Bayesian Solutions for the Factor Zoo: We Just Ran Two Quadrillion Models

We propose a novel framework for analyzing linear asset pricing models: simple, robust, and applicable to high-dimensional problems. For a (potentially misspecified) stand-alone model, it provides reliable price of risk estimates for both tradable and nontradable factors, and detects those weakly identified. For competing factors and (possibly nonnested) models, the method automatically selects the best specification—if a dominant one exists—or provides a Bayesian model averaging–stochastic discount factor (BMA-SDF), if there is no clear winner. We analyze 2.25 quadrillion models generated by a large set of factors and find that the BMA-SDF outperforms existing models in- and out-of-sample.     

A New Econometric Model of Index Arbitrage

This paper introduces a new econometric model of the mispricing associated with (contemporaneous) differences between spot and futures prices. Like existing models, this model assumes that the level of arbitrage activity is positively related to the magnitude of absolute mispricing. However, unlike existing models, the new model assumes that a parameter governing a key feature of this relationship varies over time. Specifically, several versions of a smooth transition model of mispricing are introduced that each allow the shape of the transition function to be determined by a set of explanatory variables. Using high frequency data from the S&P 500 spot and futures market, the results show that the nature of the non‐linearity in mispricing corresponds to arbitrageur behaviour that varies (in a periodic fashion) over the trading day. This is evinced by the superior fit of the new model of mispricing, in comparison to the results based on existing econometric models of mispricing. Finally, the observed periodicity in arbitrageur behaviour indicates that arbitrageurs prefer to trade during certain periods within the trading day – a result that contradicts the findings obtained when using existing econometric models of mispricing.     

On the robustness of the results of adoption date choice studies: The case of pension accounting

This paper examines the robustness of the results of adoption date choice studies to sample selection criteria, variable set, and the approach to model building. We use the new pension accounting standard (SFAS 87) in our examination. To this end, we develop a model of the relationship between the adoption date of the pension standard and the variables commonly used in adoption date studies. The variables are: (1) Firm size (2) income change prior to the adoption date and proxies for income management; (3) tightness of debt constraints; and (4) extent of the impact of the standard on financial statements.The results are consistent with the smoothing and compensation hypotheses, but not with the size hypothesis. Debt constraints did not have a significant effect on the selection of the adoption date; but, to the extent that the funding status of pension plans is a measure of the income effect of SFAS 87, the results are also consistent with the selection of adoption date to ease accounting-based debt constraints.Further tests indicate that the results of adoption date choice studies depend on the sample selection critiera, the variable set, and the approach to model building. Future researchers should be aware of the sensitivity of the results to these factors.     

区域生产性服务业发展主导产业选择模型研究

研究了区域生产性服务业发展主导产业选择模型。通过分析和总结主导产业选择的准则、指标和方法,提出了基于钻石理论的区域生产性服务业主导产业选择的指标体系,利用整体有效的DEA模型来反映各行业绩效,利用AHP反映政府在产业选择过程中起到的作用,构建了区域生产性服务业主导产业选择模型,并通过实证分析,证实了该模型的可行性。     

Strategy Selection,Surrogation, and Strategic Performance Measurement Systems

Strategic performance measurement systems operationalize firm strategy with a set of performance measures. A consequence of such alignment is the tendency for managers to lose sight of the strategic construct(s) the measures are intended to represent, and subsequently act as though the measures are the constructs of interest, a phenomenon referred to as surrogation. We investigate how involvement in strategy selection affects managers’ propensity to exhibit surrogation. We predict and find that strategy selection reduces surrogation. Surprisingly, we do not find that engaging in strategy deliberation, a key process underlying strategy selection, reduces surrogation. Thus, managers’ involvement in the actual choice of strategy appears to be both a necessary and sufficient condition to mitigate surrogation. Our paper broadens understanding of factors that influence surrogation, such as the effects of different aspects of managers’ strategic involvement and buy‐in. Further, by documenting how managers behave within (as opposed to simply with) strategic performance measurement systems, we highlight the potential for managers to endogenously influence the effectiveness of such systems.     

UK Evidence on the Characteristics versus Covariance Debate

We evaluate the Fama–French three‐factor model in the UK using the approach of Daniel and Titman (1997) to determine whether characteristics or covariance risk better explains the size and value premiums. Across all three factors, we find that return premiums bear little relationship to the corresponding loadings. We show that small and value stocks earn higher returns irrespective of their return covariance. Our study contributes to the existing literature by reporting original findings on the Fama–French three‐factor model in the UK and by reporting results that complement existing evidence from similar studies in the USA and Japan.     

