Abstract
We consider drift estimation problems for high dimension ergodic diffusion processes in nonparametric setting based on observations at discrete fixed time moments in the case when diffusion coefficients are unknown. To this end on the basis of sequential analysis methods we develop model selection procedures, for which we show non asymptotic sharp oracle inequalities. Through the obtained inequalities we show that the constructed model selection procedures are asymptotically efficient in adaptive setting, i.e. in the case when the model regularity is unknown. For the first time for such problem, we found in the explicit form the celebrated Pinsker constant which provides the sharp lower bound for the minimax squared accuracy normalized with the optimal convergence rate. Then we show that the asymptotic quadratic risk for the model selection procedure asymptotically coincides with the obtained lower bound, i.e this means that the constructed procedure is efficient. Finally, on the basis of the constructed model selection procedures in the framework of the big data models we provide the efficient estimation without using the parameter dimension or any sparse conditions.
Similar content being viewed by others
References
Bayisa FL, Zhou Z, Cronie O, Yu J (2019) Adaptive algorithm for sparse signal recovery. Digit Signal Proc 87:10–18
Comte F, Genon-Catalot V, Rozenholc Y (2009) Non-parametric estimation for a discretely observed integrated diffusion model. Stoch Process Appl 119:811–834
Dalalyan AS (2005) Sharp adaptive estimation of the drift function for ergodic diffusion. Ann Stat 33(6):2507–2528
Dalalyan AS, Kutoyants YuA (2002) Asymptotically efficient trend coefficient estimation for ergodic diffusion. Math Methods Stat 11(4):402–427
Fan J, Fan Y, Barut E (2014) Adaptive robust variable selection. Ann Stat 42(1):324–351
Florens-Zmirou D (1993) On estimating the diffusion coefficient from discrete observations. J Appl Probab 30(4):790–804
Fujimori K (2019) The Danzing selector for a linear model of diffusion processes. Stat Infer Stoch Process 22:475–498
De Gregorio A, Iacus SM (2012) Adaptive LASSO-type estimation for multivariate diffusion processes. Econ Theory 28(4):838–860
Galtchouk LI (1978) Existence and uniqueness of a solution for stochastic equations with respect to semimartingales. Theory Probab Appl 23:751–763
Galtchouk L, Pergamenshchikov S (2001) Sequential nonparametric adaptive estimation of the drift coefficient in diffusion processes. Math Methods Stat 10(3):316–330
Galtchouk L, Pergamenshchikov S (2004) Nonparametric sequential estimation of the drift in diffusion via model selection. Math Methods Stat 13:25–49
Galtchouk L, Pergamenshchikov S (2005) Nonparametric sequential minimax estimation of the drift coefficient in diffusion processes. Sequ Anal 24(3):303–330
Galtchouk L, Pergamenshchikov S (2006) Asymptotically efficient sequential kernel estimates of the drift coefficient in ergodic diffusion processes. Stat Infer Stoch Process 9:1–16
Galtchouk L, Pergamenshchikov S (2007) Uniform concentration inequality for ergodic diffusion processes. Stoch Process Appl 117:830–839
Galtchouk L, Pergamenshchikov S (2009a) Sharp non-asymptotic oracle inequalities for nonparametric heteroscedastic regression models. J Nonparametr Stat 21:1–16
Galtchouk L, Pergamenshchikov S (2009b) Adaptive asymptotically efficient estimation in heteroscedastic nonparametric regression. J Korean Stat Soc 38(4):305–322
Galtchouk L, Pergamenshchikov S (2011) Adaptive sequential estimation for ergodic diffusion processes in quadratic metric. J Nonparametr Stat 23(2):255–285
Galtchouk L, Pergamenshchikov S (2013) Uniform concentration inequality for ergodic diffusion processes observed at discrete times. Stoch Process Appl 123(1):91–109
Galtchouk L, Pergamenshchikov S (2014) Geometric ergodicity for classes of homogeneous Markov chains. Stoch Process Appl 124(10):3362–3391
Galtchouk L, Pergamenshchikov S (2015) Efficient pointwise estimation based on discrete data in ergodic nonparametric diffusions. Bernoulli 21(4):2569–2594
Galtchouk L, Pergamenshchikov S (2019) Non asymptotic sharp oracle inequalities for high dimensional ergodic diffusion models. Preprint https://hal.archives-ouvertes.fr/hal-02387034 (2019)
Gihman II, Skorohod AV (1968) Stochastic differential equations. Naukova Dumka, Kiev
Gobet E, Hoffmann M, Reiss M (2004) Nonparametric estimation of scalar diffusions based on low frequency data. Ann Stat 32(5):2223–2253
Hoffmann M (1999) Adaptive estimation in diffusion processes. Stoch Process Appl 79:135–163
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Data mining, inference and prediction. Springer series in statistics. Springer, Berlin
Jacod J (2000) Non-parametric kernel estimation of the coefficient of a diffusion. Scand J Stat 27(1):83–96
Kabanov YM, Pergamenshchikov SM (2003) Two scale stochastic systems: asymptotic analysis and control. Applications of mathematics, stochastic modelling and applied probability, vol 49. Springer Berlin
Karatzas I, Shreve SE (1998a) Brownian motion and stochastic calculus. Graduate texts in mathematics, 2nd edn. Springer Science+Business Media, New York
Karatzas I, Shreve SE (1998b) Methods of mathematical finance. Springer, New York
Kutoyants YuA (1977) Estimation of the signal parameter in a Gaussian noise. Probl Inf Transm 13(4):29–38
Kutoyants YuA (1984a) Parameter estimation for stochastic processes. Heldeman-Verlag, Berlin
Kutoyants YuA (1984b) On nonparametric estimation of trend coefficients in a diffusion process. Statistics and control of stochastic processes. Steklov seminar proceedings, Moscow, pp 230–250
Kutoyants YuA (2003) Statistical inferences for ergodic diffusion processes. Springer, Berlin
Konev VV, Pergamenshchikov SM (2015) Robust model selection for a semimartingale continuous time regression from discrete data. Stoch Process Appl 125:294–326
Lamberton D, Lapeyre B (1996) Introduction to stochastic calculus applied to finance. Chapman & Hall, London
Pinsker MS (1981) Optimal filtration of square integrable signals in gaussian noise. Probl Inf Transm 17:120–133
Acknowledgements
The work of the last author was partially supported by the Russian Federal Professor program, Project No. 1.472.2016/1.4 (the Ministry of Science and Higher Education of the Russian Federation).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This research was supported by RSF, Grant No. 20-61-47043, National Russian Research Tomsk State University, Russia.
