing the variance of expected family income. Using the longitudinal data from the Michigan Panel Study of Income Dynamics (PSID), the wife's income is found to have a large effect on quits. The average husband's quit rate increases by about 45% when the wife's income rises from zero to two-thirds that of the husband's. The wife's income effect nearly offsets the negative effect that marriage typically has on male quit rates.

This paper provides a framework and some empirical evidence to evaluate the seriousness of problems in inference that arise in stockreturn-based studies when the data are cross-sectionally dependent. The study is motivated on the grounds that statistical procedures designed to address such problems are often infeasible, and even when they can be implemented they sometimes introduce other more serious difficulties. Thus, researchers have frequently adopted an approach that ignores the cross-sectional dependence (e.g., ordinary least squares [OLS]). The objective of this paper is to help identify the contexts in which ignoring the dependence would lead to serious misstatement of significance levels. Cross-sectional dependence in stock returns data is likely to exist when at least some of the returns are sampled from common time periods. This would be the case in all studies of the reaction of stock prices to a

Inventory accounting method, LIFO, Event dates, Announcement returns

We hypothesize that past strike experience will have a negative or "teetotaler" effect on a collective bargaining unit's propensity to strike in future negotiations, other things being equal. We test this using a unique micro-level sample comprising four consecutive negotiations by 147 bargaining units in U.S. manufacturing industries, controlling for observable and unobservable differences among bargaining pairs in the propensity to strike. Our results are consistent with the view that the experience of striking is, indeed, sobering: lagged strike experience variables have a significantly negative effect on the propensity to strike in the current negotiation.

Abstract. A Bayesian model for nonsampling errors made by the auditor is investigated to determine the effects of such errors on audit inferences. Predictive distributions are used to illustrate that for “realistic” audit situations, Type II errors will have little effect on inferences for a given level of Type I error. Type I errors are shown to play a more critical role in determining the acceptability of an internal control. Résumé. Un modèle Bayesien relatif aux erreurs, de nature autre qu'échantillonnale, commises par le vérificateur est étudié afin de déterminer les effets de telles erreurs sur les inférences en vérification. Des distributions de prédiction sont employées pour illustrer le fait qu'en situation de vérification «réaliste», les erreurs de deuxième espèce auront peu d'effet sur les inférences pour un niveau donné d'erreur de première espèce. Il est montré que les erreurs de première espèce jouent un rôle plus critique en ce qui a trait à la détermination du caractère acceptable d'un procédé de contrôle interne.

Don L. Coursey, John L. Hovis, William D. Schulze; The Disparity Between Willingness to Accept and Willingness to Pay Measures of Value*, The Quarterly Jou

Despite the critical analysis of Pagan (1984) and several subsequent applied studies, empirical models characterized by expectations are often estimated with regressor proxies that are treated as ordinary nonstochastic This paper offers a Generalized Least Squares estimator designed to cope with the nonscalar disturbance matrix precipatated by generated The approach is designed as a natural extension of Pagan's analysis and the author demonstrates how it may be applied to multi-equation models. Experimentation with numerical examples reveals the potential severity of ignoring the problem. These results also suggest an easily calculated indicator of potential inference distortion in models that fail to account for regressors. Copyright 1987 by MIT Press.

Recently, Watson and Engle (1985) considered the problem of testing for a constant regression coefficient against the alternative hypothesis that the coefficient follows a stationary first-order autoregressive process. This alternative is the return to normalcy model proposed by Rosenberg (1973). Watson and Engle observe that the unknown autoregressive parameter is not identified under their null hypothesis and they suggest the use of the test procedure proposed by Davies (1977) for such situations. Davies' approach involves applying Roy's Union-Intersection Principle to the class of test statistics one gets by assuming the non-identified parameter takes a known value. Unfortunately, Watson and Engle's test statistic has no closed form and is approximated by maximisation using a grid search. Furthermore, both its finite sample and asymptotic distributions are unknown under the null hypothesis although they do provide a method of calculating a critical value whose asymptotic size can be bounded from above. In this note we suggest a different approach that helps overcome these problems. Rather than testing for zero variance in the autoregressive process as Watson and Engle suggest, we propose testing for lack of variation in the regression coefficient over time. This allows the construction of a locally best invariant (LBI) test using the results of King and Hillier (1985). Because the resultant test statistic is a ratio of quadratic forms in normal variables, standard computational techniques can be used to calculate exact and approximate critical values. A further advantage of this alternative test is that it is also LBI against the hypothesis that the coefficient follows a random walk process.