Conditional Distribution Of Returns Research Articles

Does Diversification Drive Down Risk-adjusted Returns? A Quantile Regression Approach

Abstract This study examines diversification-performance relationship in the U.S. property-liability insurance industry over the period of 1996–2010. Unlike prior studies that rely on the conditional mean estimation method, we employ quantile regression, which captures the heterogeneous effects of diversification on conditional return distribution. The results show that diversification does not necessarily drive down risk-adjusted returns and its effects vary along return distribution. We find that there is a diversification discount for firms in the lower levels of return distribution, whereas a diversification premium exists for firms in the upper levels of return distribution. We provide evidence that the relations between risk-adjusted returns and other explanatory variables are not constant, but vary over the quantiles of return distribution. Our results are robust to alternative measures of an insurer’s performance and product diversification.

Do terror attacks affect the dollar-pound exchange rate? A nonparametric causality-in-quantiles analysis

While much significant research has been done to study the effects of terror attacks on stock markets, less is known about the response of exchange rates to terror attacks. We suggest a non-parametric causality-in-quantiles test to study whether (relative) terror attacks affect exchange-rate returns and volatility. Using data on the dollar-pound exchange rate to illustrate the test, we show that terror attacks mainly affect the lower and upper quantiles of the conditional distribution of exchange-rate returns, while misspecified (due to nonlinearity and structural breaks) linear Granger causality test show no evidence of predictability. Terror attacks also affect almost all quantiles of the conditional distribution of exchange-rate volatility (except the extreme upper-end), with the significance of the effect being particularly strong for the lower quantiles. The importance of terror attacks is shown to hold also under an alternative measure of volatility and for an important emerging-market exchange rate as well.

Does US news impact Asian emerging markets? Evidence from nonparametric causality-in-quantiles test

This paper aims to analyze whether US news on inflation and unemployment causes returns and volatility of seven emerging Asian stock markets from 1994 to 2014, by employing the causality-in-quantile approach. We find evidence that US news affect returns and/or volatility of all the seven stock markets considered, with these effects clustered around the tails of the conditional distribution of returns and volatility when they are either in bear or bull modes. In general, our results highlight the importance of modeling nonlinearity and studying entire conditional distributions of stock returns and volatility to draw correct inferences.

Do terror attacks predict gold returns? Evidence from a quantile-predictive-regression approach

Abstract Much significant research has been done to study how terror attacks affect financial markets. We contribute to this research by studying whether terror attacks, in addition to standard predictors considered in earlier research, help to predict gold returns. To this end, we use a quantile-predictive-regression (QPR) approach that accounts for model uncertainty and model instability. We find that terror attacks have predictive value for the lower and especially for the upper quantiles of the conditional distribution of gold returns.

On the short-term predictability of stock returns: A quantile boosting approach

We study the predictability of stock returns using an iterative model-building approach known as quantile boosting. Examining alternative return quantiles that represent normal, bull and bear markets via recursive quantile regressions, we trace the predictive value of extensively studied predictors including the recently suggested short interest and sentiment variables. We find that short-term returns are predictable to some extent for extreme lower quantiles of the conditional distribution of returns. Interestingly, however, short-interest and sentiment variables do not add significant predictive power, challenging the recent findings on the predictive ability of short sellers for future cash flows and associated market returns.

Testing for Leverage Effect in Financial Returns

This article questions the empirical usefulness of leverage effects to describe the dynamics of equity returns. Using a recursive estimation scheme that accurately disentangles the asymmetry coming from the conditional distribution of returns and the asymmetry that is related to the past return to volatility component in GARCH models, we test for the statistical significance of the latter. Relying on both in and out of sample tests we consistently find a weak contribution of leverage effect over the past 25 years of S&P 500 returns, casting light on the importance of the conditional distribution in time series models.

The dynamic Black–Litterman approach to asset allocation

We generalize the Black–Litterman (BL) portfolio management framework to incorporate time-variation in the conditional distribution of returns in the asset allocation process. We evaluate the performance of the dynamic BL model using both standard performance ratios as well as other measures that are designed to capture tail risk in the presence of non-normally distributed asset returns. We find that the dynamic BL model outperforms a range of different benchmarks. Moreover, we show that the choice of volatility model has a considerable impact on the performance of the dynamic BL model.

On the Short-Term Predictability of Stock Returns: A Quantile Boosting Approach

We study the predictability of stock returns using an iterative model-building approach known as quantile boosting. Examining alternative return quantiles that represent normal, bull and bear markets via recursive quantile regressions, we trace the predictive value of extensively studied predictors including the recently suggested short interest and sentiment variables. We find that short-term returns are predictable to some extent for extreme lower quantiles of the conditional distribution of returns. Interestingly, however, short-interest and sentiment variables do not add significant predictive power, challenging the recent findings on the predictive ability of short sellers for future cash flows and associated market returns.

