Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 13 of 13
Full-Text Articles in Entire DC Network
Multivariate Stochastic Volatility Models Based On Generalized Fisher Transformation, Han Chen, Yijie Fei, Jun Yu
Multivariate Stochastic Volatility Models Based On Generalized Fisher Transformation, Han Chen, Yijie Fei, Jun Yu
Research Collection School Of Economics
Modeling multivariate stochastic volatility (MSV) can be challenging, particularly when both variances and covariances are time-varying. In this paper, we address these challenges by introducing a new MSV model based on the generalized Fisher transformation of Archakov and Hansen (2021). Our model is highly exible and ensures that the variance-covariance matrix is always positive-definite. Moreover, our approach separates the driving factors of volatilities and correlations. To conduct Bayesian analysis of the model, we use a Particle Gibbs Ancestor Sampling (PGAS) method, which facilitates Bayesian model comparison. We also extend our MSV model to cover the leverage effect in volatilities and …
Improved Marginal Likelihood Estimation Via Power Posteriors And Importance Sampling, Yong Li, Nianling Wang, Jun Yu
Improved Marginal Likelihood Estimation Via Power Posteriors And Importance Sampling, Yong Li, Nianling Wang, Jun Yu
Research Collection School Of Economics
Power posteriors have become popular in estimating the marginal likelihood of a Bayesian model. A power posterior is referred to as the posterior distribution that is proportional to the likelihood raised to a power b∈[0,1]. Important power-posterior-based algorithms include thermodynamic integration (TI) of Friel and Pettitt (2008) and steppingstone sampling (SS) of Xie et al. (2011). In this paper, it is shown that the Bernstein–von Mises (BvM) theorem holds for power posteriors under regularity conditions. Due to the BvM theorem, power posteriors, when adjusted by the square root of the auxiliary constant, have the same limit distribution as the original …
Hypothesis Testing, Specification Testing And Model Selection Based On The Mcmc Output Using R, Yong Li, Jun Yu, Tao Zeng
Hypothesis Testing, Specification Testing And Model Selection Based On The Mcmc Output Using R, Yong Li, Jun Yu, Tao Zeng
Research Collection School Of Economics
This chapter overviews several MCMC-based test statistics for hypothesis testing andspecification testing and MCMC-based model selection criteria developed in recentyears. The statistics for hypothesis testing can be viewed as the MCMC version ofthe “trinity” of test statistics based in maximum likelihood (ML), namely, the likelihoodratio (LR) test, the Lagrange multiplier (LM) test, and the Wald test. The model selection criteria correspond to two predictive distributions. One of them can be viewed asthe MCMC version of widely used information criterion, AIC. The asymptotic distributions of the test statistics and model selection criteria are discussed. The test statisticsand model selection criteria are …
An Improved Bayesian Unit Root Test In Stochastic Volatility Models, Yong Li, Jun Yu
An Improved Bayesian Unit Root Test In Stochastic Volatility Models, Yong Li, Jun Yu
Research Collection School Of Economics
A new posterior odds analysis is developed to test for a unit root in volatilitydynamics in the context of stochastic volatility models. Our analysis extendsthe Bayesian unit root test of So and Li (1999) in two important ways. First,a mixed informative prior distribution with a random weight is introducedfor the Bayesian unit root testing in volatility. Second, a numerically morestable algorithm is introduced to compute Bayes factor, taking into accountthe special structure of the competing models. It can be shown that theapproach introduced overcomes the problem of the diverging “size” in themarginal likelihood approach by So and Li (1999) and …
Specification Tests Based On Mcmc Output, Yong Li, Jun Yu, Tao Zeng
Specification Tests Based On Mcmc Output, Yong Li, Jun Yu, Tao Zeng
Research Collection School Of Economics
Two test statistics are proposed to determine model specification after a model is estimated by an MCMC method. The first test is the MCMC version of IOSA test and its asymptotic null distribution is normal. The second test is motivated from the power enhancement technique of Fan et al. (2015). It combines a component (J1) that tests a null point hypothesis in an expanded model and a power enhancement component (J0) obtained from the first test. It is shown that J0 converges to zero when the null model is correctly specified and diverges when the null model is misspecified. Also …
A Specification Test Based On The Mcmc Output, Yong Li, Jun Yu, Tao Zeng
A Specification Test Based On The Mcmc Output, Yong Li, Jun Yu, Tao Zeng
Research Collection School Of Economics
A test statistic is proposed to assess themodel specification after the model is estimated by Bayesian MCMC methods. Thenew test is motivated from the power enhancement technique of Fan, Liao and Yao(2015). It combines a component (J1) that tests anull point hypothesis in an expanded model and a power enhancement component (J0) obtained from the null model. It is shown that J0 converges to zero when the null model is correctly specified anddiverges when the null model is misspecified. Also shown is that J1 is asymptotically X2-distributed, suggesting that theproposed test is asymptotically pivotal, when the null model is correctlyspecified. …
A Bayesian Chi-Squared Test For Hypothesis Testing, Yong Li, Xiaobin Liu, Jun Yu
