Identification of Factor Models for Forecasting Returns

A data-driven approach for forecasting returns of asset pricesis introduced. Special emphasis is given to data-driven specificationand to dimension reduction. Specification is performed by amodified AIC, BIC-based An-algorithm. Quasi-static principalcomponent analysis, quasi-static factor models with idiosyncraticerrors and reduced rank regression are considered. The forecastingresults obtained are compared.     

Differences in Perstistence in Aggregated and Disaggregated UK Stock Returns: A Reconciliation

Studies of the persistence in the returns series of UK stocks, using inter alia variance ratios, have documented clear differences between the relatively low levels of persistence in individual security returns and the relatively high levels of persistence in the returns of portfolios composed of these same securities. In this paper, I reconcile this contrast by showing that portfolio return variance ratios should not be expected to reflect (own) persistence levels in the component security returns, but instead should reflect a 'cross-persistence' between the securities. I calculate synthetic portfolio variance ratios from measures of security return 'cross-persistence' and find that they replicate closely the observed portfolio return variance ratios, which provides empirical support for the theoretical results.     

An Examination of Alternative Factor Models in UK Stock Returns

This paper examines the mean-variance efficiency of a number offactor models in UK stock returns. The paper also explores, using theapproach of MacKinlay (1995), whether missing risk factors ornonrisk-based explanations best explain the pricing errors of thedifferent factor models. The evidence in the paper suggests that themean-variance efficiency of each factor model is rejected and missing riskfactors are unable to explain the pricing errors of any of the models.Some nonrisk-based explanations, which posit a wide spread in abnormalreturns, may be a more plausible source of explaining the pricing errorsof the factor models.     

The Correlation Structure of Unexpected Returns in U.S. Equities

We examine the correlations between unexpected market moves and unexpected equity portfolio moves conditional on market performance. We derive unexpected returns from a two-stage regime switching model. The model allows for time-varying expected returns where the market portfolio alone dictates the regime switching process. Portfolios exhibit a natural hedge where correlations during extreme unexpected market downturns are generally negative. During unexpected market upswings, correlations increase. Using the unconditional analysis would lead to overhedging during market downturns and underhedging during market upswings. The adjustments to the unconditional hedging strategy conditional on extreme market movements frequently exceed ±10%.     

Arbitrage and the Evaluation of Linear Factor Models in UK Stock Returns

I examine the impact of the no arbitrage restriction on the estimation and evaluation of linear factor models in UK stock returns. The no arbitrage restriction reduces volatility and eliminates most of the negative values of the fitted stochastic discount factor models. All of the factor models are rejected and there are significant differences in the pricing performance between models under the no arbitrage restriction. The no arbitrage restriction can have a significant impact on both the parameter estimates and pricing errors for some models.     

A Note on the Predictability of UK Stock Returns

This note presents evidence on the predictability of UK stock returns using a database of companies in the FTSE-Allshare Index newly constructed towards the beginning of 1998. The tests used are autocorrelations at various lags and variance ratios for several aggregations of base observations. The evidence is consistent with that published for US stock returns, namely that daily stock returns contain a strong element of predictability.     

Security Choice, Information Effects and Firm Characteristics: A Factor Analytic Approach

Abstract:   We examine the marginal choice between debt and equity securities using a factor analytic approach. This data reduction property eliminates the need to select the one best variable to proxy for a particular theoretical construct. Our results reinforce numerous existing findings using traditional methods and suggest both static tradeoff and asymmetric information based considerations are relevant in determining security choice. Two new results are presented related to the accounting liquidity of the firm. First, the preference for equity is increasing with liquidity as suggested by the window of opportunity hypothesis. Secondly, the market response to equity issuance announcements is inversely related to the liquidity of the firm. Profitability and growth measures support Jensen's (1986) agency cost of free cash flow as a potential explanation for the second finding.     

Financial Sector Risk and the Stock Returns: Evidence from Tokyo Stock Exchange Firms

We investigate whether the activity of financial firms creates value and/or risk to the economy within the asset pricing framework. We use stock return data from nonfinancial firms listed in the first section of the Tokyo Stock Exchange. The value-weighted index that is solely composed of nonfinancial firms is augmented with the index of the firms from the financial sector, and we estimate multivariate asset pricing model with these two indices. We note that our procedure can simultaneously take into account the cross-holding phenomena among Japanese firms, especially between the financial sector and the nonfinancial sector. Our augmented index model performs well both with cross-sectional Fama and MacBeth regression test and GMM test. Our two index model with additional Fama and French's HML factor can capture cross-sectional variations of the returns of sample portfolios better than the original Fama and French model can, when measured by Hansen and Jagannathan distance measure. We find that this additional new sector variable can be a substitute for Fama and French's size factor, but not related to the bond index return. This variable has similar factor characteristic as money supply growth or the term structure, but the latter variables contain more information than the former. Morever, our financial sector model helps explain the return and risk structure of Japanese firms during the so-called bubble period.     

