Improving Tests of Abnormal Returns by Bootstrapping the Multivariate Regression Model with Event Parameters

Parametric dummy variable-based tests for event studies usingmultivariate regression are not robust to nonnormality of theresidual, even for arbitrarily large sample sizes. Bootstrapalternatives are described, investigated, and compared for caseswhere there are nonnormalities, and cross-sectional and time-seriesdependencies. Independent bootstrapping of residual vectorsfrom the multivariate regression model controls type I errorrates in the presence of cross-sectional correlation, and surprisingly,even in the presence of time-series dependence structures. Theproposed methods not only improve upon parametric methods, butalso allow development of new and powerful event study testsfor which there is no parametric counterpart.     

Can Mutual Fund “Stars” Really Pick Stocks? New Evidence from a Bootstrap Analysis

We apply a new bootstrap statistical technique to examine the performance of the U.S. open‐end, domestic equity mutual fund industry over the 1975 to 2002 period. A bootstrap approach is necessary because the cross section of mutual fund alphas has a complex nonnormal distribution due to heterogeneous risk‐taking by funds as well as nonnormalities in individual fund alpha distributions. Our bootstrap approach uncovers findings that differ from many past studies. Specifically, we find that a sizable minority of managers pick stocks well enough to more than cover their costs. Moreover, the superior alphas of these managers persist.     

Multivariate Lagrange Multiplier Tests for Fractional Integration

We introduce a multivariate Lagrange multiplier (LM) test forfractional integration. We derive and analyze the LM statisticand show that it is asymptotically noncentral chi-squared distributedunder local alternatives, and that, under Gaussianity, the LMtest is asymptotically efficient against local alternatives.It is shown that the regression variant in Breitung and Hassler(2002, Journal of Econometrics 110, 167–185) is not equivalentto the LM test in the multivariate case, although it is in theunivariate case. A generalization of the LM test that explicitlyallows for different integration orders for each variable isalso introduced. The finite sample properties of the LM testare evaluated by Monte Carlo experiments which demonstrate thatit is superior to the Breitung and Hassler (2002) test. An applicationto multivariate time series of real interest rates for six countriesis offered, demonstrating that more clear-cut evidence can bedrawn from multivariate tests compared to conducting severalunivariate tests.     

A Monte Carlo investigation of the accuracy of multivariate CAPM tests

In a multivariate regression model relating individual returns to the market return, CAPM implies non-linear restrictions on the parameters. Several asymptotically valid tests of these restrictions have been suggested. The existing Monte Carlo evidence shows that some of these tests are unreliable for reasonable sample sizes, but does not indicate well which tests are reliable. This paper reports the results of an extensive Monte Carlo experiment. Shanken's CSR test and Jobson and Korkie's corrected likelihood ratio test are quite accurate in all cases we consider.     

Pricing currency risk in the stock market: Evidence from Finland and Sweden 1970-2009

We investigate the role of currency risk on stock markets in two interlinked Nordic countries exhibiting a gradual move from fixed to floating exchange rates. We apply the Ding and Engle (2001) covariance stationary specification in a multivariate GARCH-M setup to test a conditional international asset pricing model. Using a sample period from 1970 to 2009, we find that the currency risk is priced in both stock markets, and that the price and the risk premium are lower after the floatation of the currencies, especially for Finland. We also find the cross-country exchange rate shock from Finland to affect the price of currency risk in Sweden, but not vice versa. Finally, we discuss some of the potential issues in applying multivariate GARCH-M specifications in tests of asset pricing models.     

CAP Forum on Enron: Former Audit Firm Personnel as CFOs: Effect on Earnings Management*

Corporate hiring of former audit personnel to fill key financial positions is a practice that has attracted attention from the media, the accounting profession, and regulators. The concern is that the former external auditor who now holds a key position with the client may be able to circumvent the audit or exert pressure on the audit team and adversely influence audit quality. We compare a sample of 172 test companies that appointed to the position of chief financial officer (CFO) personnel who are former employees of the companies' auditors, with a control sample of companies that appointed new CFOs who were not affiliated with their auditors. We investigate whether the level of discretionary accruals is greater for the test sample compared with the control sample during the two years following appointment of the CFO. Both univariate and multivariate results for signed discretionary accruals suggest some support for the hypothesis that firms with affiliated CFOs are associated with greater earnings management than firms with unaffiliated CFOs. Furthermore, the results for signed discretionary accruals suggest that the association is stronger for nonpartners who moved from the audit firm to the client with little or no time gap. On average, the results for absolute discretionary accruals do not suggest differences in earnings management between affiliated and unaffiliated CFOs. However, they do indicate some earnings management relative to unaffiliated CFOs by CFOs who had little or no time gap between leaving the audit firm and joining the client firm, although at a weaker level of significance.     

