Fraud companies had a directors on both committees. Pairwise differences show no significant difference in the frequency of board meetings or meetings of audit, compensation,and nominating committees.Overall, the pairwise comparisons suggest that systematic differences between fraud companies and no-fraud matching companies are apparent in certain characteristics of the boards of directors.These univariate comparisons should be viewed with caution, however, when making inferences about the connection between governance attributes and corporate fraud. The pairwise tests implicitly assume that other potentially relevant company characteristics are fixed, which may not be the case.For this reason, we used a logit regression to test our hypotheses in a multivariate
原作者求助内容