It is common in econometric applications that several hypothesis tests are carried out at the same time. The problem then becomes how to decide which hypotheses to reject, accounting for the multitude of tests. In this paper, we suggest a stepwise multiple testing procedure which asymptotically controls the familywise error rate at a desired level. Compared to related single-step methods, our procedure is more powerful in the sense that it often will reject more false hypotheses. In addition, we advocate the use of studentization when it is feasible. Unlike some stepwise methods, our method implicitly captures the joint dependence structure of the test statistics, which results in increased ability to detect alternative hypotheses. We prove our method asymptotically controls the familywise error rate under minimal assumptions. We present our methodology in the context of comparing several strategies to a common benchmark and deciding which strategies actually beat the benchmark. However, our ideas can easily be extended and/or modified to other contexts, such as making inference for the individual regression coefficients in a multiple regression framework. Some simulation studies show the improvements of our methods over previous proposals. We also provide an application to a set of real data.

A new method is proposed for constructing confidence intervals in autoregressive models with linear time trend. Interest focuses on the sum of the autoregressive coefficients because this parameter provides a useful scalar measure of the long-run persistence properties of an economic time series. Since the type of the limiting distribution of the corresponding OLS estimator, as well as the rate of its convergence, depend in a discontinuous fashion upon whether the true parameter is less than one or equal to one (that is, trend-stationary case or unit root case), the construction of confidence intervals is notoriously difficult. The crux of our method is to recompute the OLS estimator on smaller blocks of the observed data, according to the general subsampling idea of Politis and Romano (1994a), although some extensions of the standard theory are needed. The method is more general than previous approaches in that it works for arbitrary parameter values, but also because it allows the innovations to be'-a martingale difference sequence rather than i.i.d .. Some simulation studies examine the finite sample performance.

How do auditors behave during periods of market euphoria? To address this question, we study auditor going-concern opinions around the time of the wave of stressed Internet companies filing to go public on Nasdaq, a period many characterize as the ‘dot com bubble’. We focus on the day the auditor signs the opinion that appears in a stressed, Internet registrants’ IPO filing and document a sharp increase in the number of opinions with dates between January 1999 and April 2000. Contemporaneous with this jump in transaction volume, and for the duration of these 16-months, Big 5 firms were less likely to render going-concern opinions to their stressed, Internet IPO registrant clients. Upon conducting tests for determinants that could lead auditors to shift their decision criteria during this euphoric audit market, we find the presence of a going-concern opinion varies with variables that proxy for client reasons (financial distress, company age, venture backing, IPO cash burn) and for less auditor independence/skepticism (recent fees for clients without venture backing and a rush-to-market for clients with venture backing) by the Big 5 firms. These findings suggest a mixed conclusion regarding the Big 5's behavior; as the presence of a going-concern opinion varies inversely with variables that proxy for both client viability and auditor self interest. As for consequences to investors, our analysis of two, three and four-year post-IPO stock delisting provides some evidence of a decrease in the predictive content (early-warning value) of Big 5 opinions signed during the Internet IPO bubble.

We use the IPO setting to examine the relation between auditor exposure to legal liability and audit quality and audit fees. With regard to audit quality, we report robust evidence that pre-IPO audited accruals are negative and less than post-IPO audited accruals. In contrast to extant literature, our findings provide scant support for the inference that auditors acquiesce to opportunistic earnings management by issuers in an attempt to increase the offering price. With regard to audit fees, we find auditors earn higher fees for IPO engagements than post-IPO engagements. While inherent differences in auditor responsibilities between IPO audits and post-IPO audits should lead to higher fees for IPOs, a substantial portion of IPO audit fees (in levels and changes) is associated with our proxy for the auditor’s 1933 Act exposure. Overall, our results suggest that both audit quality and audit fees are higher in a higher-litigation regime, consistent with the effects an increase in litigation exposure should have on auditor incentives.