Looking Beyond Credit Ratings: Factors Investors Consider In Pricing European Asset‐Backed Securities

In this paper, we empirically investigate what credit factors investors rely upon when pricing the spread at issue for European asset‐backed securities. More specifically, we investigate how credit factors affect new issuance spreads after taking into account credit rating. We do so by investigating primary market spreads for tranches of non‐mortgage‐related asset‐backed securities issued from 1999 to the year prior to the subprime mortgage crisis, 2007. We find that although credit ratings play a major role in determining spreads, investors appear to not rely exclusively on these ratings. Our findings strongly suggest that investors do not ignore other credit factors beyond the assigned credit rating.     

Evaluating asset pricing models using the second Hansen-Jagannathan distance

We develop a specification test and a sequence of model selection procedures for non-nested, overlapping, and nested models based on the second Hansen-Jagannathan distance, which requires a good asset pricing model to not only have small pricing errors but also be arbitrage free. Our methods have reasonably good finite sample performances and are more powerful than existing ones in detecting misspecified models with small pricing errors but are not arbitrage-free and in differentiating models that have similar pricing errors of a given set of test assets. Using the Fama and French size and book-to-market portfolios, we reach dramatically different conclusions on model performances based on our approach and existing methods.     

Are cryptocurrencies homogeneous?

This article investigates if cryptocurrencies returns' are similarly affected by a selection of demand- and supply-side determinants. Homogeneity among cryptocurrencies is tested via a least absolute shrinkage and selection operator (LASSO) model where determinants of Bitcoin returns are applied to a sample of 12 cryptocurrencies. The analysis goes beyond existing research by simultaneously covering different periods and design choices of cryptocurrencies. The results show that cryptocurrencies are heterogeneous, apart from some similarities in the impact of technical determinants and cybercrime. The cryptocurrency market displays evidence of substitution effects, and design choices related explain the impact of the determinants of return.     

Detecting Accounting Fraud in Publicly Traded U.S. Firms Using a Machine Learning Approach

We develop a state-of-the-art fraud prediction model using a machine learning approach. We demonstrate the value of combining domain knowledge and machine learning methods in model building. We select our model input based on existing accounting theories, but we differ from prior accounting research by using raw accounting numbers rather than financial ratios. We employ one of the most powerful machine learning methods, ensemble learning, rather than the commonly used method of logistic regression. To assess the performance of fraud prediction models, we introduce a new performance evaluation metric commonly used in ranking problems that is more appropriate for the fraud prediction task. Starting with an identical set of theory-motivated raw accounting numbers, we show that our new fraud prediction model outperforms two benchmark models by a large margin: the Dechow et al. logistic regression model based on financial ratios, and the Cecchini et al. support-vector-machine model with a financial kernel that maps raw accounting numbers into a broader set of ratios.     

Using the Analytic Hierarchy Process in house selection

The house selection process involves an assessment by the buyer of a myriad of qualitative and quantitative factors before negotiating a purchase. The complex interplay among these factors along with the limitations of humans to systematically consider the complex information set, create the potential to induce serious inconsistencies in decisions. This paper presents a formal judgmental model of the house selection process using the Analytic Hierarchy Process (AHP). The model will allow the buyer to consistently evaluate property attributes. We also present a simple extension of the model to help the prospective buyer arrive at an attribute weighted price that can be used for comparative rankings.     

Capturing hedge fund risk factor exposures: Hedge fund return replication with ETFs

We develop a new factor selection methodology of spanning the space of hedge fund risk factors with all available exchange traded funds (ETFs). We demonstrate the efficacy of the methodology with out-of-sample individual hedge fund return replication by ETF clone portfolios. This is consistent with our interpretation of ETF returns as proxies to risk factors driving hedge fund returns. We further consider portfolios of “cloneable” and “noncloneable” hedge funds, defined as top and bottom in-sample R² matches, and demonstrate that our ETF clone portfolios slightly outperform cloneable hedge funds out of sample.     

