Dividend Announcements and Changes in Beta

This study examines changes in beta risk around dividend announcement dates. The evidence shows that beta changes are strongly influenced by the changing behavior of large and small betas. This implies that researchers who attribute risk changes to specific announcements may need to control their research design for regression order bias. Further research may also be needed to ascertain whether or not this regression order bias plays a significant role in the estimation of abnormal returns in event studies.     

Sample Selection Bias and Repeat-Sales Index Estimates

Analysis of variations in house values among localities requires reliable house value indices. Gatzlaff and Haurin (1994) indicate that traditional hedonic house value index estimates, using only information from a sample of sold homes to estimate value movements for the entire housing stock, may be subject to substantial bias. This article extends previous work by adapting the censored sample procedure to the repeat-sales index estimation model. Using data from Dade County, Florida, a house value index constructed from a sample of homes selling more than once, rather than all houses in a locality, is found to be biased. The bias is shown to be highly correlated with changes in economic conditions.     

A comparison of extreme value theory approaches for determining value at risk

This paper compares a number of different extreme value models for determining the value at risk (VaR) of three LIFFE futures contracts. A semi-nonparametric approach is also proposed, where the tail events are modeled using the generalised Pareto distribution, and normal market conditions are captured by the empirical distribution function. The value at risk estimates from this approach are compared with those of standard nonparametric extreme value tail estimation approaches, with a small sample bias-corrected extreme value approach, and with those calculated from bootstrapping the unconditional density and bootstrapping from a GARCH(1,1) model. The results indicate that, for a holdout sample, the proposed semi-nonparametric extreme value approach yields superior results to other methods, but the small sample tail index technique is also accurate.     

Bias and Precision of Estimates of Housing Investment Risk Based on Repeat-Sales Indices:A Simulation Analysis

A simulation analysis is reported which examines the bias and precision of estimates of housing investment risk based on small sample indices of housing returns. The trade-off between smoothing bias (due to temporal aggregation in the index) and noise bias (induced by random estimation error) is examined in the housing return total volatility, beta, and autocorrelation statistics of the index returns. The study compares the performance of three different specifications of the repeat-sales index, under assumptions of either an informationally efficient or inefficient housing market, and at two levels of estimation data availability. Findings suggest that regression-based repeated-measures indices may be useful at a more micro-level (e.g., at the neighborhood level or for specific housing types) than has hitherto been employed.     

基于拒绝推论的小企业信用评分模型研究

在小企业信用评分模型的构建中,因数据缺失和样本选择性偏差可能导致模型参数估计有偏,对模型的预测能力和应用会有很大影响。本文利用从万德数据库中筛选出的小企业信息资料,模拟银行信贷筛选,产生带有缺失数据的模拟信贷样本,利用Heckman二阶段模型预测新的信用评分模型,将其结果与忽略缺失数据的审查模型和基于完全信息的标准模型进行比较。结果显示,Heckman二阶段模型的表现优于直接忽略缺失样本数据的审查模型,更接近标准模型的结果。这表明拒绝推论能够有效解决信用评分建模中数据缺失导致的样本选择偏差,提高信用评分模型的有效性和预测能力。     

Nonlinear term structure dependence: Copula functions,empirics, and risk implications

This paper documents nonlinear cross-sectional dependence in the term structure of US-Treasury yields and points out risk management implications. The analysis is based on a Kalman filter estimation of a two-factor affine model which specifies the yield curve dynamics. We then apply a broad class of copula functions for modeling dependence in factors spanning the yield curve. Our sample of monthly yields in the 1982–2001 period provides evidence of upper tail dependence in yield innovations; i.e., large positive interest rate shocks tend to occur under increased dependence. In contrast, the best-fitting copula model coincides with zero lower tail dependence. This asymmetry has substantial risk management implications. We give an example in estimating bond portfolio loss quantiles and report the biases which result from an application of the normal dependence model.     

我国金融机构尾部风险影响因素的非线性研究——来自面板平滑转换回归模型的新证据

“十三五”期间,我国防范化解金融风险攻坚战取得决定性成就,而在“十四五”规划开局之际,我国的金融风险形势面临新的挑战,防范风险仍是金融业的永恒主题。在此背景下,本文采用相对重要性分析技术方法,考察机构规模以及相关基本面因素对我国上市金融机构尾部风险的贡献程度。接着,本文结合边际效应分析技术考察机构规模对风险的异质性效应,深入分析“太大而不能倒”假说在中国的适用性。在此基础上,进一步运用前沿的面板平滑转换估计模型,研究机构规模与尾部风险的非线性关系,并分析基本面因素对该异质性效应的影响力度。研究结果表明,我国上市银行等金融机构规模的增加能够有效缓释我国金融系统的尾部风险,但该影响效应将随着特许权价值、资产质量、杠杆水平、成本水平、收入结构、贷款结构等基本面指标的变化而出现显著的非线性转变。在此基础上,对强化我国金融系统中的风险防控薄弱环节、提高金融机构的风险吸收能力提出建议,以期为我国深化金融业改革开放、推动高质量发展提供理论分析与实证检验的参考依据。     

