Neural network models for conditional distribution under Bayesian analysis
| Autor: | Tatiana Miazhynskaia, Sylvia Frühwirth-Schnatter, Georg Dorffner |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2008 |
| Předmět: |
Financial Management
Computer science Cognitive Neuroscience Machine learning computer.software_genre Probabilistic neural network symbols.namesake Arts and Humanities (miscellaneous) Humans Computer Simulation Graphical model Dynamic Bayesian network Likelihood Functions business.industry Bayes Theorem Markov chain Monte Carlo Conditional probability distribution Markov Chains Variable-order Bayesian network Bayesian statistics Nonlinear Dynamics symbols Neural Networks Computer Artificial intelligence Bayesian linear regression business computer Algorithms |
| Zdroj: | Neural Computation. 20(2):504-522 |
| ISSN: | 1530-888X 0899-7667 |
| Popis: | We use neural networks (NN) as a tool for a nonlinear autoregression to predict the second moment of the conditional density of return series. The NN models are compared to the popular econometric GARCH(1,1) model. We estimate the models in a Bayesian framework using Markov chain Monte Carlo posterior simulations. The interlinked aspects of the proposed Bayesian methodology are identification of NN hidden units and treatment of NN complexity based on model evidence. The empirical study includes the application of the designed strategy to market data, where we found a strong support for a nonlinear multilayer perceptron model with two hidden units. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|