Performance of Enhanced Index and Quantitative Equity Funds

We examine the performance of enhanced index and quantitative equity funds. Both types of funds use quantitative models in investment selection. Enhanced index funds set an explicit objective to outperform a benchmark index. Proponents of quantitative funds argue that their management style takes human emotions out of the investment decision‐making process and leads to more objective stock selection. We find evidence of outperformance by quantitatively managed growth funds, especially those investing in small cap stocks.     

The risk of financial crises: Is there a role for income inequality?

Could macroeconomic factors such as income inequality be the real root cause of financial crises? We explore a broad variety of financial and macroeconomic variables and employ a general-to-specific model selection process to find the most reliable predictors of financial crises in developed countries over a period of more than 100 years. Our in-sample results indicate that income inequality has predictive power beyond loan growth and several other financial variables. Out-of-sample forecasts for individual predictors show that their predictive power tends to vary considerably over time, but income inequality has predictive power in each forecasting period.     

Passive Hedge Fund Replication – Beyond the Linear Case

In this paper we extend Hasanhodzic and Lo (2007) by assessing the out‐of‐sample performance of various non‐linear and conditional hedge fund replication models. We find that going beyond the linear case does not necessarily enhance the replication power. On the other hand, we find that selecting factors on the basis on an economic analysis allows for a substantial improvement in out‐of‐sample replication quality, whatever the underlying form of the factor model. Overall, we confirm the findings in Hasanhodzic and Lo (2007) that the performance of the replicating strategies is systematically inferior to that of the actual hedge funds.     

The sensitivity of beta to the time horizon when log prices follow an Ornstein–Uhlenbeck process

This paper provides a new theoretical approach to investigate the sensitivity of the familiar beta of the capital asset pricing model to the length of the return measurement interval; a phenomenon known as the intervalling effect. By setting the problem in a continuous time setting, and using exact results, we are able to generalize existing results in the literature. We derive an expression for beta as a function of the time horizon h, conditional on current time t. We show that beta is monotonic in h and derive conditions for it to be increasing or decreasing.     

An unobserved component model of asset pricing across financial markets

Our research focuses on multifactor asset pricing models that investigate the importance of economic factors in the pricing of assets beyond the scope of the stock market. We present a Bayesian learning model of asset pricing across financial markets in which unobserved components are estimated using a Kalman filter (KF). Economic factors serve to drive the pricing of risk in the market, and agents update expectations recursively, as new information becomes available. We generally find that the Kalman filter provides superior performance and that economic factors like industrial production and unanticipated inflation provide consistent implications across financial markets.     

Performance ratio-based coherent risk measure and its application

Utilizing a specific acceptance set, we propose in this paper a general method to construct coherent risk measures called the generalized shortfall risk measure. Besides some existing coherent risk measures, several new types of coherent risk measures can be generated. We investigate the generalized shortfall risk measure’s desirable properties such as consistency with second-order stochastic dominance. By combining the performance evaluation with the risk control, we study in particular the performance ratio-based coherent risk (PRCR) measures, which is a sub-class of generalized shortfall risk measures. The PRCR measures are tractable and have a suitable financial interpretation. Based on the PRCR measure, we establish a portfolio selection model with transaction costs. Empirical results show that the optimal portfolio obtained under the PRCR measure performs much better than the corresponding optimal portfolio obtained under the higher moment coherent risk measure.     

A Multistage Model of Loans and the Role of Relationships

We develop a multistage model of the loan granting process to understand the contradictory findings of the existing literature on bank‐borrower relationships, credit availability, and loan rates. Upon estimating our model with the 1993, 1998, and 2003 versions of the Survey of Small Business Finances data set, we find that relationships matter in a borrower's decision whether to apply for a loan and in the loan approval/rejection decision by the financial institution. However, the effect of relationships on loan rates depends on the prevailing economic climate. While firms with preexisting relationships obtain credit at lower rates during periods of economic expansion, loan rates are not negatively correlated with preexisting relationships during periods of economic recession.     

Comparing Asset Pricing Models

A Bayesian asset pricing test is derived that is easily computed in closed form from the standard F‐statistic. Given a set of candidate traded factors, we develop a related test procedure that permits the computation of model probabilities for the collection of all possible pricing models that are based on subsets of the given factors. We find that the recent models of Hou, Xue, and Zhang (2015a, 2015b) and Fama and French (2015, 2016) are dominated by a variety of models that include a momentum factor, along with value and profitability factors that are updated monthly.