Modeling exchange rates: Smooth transitions, neural networks, and linear models

IEEE Transactions on Neural Networks

Volumn 12, Issue 4, 2001, Pages 755-764

  Medeiros, Marcelo C ^a   Veiga, Álvaro ^a   Pedreira, Carlos Eduardo ^a  

^a PONTIFICAL CATHOLIC UNIVERSITY OF RIO DE JANEIRO   (Brazil)

Author keywords

Bayesian regularization; Exchange rates; Neural networks; Smooth transition models; Time series

Indexed keywords

COMPUTER SIMULATION; LAGRANGE MULTIPLIERS; LEAST SQUARES APPROXIMATIONS; MONTE CARLO METHODS; OPTIMIZATION; PARAMETER ESTIMATION; REGRESSION ANALYSIS;

BAYESIAN REGULARIZATION; EXCHANGE RATES; SMOOTH TRANSITION MODEL;

FEEDFORWARD NEURAL NETWORKS;

EID: 0035392124     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.935089     Document Type: Article

References (34)

1. Model selection in neural networks
2. On estimating thresholds in autoregressive models
3. Methodical madness: Technical analysis and the irrationality of exchange-rate forecasts
4. Functional coefficient autoregressive models
5. Comparing predictive accuracy
6. Testing the adequacy of smooth transition autoregressive models
7. Gauss-newton approximation to Bayesian regularization
8. Linear, nonlinear and essential foreign exchange rate prediction with simple technical trading rules
9. Testing the equality of prediction mean squared errors
10. Prediction intervals for artificial neural networks
11. A test of normality of observations and regression residuals
12. Artificial neural networks: An econometric perspective
13. Functionally equivalent feedforward neural networks
14. Testing linearity against smooth transition autoregressive models
15. Bayesian interpolation
16. A hybrid linear-neural model for time series forecasting
17. A flexible coefficient smooth transition time series model
18. Diagnostic checking in a flexible nonlinear time series model
19. Nonlinear, nonparametric, nonessential exchange rate estimation
20. An empirical assessment of nonlinearities in models of exchange rate determination
21. Improving the learning speed of two-layer neural networks by choosing initial values of the adaptive weights
22. Exchange rates and fundamentals: Evidence from ou-of-sample forecasting using neural networks
23. A simple variable selection technique for nonlinear models
24. Modeling nonlinearities in real effective exchange rates
25. Uniqueness of the weights for minimal feedforward nets with a given input-output map
26. Specification, estimation and evaluation of smooth transition autoregressive models
27. Power of the neural-network linearity test
28. On a threshold model
29. Threshold autoregression, limit cycles and cyclical data (with discussion)
30. Stationary and integrated autoregressive neural-network processes
31. Testing and modeling threshold autoregressive processes
32. On single-index coefficient regression models