Market power and firm risk: A test of the ‘quiet life’ hypothesis

This paper presents an empirical investigation of John R. Hicks' ‘quiet life’ hypothesis that firms in monopolistic markets will be more risk averse than firms in competitive markets. A sample of 6,500 unit banks is used in a multivariate regression analysis to test the relationship between market concentration and overall risk measured by the coefficient of variation, as well as certain financial ratios. Financial data are for the years 1969–1978. Test results are consistent with Hicks' ‘quiet life’ hypothesis. It is also notable that while most structure-performance studies in banking have found a quantitatively small effect of structure on performance, these results suggest that the effect may be fairly substantial.     

沪深300股指期货与现货市场间风险传染效应及影响因素

本文选取2005—2019年我国沪深300股指期货和沪深300股票指数日收盘价数据,结合股票推出时间、股价波动性,设置样本组、对照组,运用GARCH模型、DCC-GARCH模型、Granger因果关系检验及多元线性回归模型分析了沪深300股指期货与现货间的风险传染效应及影响因素,并结合研究结论提出对策,以期促进资本市场健康发展。结果表明:沪深300股指期货市场与现货市场间存在双向的风险传染效应,且经DCC-GARCH模型分析表明风险传染效应在动荡期尤为明显;影响这种风险传染效应的因素有很多,主要表现为微观因素中的股票市场流动性和股票市场不确定性与极端事件两个方面。     

A LIKELIHOOD RATIO TEST OF THE ZERO-BETA CAPM IN AUSTRALIAN EQUITY RETURNS

This paper tests the zero-beta CAPM with Australian equity returns, using the multivariate approach developed by Gibbons (1982). For the period 1958 to 1987, based on its asymptotic distribution, the likelihood ratio test (LRT) statistic indicates a strong rejection of the model when an equally weighted market index is used. However, small sample adjustments to the test suggested by Jobson and Korkie (1982) and by Shanken (1985) place the validity of this conclusion in some doubt. When a value weighted market index is used for the period 1974 to 1987, the tests reveal at least moderate support for the zero-beta CAPM.     

Long memory in the high frequency cryptocurrency markets using fractal connectivity analysis: The impact of COVID-19

In this paper, we study the long memory behavior of the hourly cryptocurrency returns during the COVID-19 pandemic period. Initially, we apply different tests against the spurious long memory, with the results indicating the presence of true long memory for most cryptocurrencies. Yet, using the multivariate test, the series are found to be contaminated by level shifts or smooth trends. Then, we adopt the wavelet-based multivariate long memory approach suggested by Achard and Gannaz (2016) to model their long memory connectivity. The findings indicate a change in persistence for all series during the sample period. The fractal connectivity clustering indicates a similarity among Ethereum (ETH) and Litecoin (LTC), Monero (XMR), Bitcoin (BTC), and EOC token (EOS), while Stellar (XLM) is clustered away from the remaining series, indicating the absence of any interdependence with other crypto returns. Overall, shocks arising from COVID-19 crisis have led to changes in long-run correlation structure.     

Multivariate geometric expectiles

A generalization of expectiles for d-dimensional multivariate distribution functions is introduced. The resulting geometric expectiles are unique solutions to a convex risk minimization problem and are given by d-dimensional vectors. They are well behaved under common data transformations and the corresponding sample version is shown to be a consistent estimator. We exemplify their usage as risk measures in a number of multivariate settings, highlighting the influence of varying margins and dependence structures.     

Regulatory changes,market integration and spillover effects in the Chinese A,B and Hong Kong equity markets

We document the changes in dynamic stochastic structure of the various industrial sectors of the Chinese A, B and the Hong Kong share markets. We utilize a robustly estimated vector error correction model with multivariate generalized autoregressive conditionally heteroscedasticity (VECM-MV-GARCH) model to test for possible cointegrating vectors between the market segmentations pre and post deregulation of the Chinese B share market. Our results suggest that before deregulation there is weak evidence of cointegration between the A and B share markets. However, post deregulation the situation changes and the segments appear to be significantly cointegrated. MV-GARCH results suggest that the conditional correlations of market/sector shocks also increase significantly over the sample period.     

A CROSS-SECTIONAL REGRESSION TEST OF THE MEAN-VARIANCE EFFICIENCY OF AN AUSTRALIAN VALUE WEIGHTED MARKET PORTFOLIO

This paper tests the Mean-Variance efficiency of a value weighted Australian market portfolio using a multivariate cross-sectional regression approach developed by Shanken (1985). This test methodology is sufficiently powerful to reject the null hypothesis that the market portfolio is ex ante Mean-Variance efficient when test assets are constructed on the basis of size (market capitalisation). However, when test assets are constructed on the basis of industry classification the model is unable to reject the Mean-Variance efficiency of the market portfolio. This test statistic provides some useful diagnostics which are examined in the paper.     

