Density Estimation and Combination under Model Ambiguity



_

g

g


dFbn -


1 [ c- - g
2 7x g


dFbn = KcI11


1

2 K112,


(18)


where KI11 is a stochastic element that will affect the asymptotic distribution of KI, while KI12 is roughly
the sum of squared bias and variance of
fcn . It is O((nh)-1 + h4) and it will contribute to the asymptotic
mean of
KI.

15


2) KI2 has a different nature: it represents the part of the KI that is affected by the parameters estimation.
KI2 can be rewritten in the following way:

KcI2


(ln fbθ
x


ln fθ* )dF- + ( (ln fθ.
x


- ln g(x))dFbn =KcI21+KcI22.


(19)


Although in this case, the first term KI21 is stochastic, it will not affect the asymptotic distribution of
KI. In fact, since it is O
p (ɪ) when rescaled by the appropriate convergence rate dn = nh1/2 it converges to
zero:

dn KI21 -→p 0.                                      (20)

The second term KI22 has the following behavior:

—~-.

KFI22 -→ Eg [ln fθ. - ln g(x)] = (-KI(g, fθ )) ≤ 0,                      (21)

as such its presence is due to the approximation error. It is important to note that KI22 varies with the
underlying candidate model and it can not be observed. This implies that a term of the K
cI’s asymptotic
mean will depend on the specific model M
j , then in order to determine and estimate a limiting distribution
that is the same for all candidate models the following assumption is needed:

A6: KI22 ` αh1'2KI12.                                   (22)

A6 requires that the mean of the approximation error is proportional to a quantity KcI 12 whose estimation
depends only on
fcn, consequently it will not be influenced by any specific model fj (bθ, x). Further, when
h
к n-β with β 5, KI12 ~ C(nh) 1, then we obtain that:

d-KI22 ` d-αh1'2KI 12 -→ αC = Eg [ln fθ. - ln g(x)],                   (23)

where C is a known positive constant. Thus collecting all terms together:

1

KI ` KI11 - 2KI12 - [KI21 + KI22) ,                         (24)

we have the next theorem:

THEOREM 3: Given assumptions A1-A6, and given that nh5 -→ 0 as n -→ ∞, then

nh1/2


1

KI + 2 KI12 + KI22


-→d N(02)


15In order to see this, it is just sufficient to rewrite KII12 as R

2
^fn-Ec+Efn-g^ d_Fn.


10



More intriguing information

1. Poverty transition through targeted programme: the case of Bangladesh Poultry Model
2. The name is absent
3. Correlation Analysis of Financial Contagion: What One Should Know Before Running a Test
4. Should Local Public Employment Services be Merged with the Local Social Benefit Administrations?
5. The name is absent
6. Critical Race Theory and Education: Racism and antiracism in educational theory and praxis David Gillborn*
7. A Critical Examination of the Beliefs about Learning a Foreign Language at Primary School
8. Nietzsche, immortality, singularity and eternal recurrence1
9. The name is absent
10. Une nouvelle vision de l'économie (The knowledge society: a new approach of the economy)
11. INTERPERSONAL RELATIONS AND GROUP PROCESSES
12. The name is absent
13. The voluntary welfare associations in Germany: An overview
14. What Drives the Productive Efficiency of a Firm?: The Importance of Industry, Location, R&D, and Size
15. A Multimodal Framework for Computer Mediated Learning: The Reshaping of Curriculum Knowledge and Learning
16. The name is absent
17. Innovation Policy and the Economy, Volume 11
18. Happiness in Eastern Europe
19. The name is absent
20. The Institutional Determinants of Bilateral Trade Patterns