Forecasts of inflation from VAR models
Article Abstract:
The inaccuracy exhibited by vector autoregression (VAR) models in predicting inflation results from the misspecification which occurs during the fitting of a VAR model's price equation to US post-war economic variables. As evidence, the price equations of two VAR models are presented. Two counter the instability of these price equations, two changes in monetary policy changes are proposed to lessen misspecification and improve forecasting accuracy.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1995
User Contributions:
Comment about this article or add new information about this topic:
An integrated Bayesian vector autoregression and error correction model for forecasting electricity consumption and prices
Article Abstract:
It was argued that the Bayesian vector autoregression (VAR), error correction model (ECM) and cointegration model are restricted versions of the traditional VAR model. This concept, when used to derive a four-step method for specifying VAR forecasting models, resulted in five, different VAR models. To evaluate their performance, the five were employed to forecast electricity consumption and price using US data between 1989-91.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1995
User Contributions:
Comment about this article or add new information about this topic:
Combining VAR estimation and state space model reduction for simple good predictions
Article Abstract:
Monte Carlo methods were employed to heuristically evaluate vector autoregression estimation and state space model reduction techniques. The investigation derived 'simple to use' strategies for obtaining models with good forecasting characteristics. The results revealed that the difficulty in parameter estimation of an accurate model yields more prediction error than that of a 'parsimonious approximate model.'
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1995
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: Forecasting with generalized Bayesian vector autoregressions. Finding good predictors for inflation: a Bayesian model averaging approach
- Abstracts: Model-based clustering of multiple time series. Binomial autoregressive moving average models with an application to US recessions
- Abstracts: Maximum-likelihood estimation of fractional cointegration with an application to U.S. and Canadian bond rates
- Abstracts: Vector autoregression modelling and forecasting. Business cycle analysis and forecasting with a structural vector autoregression model for Wales