Abstract
Consider a compound Poisson process which is discretely observed with sampling interval \(\Delta \) until exactly \(n\) nonzero increments are obtained. The jump density and the intensity of the Poisson process are unknown. In this paper, we build and study parametric estimators of appropriate functions of the intensity, and an adaptive nonparametric estimator of the jump size density. The latter estimation method relies on nonparametric estimators of \(m\)th convolution powers density. The \(L^2\)-risk of the adaptive estimator achieves the optimal rate in the minimax sense over Sobolev balls. Numerical simulation results on various jump densities enlight the good performances of the proposed estimator.
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
References
Basawa IV, Brockwell PJ (1982) Nonparametric estimation for nondecreasing Lévy processes. J Roy Stat Soc Ser B 44:262–269
Birgé L, Massart P (1998) Minimum contrast estimators on sieves: exponential bounds and rates of convergence. Bernoulli 4:329–375
Buchmann B, Grübel R (2003) Decompounding: an estimation problem for Poisson random sums. Ann Stat 31:1054–1074
Buchmann B (2009) Weighted empirical processes in the nonparametric inference for Lévy processes. Math Methods Stat 18:281–309
Chen SX, Delaigle A, Hall P (2010) Nonparametric estimation for a class of Lévy processes. J Econom 157:257–271
Chesneau C, Comte F, Navarro F (2013) Fast nonparametric estimation for convolutions of densities. Can J Stat 41:617–636
Comte F, Genon-Catalot V (2009) Nonparametric estimation for pure jump Lévy processes based on high frequency data. Stoch Process Appl 119:4088–4123
Comte F, Genon-Catalot V (2010) Nonparametric adaptive estimation for pure jump Lévy processes. Ann Inst Henri Poincaré Probab Stat 46:595–617
Comte F, Genon-Catalot V (2011) Estimation for Lévy processes from high frequency data within a long time interval. Ann Stat 39:803–837
Duval C (2013a) Density estimation for compound Poisson processes from discrete data. Stoch Process Appl 123:3963–3986
Duval C (2013b) Nonparametric estimation of a renewal reward process from discrete data. Math Methods Stat 22:28–56
Embrechts P, Klüppelberg C, Mikosch T (1997) Modelling extremal events. For insurance and finance. Applications of Mathematics 33. Springer, Berlin
Figueroa-López JE, Houdré C (2006) Risk bounds for the non-parametric estimation of Lévy processes. High dimensional probability, 96–116, IMS Lecture Notes Monogr. Ser, 51, Inst. Math. Statist., Beachwood, OH
Figueroa-López JE (2009) Nonparametric estimation of Lévy models based on discrete-sampling. Optimality, 117–146, IMS Lecture Notes Monogr. Ser., 57, Inst. Math. Statist., Beachwood, OH
Gugushvili S (2009) Nonparametric estimation of the characteristic triplet of a discretely observed Lévy process. J Nonparametr Stat 21:321–343
Gugushvili S (2012) Nonparametric inference for discretely sampled Lévy processes. Ann Inst Henri Poincaré Probab Stat 48:282–307
Jongbloed G, van der Meulen FH, van der Vaart AW (2005) Nonparametric inference for Lévy-driven Ornstein-Uhlenbeck processes. Bernoulli 11:759–791
Katz RW (2002) Stochastic modeling of hurricane damage. J Appl Meteorol 41:754–762
Kessler M (1997) Estimation of an ergodic diffusion from discrete observations. Scand J Stat 24:211–229
Kim Y (1999) Nonparametric Bayesian estimators for counting processes. Ann Stat 27:562–588
Klein T, Rio E (2005) Concentration around the mean for maxima of empirical processes. Ann Probab 33:1060–1077
Neumann Michael H, Reiss M (2009) Nonparametric estimation for Lévy processes from low-frequency observations. Bernoulli 15:223–248
Scalas E (2006) The application of continuous-time random walks in finance and economics. Physica A 362:225–239
Schick A, Wefelmeyer W (2004) Root \(n\) consistent density estimators for sums of independent random variables. J Nonparametr Stat 16:925–935
Tsybakov A (2009) Introduction to nonparametric estimation. Springer, Berlin