Terror attacks and stock-market fluctuations: evidence based on a nonparametric causality-in-quantiles test for the G7 countries

We use a novel nonparametric causality-in-quantiles test to study the effects of terror attacks on stock-market returns and volatility in G7 countries. We also use the novel test to study the international repercussions of terror attacks. Test results show that terror attacks often have significant effects on returns, whereas the effect on volatility is significant only for Japan and the UK for several quantiles above the median. The effects on returns in many cases become stronger in terms of significance for the upper and lower quantiles of the conditional distribution of stock-market returns. As for international repercussions, we find that terror attacks mainly affect the tails of the conditional distribution of stock-market returns. We find no evidence of a significant cross-border effects of terror attacks on stock-market volatility, where again Japan and the UK are exceptions as far as terror attacks on the US are concerned. Finally, our results continue to hold following various robustness checks involving model structure, lag-lengths and possible omitted variable bias.

Ambiguity Aversion and Underdiversification

We examine asset allocation decisions under smooth ambiguity aversion when an investor has a prior degree of belief in the domestic capital asset pricing model (CAPM). Different from a Bayesian approach, the investor separately relies on the conditional distribution of returns and on the posterior over parameters to make decisions, rather than on the predictive distribution of returns that integrates priors and likelihood information. We find that in the perspective of U.S. investors, ambiguity aversion generates strong home bias in equity holdings, regardless of beliefs in the CAPM or risk aversion. Results become stronger under regime-switching investment opportunities.

Asymmetric spillover effects between the Shanghai and Hong Kong stock markets: evidence from quantile lagged regression

ABSTRACTThis article surveys the asymmetric spillover effects between the mainland China-based Shanghai Composite Index (SCI) and the Hong Kong based Hang Seng Index (HSI) using a quantile lagged regression model. Compared to previous studies, this article, based on data before and after the 2008 global financial crisis, presents a more detailed analysis, as we investigate the spillovers in terms of returns, volatilities and exchange rates between the renminbi (RMB) and the Hong Kong dollar (HKD) throughout the entire conditional return distribution, including the central quantiles, which are closely related to the normal circumstances, and the extreme quantiles, which correspond to the bear and bull markets. First, we find that the return spillovers from its lagged returns or from the other index not only vary across time but also depend on stock state. Second, while return volatility may boost the stock market in a bull market, it accelerates the decline in a bear market. Third, the depreciation of the RMB relative to the HKD does not significantly affect current returns for the HSI, while it negatively affects current returns for the SCI in a bad state after the crisis. The findings presented in this article will facilitate investors’ understanding of the two stock markets.

Robustly Modelling the Scale and Shape Dynamics of Stock Return Distributions

We explore time variation in the shape of the conditional return distribution using a model of multiple quantiles. We propose a joint model of scale (proxied by the interquartile range) and other quantiles standardised by the scale. The model allows us to capture the scale and shape of the distribution in one step without making assumptions about the distribution of the underlying conditional shocks from the outset. We find that, once we capture the dynamics of the scale effectively, the time variation in the shape allows a simpler interpretation. The method is illustrated by application to stock price and stock index data and provides evidence that the conditional return distribution becomes heavier tailed at times of market stress.

The Dynamic Black-Litterman Approach to Asset Allocation

We generalise the Black-Litterman (BL) portfolio management framework to incorporate time-variation in the conditional distribution of returns in the asset allocation process. We evaluate the performance of the dynamic BL model using both standard performance ratios as well as other measures that are designed to capture tail risk in the presence of non-normally distributed asset returns. We find that dynamic BL model outperforms a range of different benchmarks. Moreover, we show that the choice of volatility model has a considerable impact on the performance of the dynamic BL model.

Predictability of sustainable investments and the role of uncertainty: evidence from a non-parametric causality-in-quantiles test

ABSTRACTIn this article, we examine sustainable investments returns predictability based on the U.S. Dow Jones Sustainability Index (DJSI) and a wide set of uncertainty and financial distress indicators for the period 2002:01–2014:12. To this end, we employ a novel non-parametric causality-in-quantile approach that captures non-linearities in returns distribution. Based on our findings we conclude that the aggregate economic policy uncertainty (EPU) indicator and some components have predictive ability for real returns of the U.S. sustainable investments index. Moreover, if we split our sample to before and after the global financial crisis our results suggest that predictors carry causal information for real returns only in the after-crisis period. Finally, some marginal evidence of predictability from sovereign debt is also observed at the lower and upper ends of the conditional distribution of the real returns of sustainable investments. Our results might entail policy implications for investors and market authorities.

