Comparison of univariate ARIMA, multivariate ARIMA and vector autoregression forecasting
A comparison of the forecasting abilities of univariate ARIMA, multivariate ARIMA, and VAR, and examination of whether series should be differenced before estimating models for forecasting purposes.
Forecasting GNP using monthly M1
A presentation of multivariate time series forecasting in which the data consist of a mixture of quarterly and monthly series. In particular, a monthly series of M1 is used to forecast quarterly GNP.
Intervention, exchange-rate volatility, and the stable paretian distribution
A look at whether the United States' decision to cease intervention after March 1981 had a perceptible influence on the day-to-day behavior of exchange rates, using the stable paretian distribution.
Extension of Granger causality in multivariate time series models
This paper proposes an extension of Granger causality when more than two variables are used in a multivariate time series model, and it is necessary to consider more than one-period-ahead forecasts.
Velocity: a multivariate time-series approach
The Federal Reserve announces targets for the monetary aggregates that are implicitly conditioned on an assumption about future velocity for each of the monetary aggregates. In this paper we present explicit models of velocity for constructing rigorous tests to determine whether the behavior of velocity has changed from what was expected when the targets were chosen. We use time-series methods to develop alternative forecasts of velocity. Multivariate time-series models of velocity that include information about past interest rates produce significantly better out-of-sample forecasts than do ...
Stability in a model of staggered-reserve accounting
An investigation of the nature of the dynamic process implied by staggered-reserve accounting, using a simple reduced-form model of the money-supply process.
Estimating multivariate ARIMA models: when is close not good enough?
The purpose of this study is to examine the forecasting abilities of the same multivariate autoregressive model estimated using two methods. The first method is the "exact method" used by the SCA System from Scientific Computing Associates. The second method is an approximation method as implemented in the MTS system by Automatic Forecasting Systems, Inc. ; The two methods were used to estimate a five-series multivariate autoregressive model for the Quenouille series on hog numbers, hog prices, corn prices, corn supply, and farm wage rates. The 82 observations were arbitrarily divided into ...
Forecasting using contemporaneous correlations
In this paper, we present a forecasting technique that uses contemporaneous correlations for forecasting in a time series model when only a subset of the variables are available for the current period. This method potentially provides more accurate forecasts than the standard time series forecasting method, which does not use contemporaneous data. This procedure is illustrated with an example of forecasting the gross national product (GNP), given current N-i in a trivariate autoregressive moving average time series model, Results indicate that during the more stable economic period of 1976:IQ ...
Forecasting and seasonal adjustment
An examination of whether one should seasonally adjust data before developing multivariate time series models to provide forecasts.
Forecasting the money supply in time series models
A demonstration of time series techniques used to forecast quarterly money supply levels. The results indicate that a bivariate model, including an interest rate and M1 predicts M1 better than the univariate model using M1 only, and as well as a 5-variable model which adds prices, output, and credit.