Ueltzhöfer FAJ, Klüppelberg C (2011) An oracle inequality for penalised projection estimation of Lévy densities from high-frequency observations. J Nonparametr Stat 23:967–989
van Es B, Gugushvili S, Spreij P (2007) A kernel type nonparametric density estimator for decompounding. Bernoulli 13:672–694
Zhao Z, Wu WB (2009) Nonparametric inference of discretely sampled stable Lévy processes. J Econom 153:83–92
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1: Proofs
1.1 Proof of Proposition 21
The joint distribution of \((S_1, Z_1)\) is elementary using that the increments \(X_{j\Delta }-X_{(j-1)\Delta }\) are i.i.d.. The process \((X_{j\Delta }^x= x+X_{j\Delta }, j\ge 1)\) is strong Markov. We denote by \({\mathbb {P}}_x\) its distribution on the canonical space \({\mathbb {R}}^{{\mathbb {N}}}\), denote by \((X_j, j\ge 0)\) the canonical process of \({\mathbb {R}}^{{\mathbb {N}}}\) and by \({\mathcal {F}}_j=\sigma (X_k, k\le j)\) the canonical filtration. Let \(\theta :{\mathbb {R}}^{{\mathbb {N}}} \rightarrow {\mathbb {R}}^{{\mathbb {N}}}\) denote the shift operator. Consider the stopping times built on the canonical process \(S_0=0\),
and let
Because the \(S_i\)’s are built using the increments \((X_{j}-X_{j-1}, j\ge 1)\), their distributions under \({\mathbb {P}}_x\) are independent of the initial condition \(x\). We have \(S_i=S_{i-1}+ S_1\circ \theta _{S_{i-1}}\). The process \((X_{S_{i-1}+j} -X_{S_{i-1}}=(X_j-X_0)\circ \theta _{S_{i-1}}, j\ge 0) \) is independent of \({\mathcal {F}}_{S_{i-1}}\) and has distribution \({\mathbb {P}}_0\) and \(Z_i= Z_1 \circ \theta _{S_{i-1}}\). Consequently,
By iterate conditioning, we get the result. \(\square \)
1.2 Proof of Proposition 22
Let us set
An elementary computation yields:
and
As the standard maximum likelihood (and unbiased) estimator of \(1/p(\Delta )\) computed from the sample \((S_i-S_{i-1}, i=1, \ldots ,n)\) is \(S_n/n \ge 1\), we are tempted to estimate \(H_m(x)\) by \(H_m(S_n/n)\). This is not possible as \(S_n/n \) may be equal to \(1\). This is why we introduce a truncation. Set \(u_0= \Delta / (e^{c_0\Delta /2}-1), \; u_1= \Delta /(e^{2c_1\Delta }-1), u= \Delta /(e^{c \Delta }-1) \). Note that
We have
with
and
Thus, on the set \((1+ \frac{u_1}{\Delta } \le \frac{S_n}{n} \le 1+ \frac{u_0}{\Delta })\),
As
we have, for \(\xi \in [ 1+\frac{u_1}{\Delta }, 1+\frac{u_0}{\Delta }]\),
Writing that \(e^{2c_1\Delta } -1=2c_1\Delta e^{2sc_1\Delta }\) for \(s\in (0,1)\), using that \(2c_1\Delta \le \log (2)\), we get \(1/u_1\le 4c_1\). As
we get, using \(e^{c\Delta }-1\ge c\Delta \ge c_0\Delta \):
Then, we have, setting \(a_0= u_0 -u >0 , \;\; a_1= u-u_1>0\),
Thus, noting that \(u_0-u\ge 1/(2c_1)\) and \(u-u_1 \ge 1/(4\sqrt{2}c_0)\),
where
The proof is complete with \(C_m=2(C'_m+ C''_m)\). \(\square \)
1.3 Proof of Proposition 41
Consider \(f\) integrable with \(\Vert f\Vert _1=\int |f|\) and square integrable such that \(\int (1+x^2)^\alpha |f^*(x)|^2dx \le R\). Then
As \(f\) is a density, \(\Vert f\Vert _1=1\) and \(R(\Delta )=R\). This implies the announced result for \(g\). \(\square \)
1.4 Proof of Proposition 42
Recall that \(f^*= \sum _{m\ge 1} ((-1)^{m+1}/m) c_m(\Delta )(g^*)^m\) (see (6)–(7)). Let \(f_\ell \) be such that \(f^{*}_\ell = f^* \; 1_{[-\pi \ell , \pi \ell ]}\) and \(f_{K,\ell }\) be such that
Recall that \(\widetilde{f_{K,\ell }}\) (see (11)) is such that
We distinguish the first term of this development from the other ones and set
Analogously, with \(g_\ell \) such that \(g^{*}_\ell = g^* \; 1_{[-\pi \ell , \pi \ell ]}\),
The following decomposition of the \(L^2\)-norm holds:
which involves two bias terms and two stochastic error terms. The first bias term is the usual deconvolution bias term:
Noting that
we get, using that \(|g^*(t)|\le 1\) and \(\Vert g\Vert \le \Vert f\Vert \) (see Proposition 41):
where in the last line, we have used \(1/(2-e^{c\Delta })^2\le 1/(2-\sqrt{2})^2\le 3\) and \(e^{c\Delta }-1 \le \sqrt{2} c\Delta \) and \(A_K\) is given in (18).
