A Comparative Analysis of Firms Included in and Excluded from the NAARS Database

Abstract

In this paper we provide evidence on the representativeness of the NAARS database by comparing various characteristics of COMPUSTATI CRSP domestic industrial firms included in the database (included firms) to characteristics of otherwise similar firms that are not included (excluded firms). Our analysis covers both 1985 and 1990 and, although somewhat sensitive to the year analyzed and exchange listing, the results suggest that excluded firms tend to be smaller, with higher probabilities of both bankruptcy and qualified opinions; they are also more likely to be audited by a non-Big-Eight firm. The NAARS database is often used to select firms based on some nonnumerical characteristic such as a modified audit opinion or a specific footnote disclosure. Ball and Foster [1982] suggest that using NAARS results in larger and possibly more representative samples, while others note that samples drawn from the NAARS database may not be representative (Bowen and Noreen [1981], Elliott [1982], and Bell and Tabor [1991]). Representativeness affects the generalizability of empirical research results. Since accounting and auditing research often has potential implications for policy decisions, it is important to ensure adequate representation of the population of interest so that appropriate conclusions