Pension plan termination, Financial slack, Overfunded pension funds

[Many accounting studies examine dichotomous choices (e.g., qualify/do not qualify an audit opinion or capitalize/do not capitalize a cost). These studies often involve small overall sample sizes, disparate response group sizes, and predictor variables that are skewed and collinear. These factors can cause distributional problems in test statistics for logit (or probit) regression models, which can lead to incorrect inferences. However, few empirical benchmarks exist for assessing the effect of these factors. The current paper determines how response group size and the number, distribution, and correlation of predictor variables affect empirical error rates and the minimum required sample size for using logit. Comparisons are made with the error rates obtained from an ordinary least squares (OLS) linear probability model, an alternative that has been suggested for small sample studies. Because accounting researchers choosing between logit and OLS may be concerned with more than the calibration of the models' test statistics, comparisons of the sensitivity of logit and OLS parameter estimates to the range of data sampled for the predictor variables and of the models' classificatory ability also are made. Both simulated and real accounting data are used. The results of Monte Carlo simulations show that logit test statistics are biased when the sample size is small. However, much of the bias is attributable to the skewness of the predictor variables, a problem that is characteristic of accounting research and that also affects OLS test statistics. In such settings, OLS may result in test statistics that are minimally better calibrated. The parameter estimates of the model, however, will be more sensitive to the sampling frame. Furthermore, experimentation with data on auditors' Statement No. 87 consistency judgments indicates that OLS also may result in higher Type I error rates when it is used for prediction or classification. These results are interpreted as indicating that, even for sample sizes as small as 50, logit rather than OLS still may be the preferable model for accounting choice studies.]

Many accounting studies examine dichotomous choices (e.g., qualify/do not qualify an audit opinion or capitalize/do not capitalize a cost). These studies often involve small overall sample sizes, disparate response group sizes, and predictor variables that are skewed and collinear. These factors can cause distributional problems in test statistics for logit (or probit) regression models, which can lead to incorrect inferences. However, few empirical benchmarks exist for assessing the effect of these factors. The current paper determines how response group size and the number, distribution, and correlation of predictor variables affect empirical error rates and the minimum required sample size for using logit. Comparisons are made with the error rates obtained from an ordinary least squares (OLS) linear probability model, an alternative that has been suggested for small sample studies. Because accounting researchers choosing between logit and OLS may be concerned with more than the calibration of the models' test statistics, comparisons of the sensitivity of logit and OLS parameter estimates to the range of data sampled for the predictor variables and of the models' classificatory ability also are made. Both simulated and real accounting data are used. The results of Monte Carlo simulations show that logit test statistics are biased when the sample size is small However, much of the bias is attributable to the skewness of the predictor variables, a problem that is characteristic of accounting research and that also affects OLS test statistics. In such settings, OLS may result in test statistics that are minimally better calibrated. The parameter estimates of the model, however, will be more sensitive to the sampling frame. Furthermore experimentation with data on auditors' Statement No. 87 consistency judgments indicates that 01$ also may result in higher Type I error rates when it is used for prediction or classification These results are interpreted as indicating that, even for sample sizes as small as 50, log it rather than OLS still may be the preferable model for accounting choice studies.

The FASB has issued computer data tapes for both pension disclosures and inflation-adjusted amounts. This note reports the results of a comparison of a sample of data from the FASB data tapes with amounts from the annual reports. This study warns future users of the tapes of potential pitfalls in their use. All errors have been reported to the FASB for their use in updating the tapes.

Reviews the book "Financial Reporting by Private Companies: Analysis and Diagnosis," by A. Rashad Abdel-Khalik.

Reviews the book "Illustrations and Analysis of Disclosures of Pension Information," by Hortense Goodman, Frank C. Munn, Anthony Phillips and Miklos Vasarhelyi.

Reviews the book "Fundamentals of Private Pensions," by Dan M. McGill.

The SEC encourages companies to have their quarterly financial information reviewed by an independent accountant prior to filing Forms 10-Q (i.e., timely review). Many companies, however, choose to have their quarterly data reviewed only at year-end. Companies contracting for timely reviews are hypothesized to be seeking a higher level of monitoring because of higher internal and external agency costs. Empirical analyses support this hypothesis. The likelihood that a company purchases timely reviews is significantly associated with several proxies for internal and external agency costs.