To study the next term, we recall that, \({\mathbb {E}}(|\widehat{(g^*)(t)}-(g^*)(t)|^2)\le 1/n\). Then we get
since \(c_1(\Delta )\le \sqrt{2}\).
Hereafter, we use inequality (15) of Proposition 31.
This yields, since \(c_m(\Delta )\le (\sqrt{2})^m(c\Delta )^{m-1}\) and \(\ell /n \le 1\),
with
For the last term, we use Proposition 22, with the fact that the estimators \(\widehat{c_m(\Delta )} \) and \(\widehat{(g^*)^m(t)}\) are independent, and write
Therefore
using that \(\ell /n \le 1\) and
This ends the proof of the result with \(D_K+E_K\le B_K\) and \(\Vert g\Vert \le \Vert f\Vert \). \(\square \)
1.5 Proof of Theorem 41
Consider the contrast
and for \(\ell =1, \ldots , L_n\), the increasing sequence of spaces
Note that, for \(\ell \le L_n\) and \(t\in S_\ell \), \(\gamma _n(t) =\Vert t\Vert ^2 -2\langle t, \widehat{f_{K,\ell }}\rangle ,\) and
For \(\ell ,\ell *\le L_n, \,s\in S_\ell \) and \(t\in S_{\ell *}\), the following decomposition holds:
and \(\langle t-s, \widehat{f_{K,L_n}}-f\rangle = \langle t-s, \widehat{f_{K,L_n}}-f_{L_n}\rangle \). By definition of the estimator,
Thus, we obtain, \(\forall \ell \in \{1, \dots , L_n\}\),
Then using
and decompositions (24) and (25), we get
By the Cauchy-Schwarz Inequality and for \(\Vert t\Vert =1\), we have
Thus, inserting (31) and (32) in (30) yields
Here, the bounds of Proposition 42 can be applied. Indeed (26), (28) and (29) are uniform with respect to \(\ell \) and imply
and
Below, we prove using the Talagrand Inequality that
where \(p(\ell ,\ell ')=8\ell \vee \ell '/n\) and \(16 p(\ell , \ell ')\le \mathrm{pen}(\ell )+ \mathrm{pen}(\ell ')\) as soon as \(\kappa \ge \kappa _0=16\times 8\).
Thus, we get \({\mathbb {E}}(16 p(\ell , \hat{\ell })-\mathrm{pen}(\hat{\ell }))\le \mathrm{pen}(\ell )\) and
Proof of 33
We consider \(t\in S_{\ell ^*}\) for \(\ell ^*=\ell \vee \ell '\) with \(\ell , \ell ' \le L_n\) and (see (24) and (25))
where
We apply the Talagrand Inequality recalled in Sect. 8, and to this aim, we compute the quantities \(M, H, v\). First
The density of \(Z_1\) is \(g\) which satisfies
Therefore,
Lastly, using the bound in (27) and the fact that for \(t\in S_{\ell ^*}\),
we get
Therefore, Lemma 81 yields with \(\epsilon ^2=1/2\),
for constants \(A_1, A_2, A_3\) depending on \(c_1(\Delta )\) and \(\Vert f\Vert _\infty \). Now since
is bounded by say \(B_2\) and \(L_n e^{-A_3\sqrt{n}}\) is bounded by \(B_3\), we get
This ends the proof of (33) and thus of Theorem 41. \(\square \)
Appendix 2
The result below follows from the Talagrand concentration inequality given in Klein and Rio (2005) and arguments in Birgé and Massart (1998) (see the proof of their Corollary 2 page 354).
Lemma 81
(Talagrand Inequality) Let \(Y_1, \dots , Y_n\) be independent random variables, let \(\nu _{n,Y}(f)=(1/n)\sum _{i=1}^n [f(Y_i)-{\mathbb {E}}(f(Y_i))]\) and let \({\mathcal {F}}\) be a countable class of uniformly bounded measurable functions. Then for \(\epsilon ^2>0\)
with \(C(\epsilon ^2)=\sqrt{1+\epsilon ^2}-1,\, K_1=1/6\), and
By standard density arguments, this result can be extended to the case where \({\mathcal {F}}\) is a unit ball of a linear normed space, after checking that \(f\mapsto \nu _n(f)\) is continuous and \({\mathcal {F}}\) contains a countable dense family.
Rights and permissions
About this article
Cite this article
Comte, F., Duval, C. & Genon-Catalot, V. Nonparametric density estimation in compound Poisson processes using convolution power estimators. Metrika 77, 163–183 (2014). https://doi.org/10.1007/s00184-013-0475-3
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-013-0475-3