Multivariate dependence of implied volatilities from equity options as measure of systemic risk

This paper presents a methodology to examine the multivariate tail dependence of the implied volatility of equity options as an early warning indicator of systemic risk within the financial sector. Using non-parametric methods of estimating changes in the dependence structure in response to common shocks affecting individual risk profiles, possible linkages during periods of stress are quantifiable while recognizing that large shocks are transmitted across financial markets differently than small shocks. Before and during the initial phase of the financial crisis, we find that systemic risk increased globally as early as February 2007 — months before the unraveling of the U.S. subprime mortgage crisis and long before the collapse of Lehman Brothers. The average (multivariate) dependence among a global sample of banks and insurance companies increased by almost 30% while joint tail risk declined by about the same order of magnitude, indicating that co-movements of large changes in equity volatility were more likely to occur and responses to extreme shocks became more differentiated as distress escalated. The key policy consideration flowing from our analysis is that complementary measures of joint tail risk at high data frequency are essential to the robust measurement of systemic risk, which could enhance market-based early warning mechanisms as part of macroprudential surveillance.     

A Direct Test of Roll's Conjecture on the Firm Size Effect

Empirical research indicates that small firms earn higher average rates of return than large firms, even after accounting for beta risk. Roll conjectured that the small firm effect might be attributed to improper estimation of security betas. The evidence shows that while the direction of the bias in beta estimation is consistent with Roll's conjecture, the magnitude of the bias appears to be too small to explain the firm size effect.     

Backtesting value-at-risk based on tail losses

Extreme losses caused by leverage and financial derivatives highlight the need to backtest Value-at-Risk (VaR) based on the sizes of tail losses, because the risk measure currently used disregards losses beyond the VaR boundary. While Basel II backtests VaR by counting the number of exceptions, this paper proposes to use the saddlepoint technique by summing the sizes of tail losses. Monte Carlo simulations show that the technique is extremely accurate and powerful, even for small samples. Empirical applications for the proposed backtest find substantial downside tail risks in S&P 500, and demonstrate that risk models which account for jumps, skewed and fat-tailed distributions failed to capture the tail risk during the 1987 stock market crash. Finally, the saddlepoint technique is used to derive a multiplication factor for any risk capital requirement that is responsive to the sizes of tail losses.     

Measuring large comovements in financial markets

A general, copula-based framework for measuring the dependence among financial time series is presented. Particular emphasis is placed on multivariate conditional Spearman's rho (MCS), a new measure of multivariate conditional dependence that describes the association between large or extreme negative returns—so-called tail dependence. We demonstrate that MCS has a number of advantages over conventional measures of tail dependence, both in theory and in practical applications. In the analysis of univariate financial series, data are filtered to remove temporal dependence as a matter of routine. We show that standard filtering procedures may strongly influence the conclusions drawn concerning tail dependence. We give empirical applications to two large data sets of high-frequency asset returns. Our results have immediate implications for portfolio risk management, derivative pricing and portfolio selection. In this context we address portfolio tail diversification and tail hedging. Amongst other aspects, it is shown that the proposed modeling framework improves the estimation of portfolio risk measures such as the value at risk.     

Risk and performance estimation in hedge funds revisited: Evidence from errors in variables

This paper revisits the performance of hedge funds in the presence of errors in variables. To reduce the bias induced by measurement error, we introduce an estimator based on cross sample moments of orders three and four. This Higher Moment Estimation (HME) technique has significant consequences on the measure of factor loadings and the estimation of abnormal performance. Large changes in alphas can be attributed to measurement errors at the level of explanatory variables, while we emphasize some shifts in the economic contents of the equity risk premiums by switching from OLS to HME.     

Fair Lending Analysis of Mortgage Pricing: Does Underwriting Matter?

This paper evaluates the impact of underwriting decision on fair lending risk assessments of loan pricing. Using data from one national bank that contain a rich set of decisioning variables, we compare the estimation results from the single equation model with those from the sample selection type of models. Then we conduct three simulation studies to evaluate the sample selection bias and omitted variable bias under various scenarios. We demonstrate that the single equation approach could potentially generate biased estimates of pricing disparities when it fails to consider the impact of the underwriting decision.     

Modelling Deposit Insurance Scheme Losses in a Basel 2 Framework

This paper extends the existing literature on deposit insurance by proposing a new approach for the estimation of the loss distribution of a Deposit Insurance Scheme (DIS) that is based on the Basel 2 regulatory framework. In particular, we generate the distribution of banks’ losses following the Basel 2 theoretical approach and focus on the part of this distribution that is not covered by capital (tail risk). We also refine our approach by considering two major sources of systemic risks: the correlation between banks’ assets and interbank lending contagion. The application of our model to 2007 data for a sample of Italian banks shows that the target size of the Italian deposit insurance system covers up to 98.96% of its potential losses. Furthermore, it emerges that the introduction of bank contagion via the interbank lending market could lead to the collapse of the entire Italian banking system. Our analysis points out that the existing Italian deposit insurance system can be assessed as adequate only in normal times and not in bad market conditions with substantial contagion between banks. Overall, we argue that policy makers should explicitly consider the following when estimating DIS loss distributions: first, the regulatory framework within which banks operate such as (Basel 2) capital requirements; and, second, potential sources of systemic risk such as the correlation between banks’ assets and the risk of interbank contagion.     

