Vector autoregression modelling and forecasting

Article Abstract:

The use of vector autoregressive (VAR) models for forecasting has developed to an advanced degree since it was first introduced by C.S. Sim in 1980. At present, however, controversy continues over Sim's contention that economic theory is not necessary for system identification, a prerequisite in interpreting the effect of random shocks on the system. Meanwhile, Bayesian VAR models have been adopted due to their better performance over the unrestricted VAR.

---

Structural, VAR and BVAR models of exchange rate determination: a comparison of their forecasting performance

Article Abstract:

The out-of-sample forecasting accuracy of structural, Bayesian vector autoregressive (BVAR) and VAR characterizations of sterling exchange rates for different time periods was evaluated. The study confirmed the higher accuracy of the BVAR with respect to short-term predictions. Generally, both BVAR and VAR models outperformed the structural models investigated. These were the portfolio balance, modified uncovered interest parity and random walk models.

Research, Prices and rates, Bayesian statistical decision theory, Bayesian analysis, Foreign exchange, Foreign exchange rates

---

Business cycle analysis and forecasting with a structural vector autoregression model for Wales

Article Abstract:

A structural vector autoregression (VAR) model of the Welsh economy was employed to study the economy's response to random shocks brought about by business cycles. Specifically, the model differentiated between international and national shocks as well as their influence on regional economic variables. It use enabled an evaluation of how the Welsh economy's response to external factor differed with other regions of the UK.

Economic aspects, Econometrics, Wales, Business cycles

Similar abstracts:

• Abstracts: Unemployment variation over the business cycles: a comparison of forecasting models
• Abstracts: Prediction intervals for growth curve forecasts. Order series method for forecasting non-Gaussian time series
• Abstracts: Forecasting with generalized Bayesian vector autoregressions. Finding good predictors for inflation: a Bayesian model averaging approach
• Abstracts: Econometric modelling for short-term inflation forecasting in the euro area. Forecasting Euro area inflation using dynamic factor measures of underlying inflation
• Abstracts: Seasonal heteroscedasticity and trends. Preliminary data and econometric forecasting: an application with the Bank of Italy quarterly model

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.