Time-Varying Parameters and the Out-of-Sample Forecasting Performance of Structural Exchange Rate Models
用卡尔曼滤波的递归估计让参数随时间变化，提升了美元-英镑、美元-马克、美元-日元汇率的预测效果，其中美元-马克的预测优于随机游走模型。
Varying-parameter estimation techniques based on recursive application of the Kalman filter are used to improve the predictive performance of a class of monetary exchange rate models. I find that allowing estimated parameters to vary over time enhances the models' forecasting performance for the dollar–pound, dollar–mark, and dollar–yen exchange rates. Contrary to earlier results in the literature, ex-post forecasts for the dollar-mark rate compare favorably with those obtained from the naive random walk forecasting rule.