Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Keyword
-
- Bayesian Model Averaging and Semiparametric Regression (2)
- Copula Modeling (2)
- Archimedian Copula (1)
- Asymmetric Dependence (1)
- Bayesian Cross-Validation (1)
-
- Bayesian Pair-Copula Selection (1)
- Discrete Longitudinal Data (1)
- Electricity Market Efficiency (1)
- Electricity Spot Prices (1)
- Markov chain Monte Carlo (1)
- Multivariate Dependence (1)
- Multivariate Discrete Data (1)
- Multivariate Models in Marketing (1)
- Nonlinear Dependence (1)
- Online Advertising (1)
- Vine Copulas. (1)
- Website Exposure (1)
- Publication Type
Articles 1 - 3 of 3
Full-Text Articles in Statistical Methodology
Adventures In Library Salary Surveys, Scott L. Schaffer
Adventures In Library Salary Surveys, Scott L. Schaffer
UVM Libraries Conference Day
Salary surveys are an important tool for the library community and the administrators and boards responsible for the oversight of libraries. However, such assessments must be constructed and analyzed with great care. The Vermont Library Association Personnel Committee has conducted three salary surveys over the past several years, one focusing on academic libraries and two on public libraries. Significant issues have included confidentiality, participation rate, definitions, length and difficulty of questions, collection of data, and representativeness. Suggestions and lessons learned will be shared.
Modeling Dependence Using Skew T Copulas: Bayesian Inference And Applications, Michael S. Smith, Quan Gan, Robert Kohn
Modeling Dependence Using Skew T Copulas: Bayesian Inference And Applications, Michael S. Smith, Quan Gan, Robert Kohn
Michael Stanley Smith
[THIS IS AN AUGUST 2010 REVISION THAT REPLACES ALL PREVIOUS VERSIONS.]
We construct a copula from the skew t distribution of Sahu, Dey & Branco (2003). This copula can capture asymmetric and extreme dependence between variables, and is one of the few copulas that can do so and still be used in high dimensions effectively. However, it is difficult to estimate the copula model by maximum likelihood when the multivariate dimension is high, or when some or all of the marginal distributions are discrete-valued, or when the parameters in the marginal distributions and copula are estimated jointly. We therefore propose …
Estimation Of Copula Models With Discrete Margins Via Bayesian Data Augmentation, Michael S. Smith, Mohamad A. Khaled
Estimation Of Copula Models With Discrete Margins Via Bayesian Data Augmentation, Michael S. Smith, Mohamad A. Khaled
Michael Stanley Smith
Estimation of copula models with discrete margins is known to be difficult beyond the bivariate case. We show how this can be achieved by augmenting the likelihood with latent variables, and computing inference using the resulting augmented posterior. To evaluate this we propose two efficient Markov chain Monte Carlo sampling schemes. One generates the latent variables as a block using a Metropolis-Hasting step with a proposal that is close to its target distribution, the other generates them one at a time. Our method applies to all parametric copulas where the conditional copula functions can be evaluated, not just elliptical copulas …