Multivariate GARCH hedge ratios and hedging effectiveness in Australian futures markets

We use the All Ordinaries Index and the corresponding Share Price Index futures contract written against the All Ordinaries Index to estimate optimal hedge ratios, adopting several specifications: an ordinary least squares‐based model, a vector autoregression, a vector error‐correction model and a diagonal‐vec multivariate generalized autoregressive conditional heteroscedasticity model. Hedging effectiveness is measured using a risk‐return comparison and a utility maximization method. We find that time‐varying generalized autoregressive conditional heteroscedasticity hedge ratios perform better than constant hedge ratios in terms of minimizing risks, but when return effects are also considered, the utility‐based measure prefers the ordinary least squares method in the in‐sample hedge, whilst both approaches favour the conditional time‐varying multivariate generalized autoregressive conditional heteroscedasticity hedge ratio estimates in out‐of‐sample analyses.     

Multivariate tests of the zero-beta CAPM

A ‘cross-sectional regression test’ (CSRT) of the CAPM is developed and its connection to the Hotelling T² test of multivariate statistical analysis is explored. Algebraic relations between the CSRT, the likehood ratio test and the Langrange multiplier test are derived and a useful small-sample bound on the distribution function of the CSRT is obtained. An application of the CSRT suggests that the CRSP equally-weighted index is inefficient, but that the inefficiency is not explained by a firm size-effect from February to December.     

Bootstrap Tests for Multivariate Event Studies

Statistical tests for multivariate event studies—exact or asymptotic—are derived based on multivariate normality. As it has been previously documented that the performances of these tests are not satisfactory, because stock returns are far from normally distributed (especially for daily returns), this paper proposes the use of bootstrap methods, which are free from any specific distributional assumption, to provide better approximations to the sampling distributions of test statistics in multivariate event studies. The Monte Carlo experiments based on real daily returns data show that the bootstrap tests outperform the traditional tests by having close rejection rates to the nominal significance levels. The traditional tests, in contrast, tend to reject the null hypotheses too often.     

Deviations from Purchasing Power Parity

This study uses univariate and multivariate unit root tests to analyze the random walk behavior of real exchange rates for the period 1979–1989. The univariate test fails to reject the random walk model, but the multivariate test indicates that part of the real exchange rates is predictable, a result supporting purchasing power parity. Further analysis of the random walk component in real exchange rates shows that it is quite persistent: for all currencies it takes about five to eight years for this shock to diminish to half its size.     

Using client performance measures to identify pre-engagement factors associated with qualified audit reports in Greece

The purpose of this paper is to test the extent to which client (corporate) performance measures can be used to enhance the ability to discriminate between the choice of a qualified or unqualified (clean) audit report. Audit firms face the risk of losing the client if they issue a qualification. On the other hand, failing to qualify exposes the auditor to potential lawsuits and loss of reputation. We examined the financial statements, auditors' opinions, and financial statements notes for companies in Greece that received a qualified audit report and for those that received an unqualified audit report. We modeled the auditor's qualification using a multicriteria decision aid classification method (UTADIS—UTilités Additives Discriminates) and compared it with other multivariate statistical techniques such as discriminant and logit analysis. The qualification decision is explained by financial ratios and by nonfinancial information such as the client litigation. The developed models are accurate in classifying the total sample correctly with rates of almost 80%.     

Econometrical analysis of the sample efficient frontier

The efficient frontier is a parabola in the mean-variance space which is uniquely determined by three characteristics. Assuming that the portfolio asset returns are independent and multivariate normally distributed, we derive tests and confidence sets for all possible arrangements of these characteristics. Note that all of our results are based on the exact distributions for a finite sample size. Moreover, we determine a confidence region of the whole efficient frontier in the mean-variance space. It is shown that this set is bordered by five parabolas.     

Corporate Governance: Factors Influencing Voluntary Disclosure by Publicly Traded Canadian Firms*

We report on the comprehensiveness of voluntary corporate governance disclosures in the annual reports and management information circulars of Toronto Stock Exchange (TSE) firms. We focus on disclosure of the corporate governance practices implemented by our sample of TSE 300 firms vis‐à‐vis the 14 guidelines set out in the TSE's report on corporate governance Where Were the Directors? Our analysis indicates that only a very few firms disclose that they have fully implemented the TSE guidelines, and that the extent of disclosure of corporate governance practices implemented varies widely among the firms. We then test factors associated with the comprehensiveness of such disclosures and the choice of disclosure medium using simultaneous equations multivariate analysis. We also assess the influence of publicized corporate governance failures on disclosure. Overall, our results suggest that the choices of disclosure medium and the extent of disclosure are made concurrently, and are influenced by the strategic considerations of management.