Showing 1 - 10 of 26
We show that when a model has more shocks than observed variables the estimated filtered and smoothed shocks will be correlated. This is despite no correlation being present in the data generating process. Additionally the estimated shock innovations may be autocorrelated. These correlations...
Persistent link: https://www.econbiz.de/10014101173
Persistent link: https://www.econbiz.de/10014432242
Persistent link: https://www.econbiz.de/10014490398
We show that when a model has more shocks than observed variables the estimated filtered and smoothed shocks will be correlated. This is despite no correlation being present in the data generating process. Additionally the estimated shock innovations may be autocorrelated. These correlations...
Persistent link: https://www.econbiz.de/10012320974
Persistent link: https://www.econbiz.de/10012225079
Persistent link: https://www.econbiz.de/10013348921
Persistent link: https://www.econbiz.de/10011777175
Persistent link: https://www.econbiz.de/10001400861
Persistent link: https://www.econbiz.de/10001550926
Persistent link: https://www.econbiz.de/10001419380