Factor state–space models for high-dimensional realized covariance matrices of asset returns

We propose a dynamic factor state–space model for high-dimensional covariance matrices of asset returns. It makes use of observed risk factors and assumes that the latent integrated joint covariance matrix of the assets and the factors is observed through their realized covariance matrix with a Wishart measurement density. For the latent integrated covariance matrix of the assets we impose a strict factor structure allowing for dynamic variation in the covariance matrices of the factors and the residual components as well as in the factor loadings. This factor structure translates into a factorization of the Wishart measurement density which facilitates statistical inference based on simple Bayesian MCMC procedures making the approach scalable w.r.t. the number of assets. An empirical application to realized covariance matrices for 60 NYSE traded stocks using the Fama–French factors and sector-specific factors represented by Exchange Traded Funds (ETFs) shows that the model performs very well in- and out of sample.     

The interaction effect of gender and ethnicity in loan approval: A Bayesian estimation with data from a laboratory field experiment

Microfinance targets women and uses loan provision as a tool for empowerment, which translates into better household nutrition, improved education, and a scale down of domestic violence. However, ethnic discrimination in microfinance may exist in countries with a segregated indigenous population. We assessed this possibility with a field experiment in Bolivia. The controlled laboratory experiment evaluated whether credit officers rejected microloan applications based on the interaction effect of ethnicity and gender of potential borrowers. Point estimates of a Bayesian mixed‐effects logistic regression, estimated with the experimental data, indicate that nonindigenous women have double the chance of loan approval, but indigenous women have only 1.5 times the chance of loan approval when compared with men. While the findings about gender are limited, the evidence for the interaction of gender and ethnicity is more robust and suggests the existence of positive taste‐based discrimination favorable for nonethnic women in Bolivia. We conclude that the affirmative actions towards women promoted by development agencies and microfinance institutions must not overlook ethnicity as an important factor for financial policies of sustainable development. In practice, these policies should be aimed at identifying and reducing both social desirability bias and the structural barriers to financial inclusion that indigenous women may face when trying to obtain access to a loan.     

Japan's FDI drivers in a time of financial uncertainty. New evidence based on Bayesian Model Averaging

In this paper we analyse the determinants of Japanese outward FDI stock for the period 1996–2017. This period is especially relevant as it covers a process of increasing economic globalization and two financial crises. To this aim, we consider a large set of candidate variables based on the theory as well as on previous empirical analysis. Our sample includes a total of 27 host countries. We select the covariates using a data-driven methodology, the Bayesian Model Averaging (BMA) analysis. Moreover, we also analyse whether these determinants change depending on the degree of development (emerging vs developed) or the geographical areas (EU vs East Asia) of the countries considered. We find that Japan's FDI can be explained by a wide variety of variables, that include not only the typical gravitational ones but also institutional and macroeconomic variables, including those that measure financial development. Moreover, Japanese FDI can be explained by both horizontal and vertical FDI motives in the groups of countries analysed. However, in developed, and more precisely, EU countries, horizontal FDI strategies are predominant, whereas for East Asian and emerging countries, there is more evidence in favour of vertical FDI.     

International stock return predictability

We propose a new methodology for predicting international stock returns. Our Bayesian framework performs probabilistic selection of predictors that can shift at multiple unknown structural break dates. The approach generates significantly more accurate forecasts of international stock returns than a range of popular models that are economically meaningful for a risk-averse mean–variance investor. Allowing for regime-specific variable selection reduces considerably the international diversification of an unhedged U.S. investor’s portfolio.     

Contagion between real estate and financial markets: A Bayesian quantile-on-quantile approach

We study contagion between Real Estate Investment Trusts (REITs) and the equity market in the U.S. over four sub-samples covering January, 2003 to December, 2017, by using Bayesian nonparametric quantile-on-quantile (QQ) regressions with heteroskedasticity. We find that the spillovers from the REITs on to the equity market has varied over time and quantiles defining the states of these two markets across the four sub-samples, thus providing evidence of shift-contagion. Further, contagion from REITs upon the stock market went up during the global financial crisis particularly, and also over the period corresponding to the European sovereign debt crisis, relative to the pre-crisis period. Our main findings are robust to alternative model specifications of the benchmark Bayesian QQ model, especially when we control for omitted variable bias using the heteroskedastic error structure. Our results have important implications for various agents in the economy namely, academics, investors and policymakers.     

