Event-Induced Volatility and Tests for Abnormal Performance

I analyze a simple test statistic for mean abnormal returns in the presence of stochastic volatility during both event and nonevent windows and in the presence of event‐induced variance increases. Unlike previous tests, the parametric test evaluated here does not require that the volatility effect of the event be the same across all securities. Simulations show that the test exhibits nontrivial gains in power over previously developed parametric and nonparametric tests, and the true null hypothesis is rejected at appropriate levels.     

A Complete Nonparametric Event Study Approach

Event studies have been used to examine the direction, magnitude, and speed of security price reactions to various phenomenon. Concerns over the lack of normality in stock return distributions motivated the introduction of nonparametric test statistics in the event study literature. A parametric procedure (OLS), however, has been extensively employed in the estimation of parameters for the market model. This paper, in contrast, applies Theil's nonparametric regression in the estimation of abnormal returns; an approach which is distribution free and provides a complete nonparametric approach for the detection of abnormal performance. Simulation results indicate Theil's estimation procedure offers a slight improvement in power in the detection of abnormal performance over the traditionally employed methodology. The results suggest employing Theil's nonparametric estimation procedure combined with the rank statistic. This complete nonparametric combination offers similar power with fewer underlying assumptions.     

Accrual mispricing,value-at-risk,and expected stock returns

We investigate the extent to which a parsimonious measure of maximum likely loss that captures the tail risk of returns—known as value-at-risk (VaR)—explains the relationship between accruals and the cross-sectional dispersion of expected stock returns. We construct portfolios based on Sloan’s (Account Rev 71(3):289–315, 1996) total accruals (TA) measure and individual asset-level VaR, which reflects the dynamic behavior of the asset distribution. We document that VaR is in congruence with portfolio-level accruals and that there is a significant positive relationship between VaR and the cross-section of portfolio returns. Allowing a double-sort involving VaR and TA further suggests that the spread between low- and high-TA portfolios is significantly attenuated after controlling for VaR. We also conduct a firm-level cross-sectional regression analysis and demonstrate that the TA- and VaR-based characteristics—but not the factor-mimicking portfolios—are compensated with higher expected returns, and that VaR neither subsumes nor is subsumed by TA. Finally, our cross-sectional decomposition analysis suggests that the firm-level VaR captures at least 7% of the accrual premium even in the presence of size and book-to-market. These findings lend support for the mispricing explanation of the accrual anomaly.

     

How Do Extreme Global Shocks Affect Foreign Portfolio Investment? An Event Study for India

Foreign portfolio flows in and out of India are relevant for policymakers, and are often portrayed in the media as having a destabilizing effect on the domestic market. We use an event study approach to examine whether extreme global shocks trigger abnormal responses in foreign equity flows in and out of India, or abnormal responses in the Indian stock market. We do not find strong evidence of abnormal responses, even for the case of the global crisis of 2008.     

CONSISTENT ESTIMATION OF RESIDUAL VARIANCE IN REGULATORY EVENT STUDIES

This study presents new evidence on alternative methods used to test for abnormal returns in regulatory event studies where cross-sectional correlation in residuals is significant. Results contradict earlier studies that find no advantages to using joint generalized least squares (JGLS) methods over ordinary least squares (OLS). We find that in an actual regulatory event study cross-correlation is significant, and that failing to correct for this correlation results in substantially higher calculated F-statistics. In Monte Carlo simulations we find that OLS test statistics are not well specified when residuals exhibit cross-sectional correlation at levels that are reasonable to expect in daily return data, while JGLS test statistics are well specified. The study includes tests of the effective power of the OLS and JGLS statistics.     

Valuation of American options in the presence of event risk

This paper studies the valuation of American options in the presence of external/non-hedgeable event risk. When the event occurs, the American option is terminated and a rebate is paid instead of the promised pay-off profile. Consequently, the presence of event risk influences the exercise strategy of the option holder. For the financial market in a diffusion setting, the probabilistic structure in terms of equivalent martingale measures is briefly analysed. Then, for a given equivalent martingale measure the optimal stopping problem of the American option is solved. As a main result, no-arbitrage bounds for American option values in the presence of event risk are derived, as well as hedging strategies corresponding to the no-arbitrage bounds.Received: May 2004, Mathematics Subject Classification: 90C47, 60H30, 60G40JEL Classification: G13, D52, D81The author thanks John Gould and Ross Maller for useful discussions. The author is also grateful to a referee for helpful comments. This research was partially supported by University of Western Australia Research Grant RA/1/485.     