Interest Rate Risk Rewards in Stock Returns of Financial Corporations: Evidence from Germany

The interest rate sensitivity of stock returns of financial and non-financial corporations is a well-known phenomenon. However, only little is known about the part of total stock returns that is attributable to the compensation an investor receives for being exposed to interest rate risk when investing in equity securities. We pursue here a benchmark portfolio approach, constructing benchmark portfolios having the same interest rate risk exposure as a particular stock. By studying the time series of returns of these asset-specific benchmarks, we find: i) Regardless of the industry considered, the interest rate risk benchmarks of German corporations have mostly earned a significantly positive reward. ii) Returns of interest rate risk benchmarks of financial institutions exceeded significantly those of non-financial corporations. iii) An investor willing to bear nothing but the average interest rate risk of German financial institutions would have earned a mean return of about or even exceeding 70% of the corresponding total stock returns. iv) Returns of the interest rate risk benchmarks of the German insurance sector were significantly higher than those of German banks, which seems to contradict conventional market wisdom that insurances hedge interest rate risks.     

Forecasting Commodity Market Returns Volatility: A Hybrid Ensemble Learning GARCH-LSTM based Approach

This study investigates the advantage of combining the forecasting abilities of multiple generalized autoregressive conditional heteroscedasticity (GARCH)-type models, such as the standard GARCH (GARCH), exponential GARCH (eGARCH), and threshold GARCH (tGARCH) models with advanced deep learning methods to predict the volatility of five important metals (nickel, copper, tin, lead, and gold) in the Indian commodity market. This paper proposes integrating the forecasts of one to three GARCH-type models into an ensemble learning-based hybrid long short-term memory (LSTM) model to forecast commodity price volatility. We further evaluate the forecasting performance of these models for standalone LSTM and GARCH-type models using the root mean squared error, mean absolute error, and mean fundamental percentage error. The results highlight that combining the information from the forecasts of multiple GARCH types into a hybrid LSTM model leads to superior volatility forecasting capability. The SET-LSTM, which represents the model that combines forecasts of the GARCH, eGARCH, and tGARCH into the LSTM hybrid, has shown the best overall results for all metals, barring a few exceptions. Moreover, the equivalence of forecasting accuracy is tested using the Diebold–Mariano and Wilcoxon signed-rank tests.     

Cross‐sectional Tests of Conditional Asset Pricing Models: Evidence from the German Stock Market

We study the performance of conditional asset pricing models and multifactor models in explaining the German cross‐section of stock returns. We focus on several variables, which (according to previous research) are associated with market expectations on future market excess returns or business cycle conditions. Our results suggest that the empirical performance of the Capital Asset Pricing Model (CAPM) can be improved when allowing for time‐varying parameters of the stochastic discount factor. A conditional CAPM using the term spread explains the returns on our size and book‐to‐market sorted portfolios about as well as the Fama‐French three‐factor model and performs best in terms of the Hansen‐Jagannathan distance. Structural break tests do not necessarily indicate parameter instability of conditional model specifications. Another major finding of the paper is that the Fama‐French model – despite its generally good cross‐sectional performance – is subject to model instability. Unconditional models, however, do a better job than conditional ones at capturing time‐series predictability of the test portfolio returns.     

Macro Liquidity Risk,Money Growth,and the Cross-Section of Stock Returns: The Case of Korea

According to the homogeneity of money holding purpose, we decompose the broad money M2 into an underlying and a non-underlying part and propose innovations in future non-underlying M2 growth as a proxy for macro liquidity. In both the cross-sectional regression tests and the GMM tests, we find that risk related to innovations in future non-underlying M2 growth is strongly significantly priced in Korea, after controlling for the well-known risk factors and other macroeconomic variables. Meanwhile, risk related to innovations in future aggregate or underlying M2 growth is insignificantly priced. These results indicate that non-underlying M2 growth more directly affects macro liquidity than does aggregate or underlying M2 growth.     

基于灰色关联度分析的浙江省旅游产业结构优化升级研究

浙江省旅游资源丰富,社会经济文化水平居全国前列,具备良好的旅游产业基础,但要实现产业转型升级.需进一步调整优化产业结构.文章采用灰色关联度分析法对浙江省旅游产业内部六大行业2002-2011年收入数据进行关联度分析,提出提升餐饮业文化内涵、协调住宿业均衡发展、增强娱乐游览业高附加值、积极构建购物大产业、大力拓展文化产业等优化升级措施.     

