Abstract
Analyse: In the first three chapters, the author reviews several monetary and porfolio-balance models of exchange-rate determination.
Chapter 4 is used to derive the Kalman filter algorithm and to discuss the state-space representation of an economic system. There is also a discussion of state-space representations of regression and time-series models. It is shown that the Kalman filter and ordinary least squares are equivalent under certain theoretical conditions.
This fact is empirically demonstrated in Chapter 5. The author briefly discusses the estimation of a time-varying coefficient regression vector and introduces the idea of "smoothing".
In Chapter 6, the author combines the Kalman filter with a "prediction error" method and a Davidon-Fletcher-Powell variable metric algorithm to estimate the parameters of a structural- (quasi-reduced-) form portfolio-balance model of exchange-rate determination. The Kalman filter is then called to obtain predicted and smoothed series for the long-run equilibrium exchange rate.
Chapter 4 is used to derive the Kalman filter algorithm and to discuss the state-space representation of an economic system. There is also a discussion of state-space representations of regression and time-series models. It is shown that the Kalman filter and ordinary least squares are equivalent under certain theoretical conditions.
This fact is empirically demonstrated in Chapter 5. The author briefly discusses the estimation of a time-varying coefficient regression vector and introduces the idea of "smoothing".
In Chapter 6, the author combines the Kalman filter with a "prediction error" method and a Davidon-Fletcher-Powell variable metric algorithm to estimate the parameters of a structural- (quasi-reduced-) form portfolio-balance model of exchange-rate determination. The Kalman filter is then called to obtain predicted and smoothed series for the long-run equilibrium exchange rate.