The HS-SAS and GSH-SAS Distribution as Model for Unconditional and Conditional Return Distributions

We introduce two new skewed and leptokurtic distributions derived from the hyperbolic secant distribution and from Vaughan (2002)’s generalized hyperbolic distribution by use of the sinh-arcsinh transformation introduced in Jones and Pewsey (2009). Properties of these new distribution are given. Their flexibility for modeling financial return data is comparable to that of their most advanced peers. Contrary to the latter for both distributions a closed-form solution for the density, cumulative distribution and quantile function can be given.

The heterogeneity dependence between crude oil price changes and industry stock market returns in China: Evidence from a quantile regression approach

This paper explores the dependence between real crude oil price changes and Chinese real industry stock market returns based on the monthly data from 1994/03 to 2014/06. We address this issue using the quantile regression approach, enabling a more detailed investigation of structure and degree of dependence. Empirical results reveal that the reaction of market returns to crude oil is highly heterogeneous across conditional distribution of industry stock returns. Furthermore, there is evidence that this dependence is positive and exists only in recessions or bearish markets with low expected returns. The dependence at low quantiles is not limited to one market, but is a common feature across industries. Additionally, dependence also changes since the onset of structural breaks. We determine that Chinese industry stock and global crude oil markets have contagion in rare situations. Most cases do not demonstrate contagion.

Recovering Conditional Return Distributions by Regression: Estimation and Applications

I propose a regression approach to recovering the return distribution of an individual asset conditional on the return of an aggregate index based on their marginal distributions. This approach relies on the identifying assumption that the conditional return distribution of the asset given the index return does not vary over time. I show how to empirically implement this approach using option price data. I then apply this approach to examine the cross-sectional equity risk premium associated with systematic disaster risk, to estimate the exposure of banks to systemic shocks, and to extend the Ross (Journal of Finance, 2014) recovery theorem to individual assets.

Volatility Forecast in Crises and Expansions

We build a discrete-time non-linear model for volatility forecasting purposes. This model belongs to the class of threshold-autoregressive models, where changes in regimes are governed by past returns. The ability to capture changes in volatility regimes and using more accurate volatility measures allow outperforming other benchmark models, such as linear heterogeneous autoregressive model and GARCH specifications. Finally, we show how to derive closed-form expression for multiple-step-ahead forecasting by exploiting information about the conditional distribution of returns.

Revisiting the asymmetric dynamic dependence of stock returns: Evidence from a quantile autoregression model

The paper provides an overview of the asymmetric dynamic dependency of the conditional return distribution using a quantile autoregression model for three indexes, namely the Shenzhen Component (SZC), the Standard & Poor's 500 (S&P 500) and Stoxx Europe 600 (S&E 600) indexes. Our findings can be summarized as follows. For SZC index, lagged extreme positive returns display more impact on current returns than that of lagged other returns at median and high quantiles; at median and high quantiles lagged positive returns display more impact on current returns than that of lagged negative returns; at lower quantiles lagged positive returns display less impact on current returns than that of lagged negative returns. For S&E 600 index, at low quantiles lagged extreme positive returns display less impact on current returns than that of lagged other returns; at high quantiles lagged extreme positive returns display more impact on current returns than that of lagged other returns; at low quantiles lagged positive returns display less impact on current returns than that of lagged negative returns; at high quantiles lagged positive returns display more impact on current returns than that of lagged negative returns. For S&P 500 index, at low quantiles lagged extreme positive returns display less impact on current returns than that of lagged other returns; at high quantiles lagged extreme positive returns display more impact on current returns than that of lagged other returns; at low quantiles lagged positive returns display less impact on current returns than that of lagged negative returns; and at high quantiles lagged positive returns display more impact on current returns than that of lagged negative returns. We find insignificant asymmetric dynamic dependency of middle returns for the three indexes. The sensitivity of our results is evaluated by a robustness check. The findings of this paper should help investors make appropriate decisions to maintain control of stock returns.

Risk, Return, and Volatility Feedback: A Bayesian Nonparametric Analysis

The relationship between risk and return is one of the most studied topics in finance. The majority of the literature is based on a linear, parametric relationship between expected returns and conditional volatility. This paper models the contemporaneous relationship between market excess returns and contemporaneous log-realized variances nonparametrically with an infinite mixture representation of their joint distribution. The conditional distribution of excess returns given log-realized variance will also have an infinite mixture representation but with probabilities and arguments depending on the value of realized variance. Our nonparametric approach allows for deviation from Gaussianity by allowing for higher-order nonzero moments and a smooth nonlinear relationship between the conditional mean of excess returns and contemporaneous log-realized variance. We find strong robust evidence of volatility feedback in monthly data. Once volatility feedback is accounted for, there is an unambiguous positive relationship between expected excess returns and expected log-realized variance. This relationship is nonlinear. Volatility feedback impacts the whole distribution and not just the conditional mean.