发达国家金融结构演变的新趋势及其借鉴意义

本文使用全部私人市场资本化总量与全部私人信贷总量之比和股票市场资本化总量与存款货币银行信贷总量之比两大指标,来描述发达国家的金融结构;用金融发展总水平这一指标来描述发达国家金融发展的水平。无论从对23个样本国家时间序列数据的分析还是从结合金融发展的分析来看,发达国家金融结构演变都显示出了股票市场主导的金融市场融资比重增加和银行主导的金融中介融资比重下降的趋势。其中,少数发达国家出现了由中介为主体到由市场为主体逆转的趋势,和／或者出现了由银行为主导到由股票市场为主导逆转的趋势。作者还提出了这一新趋势对我国金融结构转变的借鉴意义。     

Do Assumptions About Factor Structure Matter in Empirical Tests of the APT?

The effect of assumptions about factor structure on empirical tests of multifactor models such as the Arbitrage Pricing Policy Theory has received little attention in the literature. Using data on securities traded on the London Stock Exchange, we examine whether returns are best described by an approximate factor structure and whether assumptions about correlations across idiosyncratic returns have a significant impact on estimated prices of risk and their significance. Our findings suggest that returns are best described by an approximate factor structure and, if this is taken into account when empirically testing the APT, six factors carry significant prices of risk. However, if a strict factor structure is imposed, no factors carry significant prices of risk. These findings suggest that assumptions about factor structure matter in empirically testing the APT.     

金融结构、银行业结构与产业结构调整

本文基于广东省的实践,分别考察了广东省金融结构、银行结构与产业结构调整的互动关系。运用2006-2011年广东省各市的面板数据,实证分析了广东省金融结构对产业结构调整影响,发现广东省银行业的发展对产业结构调整有明显的正向促进作用,而股票市场的发展对产业结构调整有一定的负向影响。这表明行业的发展在广东的经济发展中发挥着不可替代的作用,而股票市场由于不完善及多种非经济因素的影响,对产业结构调整产生了一定的阻碍作用。在此基础上运用1980-2011年广东省时间序列数据进一步分析了银行业结构与产业结构之间关系,结果表明广东省银行集中度的提高对产业结构调整有长期的负向影响。因此,必须提高银行业的竞争,逐步降低四大国有商业银行的垄断地位,同时加强股票市场的完善。     

银行业结构对产业结构升级的影响研究——基于最优金融结构理论与门槛模型的分析

基于"最优金融结构"理论,利用我国2004—2017年31个省区市的省级非平衡面板数据,实证检验了银行结构对产业结构升级的影响。结果表明:中小银行占比的增加对我国产业结构升级具有显著促进作用,且该作用在东中西部地区存在明显差异,东部地区中小银行占比增加对产业结构升级的影响并不显著,而中西部地区则具有显著的促进作用。在此基础上,运用面板门槛模型对区域差异性的影响因素进行分析,研究发现,在外商投资水平、财政收入水平、市场化水平、自然资源水平以及人力资源水平因素的不同门槛值区间内,中小银行占比增加对产业结构升级的影响具有程度和方向上的显著差异。     

Assessing the Real Estate Pricing Puzzle: A Diagnostic Application of the Stochastic Discounting Factor to the Distribution of REIT Returns

This article applies a general asset-pricing framework and the volatility bounds methodology of Hansen and Jagannathan (1991) to REIT returns. The state of real estate asset pricing remains somewhat of a puzzle relative to the identification of state variables and the structural form of models. This article offers a framework whereby real estate asset-pricing models and data can be diagnosed to answer questions about the shortcomings. In addition, several nominated discount processes are investigated for success in pricing real estate securities. Although the nominated specifications demonstrate some success in satisfying the restrictions on the first and second moments of the real estate returns distribution, they do not successfully price the securities under a no-arbitrage condition. This result calls into question previous real estate performance studies that employ these risk-adjustment processes.     

Gaussian Estimation and Forecasting of Multi-Factor Term Structure Models with an Application to Japan and the United Kingdom

In this paper we extend the exact discrete model of Bergstrom (1966) first used in empirical finance by Brennan and Schwartz (1979) to estimate their two-factor term structure model to estimate other two-factor term structure models using the recent assumption in Nowman (1997) for single factor models. Following Nowman (1997) we use the exact Gaussian estimation methods of Bergstrom (1983–1986, 1990) to estimate two-factor CKLS, Vasicek and CIR models. We estimate the models using monthly UK and Japanese interest rate data and our results indicate that the estimation method works well in practice.