A Bayesian Chi-Squared Test For Hypothesis Testing, Yong Li, Xiaobin Liu, Jun Yu
Research Collection School Of Economics
A new Bayesian test statistic is proposed to test a point null hypothesis based on a quadratic loss. The proposed test statistic may be regarded as the Bayesian version of the Lagrange multiplier test. Its asymptotic distribution is obtained based on a set of regular conditions and follows a chi-squared distribution when the null hypothesis is correct. The new statistic has several important advantages that make it appealing in practical applications. First, it is well-defined under improper prior distributions. Second, it avoids Jeffrey-Lindley's paradox. Third, it always takes a non-negative value and is relatively easy to compute, even for models …
A New Approach To Bayesian Hypothesis Testing, Yong Li, Tao Zeng, Jun Yu
A New Approach To Bayesian Hypothesis Testing, Yong Li, Tao Zeng, Jun Yu
Research Collection School Of Economics
In this paper a new Bayesian approach is proposed to test a point null hypothesis based on the deviance in a decision-theoretical framework. The proposed test statistic may be regarded as the Bayesian version of the likelihood ratio test and appeals in practical applications with three desirable properties. First, it is immune to Jeffreys’ concern about the use of improper priors. Second, it avoids Jeffreys–Lindley’s paradox, Third, it is easy to compute and its threshold value is easily derived, facilitating the implementation in practice. The method is illustrated using some real examples in economics and finance. It is found that …
Bayesian Hypothesis Testing In Latent Variable Models, Yong Li, Jun Yu
Bayesian Hypothesis Testing In Latent Variable Models, Yong Li, Jun Yu
Research Collection School Of Economics
Hypothesis testing using Bayes factors (BFs) is known not to be well defined under the improper prior. In the context of latent variable models, an additional problem with BFs is that they are difficult to compute. In this paper, a new Bayesian method, based on the decision theory and the EM algorithm, is introduced to test a point hypothesis in latent variable models. The new statistic is a by-product of the Bayesian MCMC output and, hence, easy to compute. It is shown that the new statistic is appropriately defined under improper priors because the method employs a continuous loss function. …
On Leverage In A Stochastic Volatility Model, Jun Yu
On Leverage In A Stochastic Volatility Model, Jun Yu
Research Collection School Of Economics
This paper is concerned with the specification for modelling financial leverage effect in the context of stochastic volatility (SV) models. Two alternative specifications co-exist in the literature. One is the Euler approximation to the well-known continuous time SV model with leverage effect and the other is the discrete time SV model of Jacquier et al. (J. Econometrics 122 (2004) 185). Using a Gaussian nonlinear state space form with uncorrelated measurement and transition errors, I show that it is easy to interpret the leverage effect in the conventional model whereas it is not clear how to obtain and interpret the leverage …
Asymmetric Response Of Volatility: Evidence From Stochastic Volatility Models And Realized Volatility, Jun Yu
Research Collection School Of Economics
This paper examines the asymmetric response of equity volatility to return shocks. We generalize the news impact function (NIF), originally introduced by Engle and Ng (1993) to study asymmetric volatility under the ARCH-type models, to be applicable to both stochastic volatility (SV) and ARCH-type models. Based on the generalized concept, we provide a unified framework to examine asymmetric properties of volatility. A new asymmetric volatility model, which nests both ARCH and SV models and at the same time allows for a more flexible NIF, is proposed. Empirical results based on daily index return data support the classical asymmetric SV model …
On Leverage In A Stochastic Volatility Model, Jun Yu
On Leverage In A Stochastic Volatility Model, Jun Yu
Research Collection School Of Economics
This paper is concerned with specification for modelling financial leverage effect in the context of stochastic volatility (SV) models. Two alternative specifications co-exist in the literature. One is the Euler approximation to the well known continuous time SV model with leverage effect and the other is the discrete time SV model of Jacquier, Polson and Rossi (2004, Journal of Econometrics, forthcoming). Using a Gaussian nonlinear state space form with uncorrelated measurement and transition errors, I show that it is easy to interpret the leverage effect in the conventional model whereas it is not clear how to obtain the leverage effect …
On Leverage In A Stochastic Volatility Model, Jun Yu
On Leverage In A Stochastic Volatility Model, Jun Yu
Research Collection School Of Economics
This paper is concerned with specification for modelling financial leverage effect in the context of stochastic volatility (SV) models. Two alternative specifications co-exist in the literature. One is the Euler approximation to the well known continuous time SV model with leverage effect and the other is the discrete time SV model of Jacquier, Polson and Rossi (2004, Journal of Econometrics, forthcoming). Using a Gaussian nonlinear state space form with uncorrelated measurement and transition errors, I show that it is easy to interpret the leverage effect in the conventional model whereas it is not clear how to obtain the leverage effect …