Estimation in Financial Models - RiskLab
Estimation in Financial Models - RiskLab
Estimation in Financial Models - RiskLab
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
A.2 The discrete case<br />
For reasons of completeness we aga<strong>in</strong> note here the Kalman-Bucy lter for<br />
the discrete case, as already given <strong>in</strong> section 3.1.2.<br />
Consider the stochastic system<br />
X i = D i X i,1 + S i + " i ; i =1;:::;n; (System)<br />
(A.7)<br />
where fX i g n i=0<br />
are random d 1vectors, fD i g n i=0<br />
are non-random d d matrices,<br />
fS i g n i=1<br />
are non-random d1 vectors, X 0 N d (x 0 ;V 0 ), " i N d (0;V i ),<br />
i = 1;:::;n and X 0 , " 1 ;:::, " n are stochastically <strong>in</strong>dependent. Assume the<br />
observable quantities are Y 0 ;Y 1 ;:::;Y n given by<br />
Y i = T i X i + U i + e i ; i =0; 1;:::;n; (Observations)<br />
(A.8)<br />
where fT i g n i=0<br />
are non-random k d matrices (k d), fU i g n i=0<br />
are nonrandom<br />
k 1 vectors, e i N k (0;W i ) and X 0 ;" 1 ;:::;" m ;e 0 ;e 1 ;:::;e n are<br />
stochastically <strong>in</strong>dependent, i =0; 1;:::;n.<br />
The Kalman-Bucy lter<br />
Under some assumptions (see Pedersen [59], pp. 4{5), we have for given<br />
observations y 0 ;y 1 ;:::;y n of Y 0 ;Y 1 ;:::;Y n<br />
X i jY i = y i N d<br />
<br />
i (y i ); i<br />
<br />
; (A.9)<br />
X i jY i,1 = y i,1 N d<br />
<br />
Di i,1 (y i,1 )+S i ;R i<br />
<br />
; (A.10)<br />
Y i jY i,1 = y i,1 N d<br />
<br />
Ti (D i i,1 (y i,1 )+S i )+U i ;T i R i T T<br />
i<br />
+ W i<br />
<br />
;(A.11)<br />
where R i = D i i,1 D T i<br />
+ V i is positive denite, and where<br />
0 (y 0 ) = x 0 + V 0 T T 0<br />
<br />
T0 V 0 T T 0<br />
+ W 0<br />
,1<br />
(y0 , T 0 x 0 , U 0 ); (A.12)<br />
0 = V 0 , V 0 T T 0<br />
i (y i ) = D i i,1 (y i,1 )+S i + R i T T<br />
i<br />
<br />
T0 V 0 T T ,1<br />
0<br />
+ W 0 T0 V 0 ; (A.13)<br />
<br />
Ti R i Ti T ,1<br />
+ W i<br />
(y i , T i<br />
<br />
Di i,1 (y i,1 )+S i<br />
<br />
, Ui ) ; (A.14)<br />
i = R i , R i T T<br />
i (T i R i T T<br />
i + W i ) ,1 T i R i : (A.15)<br />
72