Forecasting bank loans loss-given-default

With the advent of the new Basel Capital Accord, banking organizations are invited to estimate credit risk capital requirements using an internal ratings based approach. In order to be compliant with this approach, institutions must estimate the loss-given-default, the fraction of the credit exposure that is lost if the borrower defaults. This study evaluates the ability of a parametric fractional response regression and a nonparametric regression tree model to forecast bank loan credit losses. The out-of-sample predictive ability of these models is evaluated at several recovery horizons after the default event. The out-of-time predictive ability is also estimated for a recovery horizon of 1 year. The performance of the models is benchmarked against recovery estimates given by historical averages. The results suggest that regression trees are an interesting alternative to parametric models in modeling and forecasting loss-given-default.     

Using daily stock returns: The case of event studies

This paper examines properties of daily stock returns and how the particular characteristics of these data affect event study methodologies. Daily data generally present few difficulties for event studies. Standard procedures are typically well-specified even when special daily data characteristics are ignored. However, recognition of autocorrelation in daily excess returns and changes in their variance conditional on an event can sometimes be advantageous. In addition, tests ignoring cross-sectional dependence can be well-specified and have higher power than tests which account for potential dependence.     

Is there a viable alternative to ordinary least squares regression when security abnormal returns are the dependent variable?

Regression analysis is often used to estimate a linear relationship between security abnormal returns and firm-specific variables. If the abnormal returns are caused by a common event (i.e., there is “event clustering”) the error term of the cross-sectional regression will be heteroskedastic and correlated across observations. The size and power of alternative test statistics for the event clustering case has been evaluated under ideal conditions (Monte Carlo experiments using normally distributed synthetic security returns) by Chandra and Balachandran (J Finance 47:2055–2070, 1992) and Karafiath (J Financ Quant Anal 29(2):279–300, 1994). Harrington and Shrider (J Financ Quant Anal 42(1):229–256, 2007) evaluate cross-sectional regressions using actual (not simulated) stock returns only for the case of cross-sectional independence, i.e., in the absence of clustering. In order to evaluate the event clustering case, random samples of security returns are drawn from the data set provided by the Center for Research in Security Prices (CRSP) and the empirical distributions of alternative test statistics compared. These simulations include a comparison of OLS, WLS, GLS, two heteroskedastic-consistent estimators, and a bootstrap test for GLS. In addition, the Sefcik and Thompson (J Accounting Res 24(2):316–334, 1986) portfolio counterparts to OLS, WLS, and GLS, are evaluated. The main result from these simulations is none of the other estimator shows clear advantages over OLS or WLS. Researchers should be aware, however, that in these simulations the variance of the error term in the cross-sectional regression is unrelated to the explanatory variable.

Conducting Event Studies on a Small Stock Exchange

Abstract

This paper analyses whether it is possible to perform an event study on a small stock exchange with thinly trade stocks. The main conclusion is that event studies can be performed provided that certain adjustments are made. First, a minimum of 25 events appears necessary to obtain acceptable size and power in statistical tests. Second, trade to trade returns should be used. Third, one should not expect to consistently detect abnormal performance of less than about 1% (or perhaps even 2%), unless the sample contains primarily thickly traded stocks. Fourth, nonparametric tests are generally preferable to parametric tests of abnormal performance. Fifth, researchers should present separate results for thickly and thinly traded stock groups. Finally, when nonnormality, event induced variance, unknown event day, and problems of very thin trading are all considered simultaneously, no one test statistic or type of test statistic dominates the others.     

Comparison of modeling methods for Loss Given Default

We compare six modeling methods for Loss Given Default (LGD). We find that non-parametric methods (regression tree and neural network) perform better than parametric methods both in and out of sample when over-fitting is properly controlled. Among the parametric methods, fractional response regression has a slight edge over OLS regression. Performance of the transformation methods (inverse Gaussian and beta transformation) is very sensitive to ε, a small adjustment made to LGDs of 0 or 1 prior to transformation. Model fit is poor when ε is too small or too large, although the fitted LGDs have strong bi-modal distribution with very small ε. Therefore, models that produce strong bi-model pattern do not necessarily have good model fit and accurate LGD predictions. Even with an optimal ε, the performance of the transformation methods can only match that of the OLS.     

An Asymptotic Theory for Estimating Beta-Pricing Models Using Cross-Sectional Regression

Without the assumption of conditional homoskedasticity, a general asymptotic distribution theory for the two-stage cross-sectional regression method shows that the standard errors produced by the Fama–MacBeth procedure do not necessarily overstate the precision of the risk premium estimates. When factors are misspecified, estimators for risk premiums can be biased, and the t -value of a premium may converge to infinity in probability even when the true premium is zero. However, when a beta-pricing model is misspecified, the t -values for firm characteristics generally converge to infinity in probability, which supports the use of firm characteristics in cross-sectional regressions for detecting model misspecification.     

