A5059521360- Market Dynamics and Volatility
- Monetary Policy and Economic Impact
- Financial Risk and Volatility Modeling
- Financial Markets and Investment Strategies
- COVID-19 Pandemic Impacts
- Culture, Economy, and Development Studies
- Forecasting Techniques and Applications
- Insurance, Mortality, Demography, Risk Management
- Historical Economic and Social Studies
- Hydrology and Drought Analysis
- Stochastic processes and financial applications
- Climate variability and models
- Spatial and Panel Data Analysis
- Statistical Methods and Inference
- Point processes and geometric inequalities
- demographic modeling and climate adaptation
- Remote Sensing and LiDAR Applications
- Global Energy and Sustainability Research
- Global trade and economics
- Simulation and Modeling Applications
- Stock Market Forecasting Methods
- Geophysics and Gravity Measurements
- Meteorological Phenomena and Simulations
- Precipitation Measurement and Analysis
- Image Enhancement Techniques
Shandong University
2020-2024
The University of Melbourne
2014-2024
Commonwealth Scientific and Industrial Research Organisation
2012-2024
University of Technology Sydney
2010-2020
Ospedale Infermi di Rimini
2017
Health Sciences and Nutrition
2014
CSIRO Land and Water
2012
University of Toronto
2011
University of Missouri
2005-2007
MYStIX (Massive Young Star-Forming Complex Study in Infrared and Xray) seeks to characterize 20 OB-dominated young clusters their environs at distances d < 4 kpc using imaging detectors on the Chandra X-ray Observatory, Spitzer Space Telescope, United Kingdom InfraRed Telescope. The observational goals are construct catalogs of star-forming complex stellar members with well-defined criteria, maps nebular gas (particularly hot emitting plasma) dust. A catalog Probable Members (MPCMs) several...
In the statistical analysis of spatial point patterns, it is often important to investigate whether pattern depends on covariates.This paper describes nonparametric (kernel and local likelihood) methods for estimating effect covariates process intensity.Variance estimates confidence intervals are provided in case a Poisson process.Techniques demonstrated with simulated examples applications exploration geology forest ecology.
Existing methods of partitioning the market index into bull and bear regimes do not identify corrections or rallies. In contrast, our probabilistic model return distribution allows for rich heterogeneous intraregime dynamics. We focus on characteristics dynamics rallies corrections, including, example, probability transition from a rally versus back to primary state. A Bayesian estimation approach accounts parameter regime uncertainty provides statements regarding future returns. show how...
SUMMARY This paper proposes an infinite hidden Markov model to integrate the regime switching and structural break dynamics in a unified Bayesian framework. Two parallel hierarchical structures, one governing transition probabilities another parameters of conditional data density, keep parsimonious improve forecasts. flexible approach allows for persistence estimates number states automatically. An application US real interest rates compares new existing parametric alternatives. Copyright ©...
Journal Article Identifying Speculative Bubbles Using an Infinite Hidden Markov Model Get access Shuping Shi, Shi Macquarie University Search for other works by this author on: Oxford Academic Google Scholar Yong Song The of Melbourne and Rimini Centre Economic Analysis Financial Econometrics, Volume 14, Issue 1, Winter 2016, Pages 159–184, https://doi.org/10.1093/jjfinec/nbu025 Published: 18 August 2014 history Received: 12 February 2012 Revision received: 14 July Accepted: 17
Abstract Inflation expectations play a key role in determining future economic outcomes. The associated uncertainty provides direct gauge of how well‐anchored the inflation are. We construct model‐based measure by augmenting standard unobserved components model with information from noisy and possibly biased measures obtained financial markets. This new is more accurately estimated can provide valuable for policymakers. Using U.S. data, we find significant changes during Great Recession.
We use over 200 years of conflict and wheat price data to provide the first quantitative evidence that Atlantic trade contributed Europe’s pacification between 1640 1850. While decline in Europe during this period has been well documented, role not previously explored due a lack historical data. overcome constraint by using prices calculate time-varying measures pass-through New World, which we as proxy for trade. To identify causal effects Atlantictrade, exploit exogenous changes wind...
Existing methods of partitioning the market index into bull and bear regimes do not identify corrections or rallies. In contrast, our probabilistic model return distribution allows for rich heterogeneous intra-regime dynamics. We focus on characteristics dynamics rallies corrections, including, example, probability transition from a rally versus back to primary state. A Bayesian estimation approach accounts parameter regime uncertainty provides statements regarding future returns. show how...
The new financial industry represented by peer-to-peer lending has gradually become a source of volatility due to the increasing complexity Chinese market. This leads greater risk P2P investors and focus regulatory authorities in China. Based on background data platform, Honglingchuangtou, we use factor analysis method construct platform (PV) index an HAR model study heterogeneous traders leverage effect empirical results show that there are both short-term long-term market have greatest...
Recently, the information analysis technology of underwater has developed rapidly, which is beneficial to resource exploration, aquaculture, etc. Dangerous and laborious manual work replaced by deep learning-based computer vision technology, gradually become mainstream. The binocular cameras based visual method can not only collect seabed images but also construct 3D scene information. parallax image was used calculate depth object. A camera refined for creature body length estimation...
For a spatial point process model in which the intensity depends on covariates, we develop graphical diagnostics for validating covariate effect term model, and assessing whether another should be added to model. The are point-process counterparts of well-known partial residual plots (component-plus-residual plots) variable generalized linear models. new can derived as limits these classical techniques under increasingly fine discretization, leads efficient numerical approximations. also...
Abstract. For a spatial point process model fitted to pattern data, we develop diagnostics for validation, analogous the classical measures of leverage and influence in generalized linear model. The can be characterized as derivatives basic functionals They also derived heuristically (and computed practice) limits under increasingly fine discretizations domain. We apply two example datasets where there are concerns about validity.
Summary This paper provides a feasible approach to estimation and forecasting of multiple structural breaks for vector autoregressions other multivariate models. Owing conjugate prior assumptions we obtain very efficient sampler the regime allocation variable. A new hierarchical is introduced allow learning over different breaks. The model extended independent in regression coefficients volatility parameters. Two empirical applications show improvements has benchmarks. In macro application...
Abstract Parameterizations in numerical models account for unresolved processes. These parameterizations are inherently difficult to construct and as such typically have notable imperfections. One approach this uncertainty is through stochastic parameterizations. This paper describes a methodological whereby existing provide the basis simple approach. More importantly, systematically how one can “train” with observations. In particular, trigger function has been implemented convective...
Summary Downscaled rainfall projections from climate models are essential for many meteorological and hydrological applications. The technique presented utilizes an approach that efficiently parameterizes spatiotemporal dynamic in terms of the close association between mean sea level pressure patterns during winter over south-west Western Australia by means Bayesian hierarchical modelling. This allows us to understand characteristics variability associated patterns. An application is show...
Abstract Change‐point (CP) VAR models face a dimensionality curse due to the proliferation of parameters that arises when new breaks are detected. We introduce Sparse CP‐VAR model which determines truly vary break is By doing so, number be estimated at each regime drastically reduced and dynamics becomes easier interpreted. The disentangles mean covariance matrix. former uses CP with shrinkage prior distributions, while latter driven by an infinite hidden Markov framework. An extensive...
We document speed-up gains of graphical processing unit (GPU) computing over central (CPU) for the estimation discrete choice random coefficient demand model. When we use a moderate-sized GPU, computation is six to twenty times faster, where smallest factor, six, obtained from comparison with parallel sixteen CPU cores.