Original Research
The out-of-sample forecasting performance of variable parameter exchange rate models in South Africa
South African Journal of Business Management | Vol 26, No 2 | a825 |
DOI: https://doi.org/10.4102/sajbm.v26i2.825
| © 2018 Gilbert Wesso
| This work is licensed under CC Attribution 4.0
Submitted: 15 October 2018 | Published: 30 June 1995
Submitted: 15 October 2018 | Published: 30 June 1995
About the author(s)
Gilbert Wesso, Department of Statistics, University of the Western Cape, South AfricaFull Text:
PDF (989KB)Abstract
In this article the out-of-sample forecasting performance of exchange rate determination is examined without imposing the restriction that coefficients are fixed over time. Both fixed and variable coefficient versions of conventional structural models are considered, with and without a lagged dependent variable. A Variable Parameter Regression (VPR) technique based on recursive application of the Kalman filter is used to improve the predictive performance of a class oi monetary exchange rate models.
Keywords
No related keywords in the metadata.
Metrics
Total abstract views: 1564Total article views: 530
Crossref Citations
1. Neural Networks and Econometric Methodologies for South African Exchange Rate Forecasting
G R Wesso
Studies in Economics and Econometrics vol: 20 issue: 3 first page: 21 year: 1996
doi: 10.1080/03796205.1996.12129098