The Pricing of Event Risks with Parameter Uncertainty

Financial instruments whose payoffs are linked to exogenous events, such as the occurrence of a natural catastrophe or an unusual weather pattern depend crucially on actuarial models for determining event (e.g., default) probabilities. In many instances, investors appear to receive premiums far in excess of these modeled actuarial probabilities, even for event risks that are uncorrelated with returns on other financial assets. Some have attributed these larger spreads to uncertainty in the probabilities generated by the models. We provide a simple model of such parameter uncertainty and demonstrate how it affects rational investors' demand for event risk exposures. We show that while parameter uncertainty does indeed affect bond spreads, it does not tend to increase spreads by much. Indeed, the spread increases due to parameter uncertainty in our numerical examples are on the order of only 1–2 basis points. Moreover, in many instances, including those that have the most sensible correlation settings, parameter uncertainty tends to decrease the size of bond spreads. We therefore argue that parameter uncertainty does not appear to be a satisfactory explanation for high event-risk returns.     

A Generalized Method for Detecting Abnormal Returns and Changes in Systematic Risk

We generalize traditional event-study techniques to allow for event-induced parameter shifts, shifting variances, and firm-specific event periods. Our method, which nests traditional methods, also permits systematic risk to change gradually during the event period and exit the period at higher or lower levels. We use our approach to study 123 banks that acquired other institutions between 1989 and 1995. We find a significant change in the systematic risk of the acquiring firms, significant ARCH effects, and an event period that ends before the date of the announcement. None of these results is detectable using conventional methods.     

Trading Halts and Price Discovery

Trading halts have their proponents and opponents. Recent literature has examined the benefits of halts, if any, by studying the consequences of halts on order flow and price volatility. This study complements existing literature by examining the consequences of trading halts on price discovery. Our results indicate that stock price adjustments surrounding trading halts are conditioned on the underlying event that caused the halt. The weighted price contributions of all subsamples are concentrated in the halt period and some subsamples show significant price contribution in the pre-halt period as well. We find minimal evidence of price discovery continuing after the halt is removed. In addition, cross-sectional analysis shows that price discovery in the pre-halt and halt periods are more pronounced for larger firms and for firms with specific news events.      

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.     

A reexamination of corporate sell-offs of real estate assets

This article reexamines the now generally accepted notion that sell-offs of real estate assets provide positive returns for sellers but not for buyers. Following previous research, we use event study methods, but we modify the conventional market model to permit its residuals (unexpected returns) to be described by a time-varying conditional variance. We also differ from previous work in that our sample contains only sell-offs that can be precisely dated. Although we find substantial evidence of time-varying volatility in the unexpected return series, our economic results confirm the conventional viewpoint.     

Update on coronary artery calcium imaging

This update of coronary calcium imaging discusses methods of detecting and measuring coronary artery calcium and their correlation to coronary artery disease risk. The value of EBCT to traditional non-invasive cardiovascular tests is compared. A negative EBCT test makes the presence of atherosclerotic plaque, including unstable plaque, very unlikely. Negative EBCT may be consistent with low risk of a cardiovascular event over the next 2-5 years. Conversely, positive EBCT confirms the presence of a coronary plaque. The greater the amount of calcium, the greater the likelihood of occlusive disease, but there is a not a 1:1 relationship and findings may not be site specific. A high calcium score may be consistent with moderate to high risk of cardiovascular event within the next 2-5 years. Limitations and cautions concerning the general use of EBCT for screening are discussed.     

The Effects of Attributes on the Repeat Sales Pattern of Residential Property in Hong Kong

There has been copious research work on the development of house price models and the construction of house price indices. However, results in some studies revealed that the accuracy of such indices could be subject to selection bias when using only information from a sample of sold properties to estimate value movements for the entire housing stock. In particular, estimated house price appreciation is usually systematically higher among properties that change hands more frequently. It therefore suggests that the determination of important factors affecting the transaction frequency or intensity of a housing unit should be a more fundamental research question. This paper examines the possible factors that determine the popularity of residential unit by means of a repeated sales pattern. The Poisson regression model and event history analysis techniques are employed to assess the effect of attributes on transaction frequency and intensity. The event history analyses technique can take account of transaction-specific as well as time-dependent covariates, and therefore is recommended for analyzing repeated sales data in a real estate market. All transaction records during the period 1993–2000 from the Land Registry of one of the most popular residential estates in Hong Kong were used to illustrate the method. Unlike a response to favorable transaction price, good quality units do not necessarily inherently display a high transaction frequency. Rather, units of average quality are more likely to be transactionally active.     

事件模拟与非正常收益模型的检验力——基于中国A股市场的经验检验

本文分别以1990年12月至2003年12月两市所有A股公司为抽样总体,检验了均值调整模型、市场调整模型和市场模型为基础的多种检验方法的检验力。研究发现,无论事件研究中各公司事件是否相近或重叠,都应采用市场模型为基础的非参数秩检验法。而累积非正常收益的检验也应以市场模型为计算基础。若样本公司事件日相近或重叠,统计量的设置要考虑累积非正常收益截面数据的相关性。均值调整模型在本文所定义的各种检验方法中,均无明显优势。经敏感性测试,本文结论不变。