Earnings Volatility and Earnings Prediction: Analysis and UK Evidence

This paper confirms that US evidence of a negative relationship between earnings persistence and earnings volatility applies to UK firms over the period 1991–2010. Our analytical framework highlights the possibility that this result may reflect downward estimation bias in earnings persistence (and persistence of cash flow and accruals components of earnings) related to transitory earnings elements. Out‐of‐sample forecasts, based on models estimated for earnings volatility quartiles, suggest significant improvement in earnings forecasts for lower volatility firms. The results also suggest that the negative association between earnings persistence and volatility may be due to both estimation bias and variation in core earnings persistence.     

Minimum variance hedging when spot price changes are partially predictable

In many markets, changes in the spot price are partially predictable. We show that when this is the case: (1) although unbiased, traditional regression estimates of the minimum variance hedge ratio are inefficient, (2) estimates of the riskiness of both hedged and unhedged positions are biased upward, and (3) estimates of the percentage risk reduction achievable through hedging are biased downward. For natural gas cross hedges, we find that both the inefficiency and bias are substantial. We further find that incorporating the expected change in the spot price, as measured by the futures-spot price spread at the beginning of the hedge, into the regression results in a substantial increase in efficiency and reduction in the bias.     

Semiparametric estimation of multi-asset portfolio tail risk

When correlations between assets turn positive, multi-asset portfolios can become riskier than single assets. This article presents the estimation of tail risk at very high quantiles using a semiparametric estimator which is particularly suitable for portfolios with a large number of assets. The estimator captures simultaneously the information contained in each individual asset return that composes the portfolio, and the interrelation between assets. Noticeably, the accuracy of the estimates does not deteriorate when the number of assets in the portfolio increases. The implementation is as easy for a large number of assets as it is for a small number. We estimate the probability distribution of large losses for the American stock market considering portfolios with ten, fifty and one hundred assets of stocks with different market capitalization. In either case, the approximation for the portfolio tail risk is very accurate. We compare our results with well known benchmark models.     

Semi-parametric Bayesian tail risk forecasting incorporating realized measures of volatility

Realized measures employing intra-day sources of data have proven effective for dynamic volatility and tail-risk estimation and forecasting. Expected shortfall (ES) is a tail risk measure, now recommended by the Basel Committee, involving a conditional expectation that can be semi-parametrically estimated via an asymmetric sum of squares function. The conditional autoregressive expectile class of model, used to implicitly model ES, has been extended to allow the intra-day range, not just the daily return, as an input. This model class is here further extended to incorporate information on realized measures of volatility, including realized variance and realized range (RR), as well as scaled and smoothed versions of these. An asymmetric Gaussian density error formulation allows a likelihood that leads to direct estimation and one-step-ahead forecasts of quantiles and expectiles, and subsequently of ES. A Bayesian adaptive Markov chain Monte Carlo method is developed and employed for estimation and forecasting. In an empirical study forecasting daily tail risk measures in six financial market return series, over a seven-year period, models employing the RR generate the most accurate tail risk forecasts, compared to models employing other realized measures as well as to a range of well-known competitors.     

Jump-diffusion volatility models for variance swaps: An empirical performance analysis

This paper studies a class of tractable jump-diffusion models, including stochastic volatility models with various specifications of jump intensity for stock returns and variance processes. We employ the Markov chain Monte Carlo (MCMC) method to implement model estimation, and investigate the performance of all models in capturing the term structure of variance swap rates and fitting the dynamics of stock returns. It is evident that the stochastic volatility models, equipped with self-exciting jumps in the spot variance and linearly-dependent jumps in the central-tendency variance, can produce consistent model estimates, aptly explain the stylized facts in variance swaps, and boost pricing performance. Moreover, our empirical results show that large self-exciting jumps in the spot variance, as an independent risk source, facilitate term structure modeling for variance swaps, whilst the central-tendency variance may jump with small sizes, but signaling substantial regime changes in the long run. Both types of jumps occur infrequently, and are more related to market turmoils over the period from 2008 to 2021.     

An Empirical Study of Sample-Selection Bias in Indices of Commercial Real Estate

Real estate price indices based solely on samples of sold properties may not accurately represent the population of properties due to potential sample-selection bias. This study addresses this potential for sample-selection bias in the construction of commercial price indices within the context of the Phoenix area office market. The empirical analysis confirms the presence of sample-selection bias in the estimation of the total price equation. However, within this sample, the price indices generated after correcting for sample-selection bias do not appear significantly different from those that do not consider selectivity bias.