Spectral calibration of exponential Levy models ??
17
= 1 κ(u)-2(u4 + u2)F(O) - O)(u)|2.
Together with the previous result this gives for all u ∈ R the assertion of
the lemma.
ut
We shall frequently use the following norm bounds for the B-splines (bk),
which follow from kbk k∞ = 1 and |xk+1
xk-1 | 6 2∆:
∣Fbk∣∣l2 = 2∏kb∖∖bkkb2 6 (4π∆)1 /2, ∣∣Fbk∣∣∞ 6 \\bk\\Lɪ 6 2∆. (35)
We decompose σ2 in terms of L and R from (33) and (34):
U
σ2 = /
-U
2
-2(u2 — 1) + γ + Re(Fμ(u)) — λ + Re(L(u) + R(u))) wjU(u) du
U
= σ2 + / Re (Fμ(u) + L(u) + R(u)) wσ (u)du,
-U
which yields
(36)
∣ U ∣2 ∣ U ∣2
E[ ∣σ2 — σ212] 6 3∣∕ F μ ( u ) wU ( u )d u ∣ +3 E ∣/ L ( u ) wU ( u )d u ∣
U2
+ 3 Eh∣∣ R(u)wσU (u) du∣∣ i.
Let us consider the three terms in the sum separately. The nuisance of
Fμ causes a deterministic error which can be bounded using ( iu ) sFμ (u ) =
F μ (s )(u) and the Plancherel isometry by:
∣/ Fμ(u)wσ(u)du∣ = 2π∣ f μ(s)(x)F-1(wU(u)/(iu)s)(x)dx∣
-U -∞
6 U-(s+3) kμ(s) ∣U∣∣F(w~σ(u)/us) ∣∣b 1.
(37)
The linear error term can be split into a bias and a variance part (Var[Z] :=
E[|Z - E[Z]|2]):
U 2U
Eh∣∣Z-UL(u)wσU(u)du∣∣ i = ∣∣Z-U
- i) E[F (O) - O)(u)]wσU (u)
ψτ ( u — i )
2
d u∣
+ Varh Γu u(u — i)√C>lu) w(u) dui =: Lb + L.
-J-U Vt ( u — i ) -l
The bias term is easily bounded by Proposition 2, using the uniform bound
on U s+3 wσU (u)/us :
U
|Lb| 6 ∣∣F(Oi-O)IU / ∖φτ(u — i)∣-1(u4 + u2)1 /2wσ(u)|du
-U
U2
< ∆2U-(s+3) eτɪu +2tkμkL1 |u|s+2 du.
-U
More intriguing information
1. Who is missing from higher education?2. Incorporating global skills within UK higher education of engineers
3. The name is absent
4. THE UNCERTAIN FUTURE OF THE MEXICAN MARKET FOR U.S. COTTON: IMPACT OF THE ELIMINATION OF TEXTILE AND CLOTHING QUOTAS
5. The Clustering of Financial Services in London*
6. The name is absent
7. Monopolistic Pricing in the Banking Industry: a Dynamic Model
8. Opciones de política económica en el Perú 2011-2015
9. Business Networks and Performance: A Spatial Approach
10. The name is absent