基于信息辅助块稀疏贝叶斯学习的直扩通信窄带干扰抑制

现有基于Nyquist-Shannon采样定理的窄带干扰(Narrowband Interference,NBI)抑制方法存在应用受限于采样率较高的问题。应用压缩感知(Compressive Sensing,CS)理论解决上述问题，利用NBI在频域表现出的块稀疏特性以及直接序列扩频(Direct Sequence Spread Spectrum,DSSS)信号的类噪声特性，提出了基于块稀疏贝叶斯学习(Block Sparse Bayesian Learning,BSBL)框架的DSSS通信NBI抑制模型。实现干扰抑制后，利用传统的CS重构算法实现DSSS信号的压缩域解调。为进一步提高算法性能，将NBI稀疏分块的块内自相关矩阵建模为单位矩阵，提出了信息辅助BSBL(Aid BSBL,ABSBL)算法，设计了基于ABSBL的DSSS通信NBI抑制算法。该算法在保持较好NBI抑制性能的条件下，提高了运算效率并且不依赖NBI的稀疏结构。仿真验证和对比分析结果表明，所提方法能够有效抑制DSSS通信中的NBI，在干扰强度相同的条件下，NBI带宽越小、压缩率越大，算法对NBI的抑制性能越好。     

Small Area Estimation for Disease Prevalence Mapping

Small area estimation (SAE) entails estimating characteristics of interest for domains, often geographical areas, in which there may be few or no samples available. SAE has a long history and a wide variety of methods have been suggested, from a bewildering range of philosophical standpoints. We describe design-based and model-based approaches and models that are specified at the area level and at the unit level, focusing on health applications and fully Bayesian spatial models. The use of auxiliary information is a key ingredient for successful inference when response data are sparse, and we discuss a number of approaches that allow the inclusion of covariate data. SAE for HIV prevalence, using data collected from a Demographic Health Survey in Malawi in 2015–2016, is used to illustrate a number of techniques. The potential use of SAE techniques for outcomes related to coronavirus disease 2019 is discussed.     

Hierarchical Bayesian conjoint models incorporating measurement uncertainty

The authors explore situations where consumers supplement their judgments with a measurement of uncertainty about their own preferences, either implicitly or explicitly, and develop two sets of hierarchical Bayesian conjoint models incorporating such measurements. The first set of models uses the relative location of a rating to determine the importance or weight given to the rating, in a regression setting. The second set uses interval judgment as a dependent variable in a regression setting. After specifying the models, the authors perform a theoretical comparison with a basic Bayesian regression model. They show that, under different conditions, the proposed models will yield more precise individual-level partworth estimates. Two simulated data examples and data from a conjoint study are used to illustrate the gains that could be obtained from modeling uncertainty. In the empirical application, the authors show that model fit improves when ratings for items that respondents do not like are given more weight compared to ratings for items that they do like. Electronic Supplementary Material  The online version of this article (doi:) contains supplementary material, which is available to authorized users.

Role of Forgetting in Memory-Based Choice Decisions: A Structural Model

We propose a structural model to investigate the impact of forgetting on consumers' brand choice decisions in frequently purchased products. Forgetting results in consumers imperfectly recalling their prior brand evaluations when making a purchase decision in the category. We conceptualize the imperfect recall by positing that consumers recall their prior evaluations with noise. Based on prior research in the behavioral area, we characterize the extent of forgetting as an increasing and concave function of time. Our framework generates analytical results on the impact of forgetting on consumers' brand evaluations and their consequent purchase behavior. We calibrate our model using scanner panel data for liquid detergents. Furthermore, we obtain insights into the consumers' extent of forgetting in the category, extent of learning, predicted price elasticities and implications on state dependence and habit persistence. Our results underscore the importance of modeling consumers' ability to recall only imperfectly.     

Closed-form Bayesian inferences for the logit model via polynomial expansions

Articles in Marketing and choice literatures have demonstrated the need for incorporating person-level heterogeneity into behavioral models (e.g., logit models for multiple binary outcomes as studied here). However, the logit likelihood extended with a population distribution of heterogeneity doesn’t yield closed-form inferences, and therefore numerical integration techniques are relied upon (e.g., MCMC methods). We present here an alternative, closed-form Bayesian inferences for the logit model, which we obtain by approximating the logit likelihood via a polynomial expansion, and then positing a distribution of heterogeneity from a flexible family that is now conjugate and integrable. For problems where the response coefficients are independent, choosing the Gamma distribution leads to rapidly convergent closed-form expansions; if there are correlations among the coefficients one can still obtain rapidly convergent closed-form expansions by positing a distribution of heterogeneity from a Multivariate Gamma distribution. The solution then comes from the moment generating function of the Multivariate Gamma distribution or in general from the multivariate heterogeneity distribution assumed. Closed-form Bayesian inferences, derivatives (useful for elasticity calculations), population distribution parameter estimates (useful for summarization) and starting values (useful for complicated algorithms) are hence directly available. Two simulation studies demonstrate the efficacy of our approach. JEL Classification C6 · C8 · M3