Appendix
Appendix
1.1 Property of the penalty term
Proposition A.1
For any \(0<\varepsilon <1/2\),
where the term \(\mathbf{g}^{*}_{T}\) is given in (3.6).
Proof
Note that on the set \(\mathbf{G}_{*}\)
Taking into account here that
we obtain
where \(I_{1}=\sum ^n_{j=1}\lambda ^2(j)g_{j,n}\xi _{j,n}\) and \(I_{2}=\sum ^n_{j=1}(1-\lambda (j))\lambda (j)\theta _{j,n}\xi _{j,n}\). Moreover, note that, for any \(0<\varepsilon <1\),
Therefore
and
Taking into account here the definition of \(\mathbf{B}(\cdot )\) in (6.1) and that \(\mathbf{E}_{\vartheta }I_{2}=0\) we can rewrite the last inequality as
Now Propositions 6.1– 6.2 imply that
Hence Proposition A.1. \(\square \)
1.2 Asymptotic analysis tools
Proposition A.2
Assume that the conditions \(\mathbf{A}_1)\)–\(\mathbf{A}_2)\) hold. Then, for any \(\mathbf{x}_{0}<\mathbf{x}_{1}\) and \(a>0\),
The proof is the same as for Lemma A.3 in Galtchouk and Pergamenshchikov (2015), so it is omitted.
Proof of Proposition 3.3
First, note that, to show the limit (3.7) it suffices to check that, for any \(a>0\),
Indeed, using the definition of \(\mathbf{g}_{1}(z)\) in (2.16) we represent it on the set \(\Gamma (z)\) as \( \mathbf{g}_{1}(z) =\mathbf{g}_{1,1}(z)+\mathbf{g}_{1,2}(z)\), where
and
To estimate the term \(\mathbf{g}_{1,2}(z)\) note that
Moreover, note also here, that for some constant \(C>0\)
From the definition (2.13) it follows that \(\{\tau (z)=j\}\in {{\mathcal {F}}}_{t_{j-1}}\), i.e.
Therefore, for some \(C>0\)
and
Using the definition (2.12), the conditions \(\mathbf{A}_{1}\))–\(\mathbf{A}_{2}\)), and Propositions 4.1–4.2 from Galtchouk and Pergamenshchikov (2015) we obtain the property (3.7). Hence Proposition 3.3. \(\square \)
Proof of Proposition 3.4
Note that
Taking into account the definition of \(N_{0}\) in (2.9) we obtain through Proposition 3.1 from Galtchouk and Pergamenshchikov (2019) the limit equality (3.11). Hence Proposition 3.4. \(\square \)
Now, we study the heteroscedastic property in the model (3.4). To this end we study asymptotic properties of the average variance \(\mathbf{s}_{n}\) defined in (7.10).
Proposition A.3
Assume that the condition \(\mathbf{A}_1)\) holds. Then
Proof
Using the definition of \(\sigma _{l}\) in (3.4) and taking into account the form of h given in (2.13), we can represent the term \(\mathbf{s}_{n}\) as
where \({\widetilde{b}}_{\vartheta }(x)=b^2(x)/\mathbf{q}_{\vartheta }(x)\),
and
First of all note, that the function \({\widetilde{b}}_{\vartheta }(\cdot )\) and its derivative are uniformly bounded, i.e. \( \sup _{\vartheta \in \Theta _{k,r}} \max _{\mathbf{x}_{0}\le z\le \mathbf{x}_{1}}\, \left( {\widetilde{b}}_{\vartheta }(z) + \vert {\widetilde{b}}^{\prime }_{\vartheta }(z)\vert \right) <\infty \). Therefore,
As the second term (A.3), note that, in view of the condition (3.2),
Therefore, \( \lim _{T\rightarrow \infty } \sup _{\vartheta \in \Theta _{k,r}} \, \vert R_{1}(\vartheta ) \vert =0\). Moreover, taking into account that \(2{\widetilde{q}}_{T}(z_{l})-\upsilon _{T}>\upsilon ^{1/2}_{T}\), we obtain, for sufficiently large T, that for some \(C>0\)
Note here, that for any \(1\le l\le n\) and for sufficiently large T,
and, therefore, Proposition A.2 implies \( \lim _{T\rightarrow \infty } \sup _{\vartheta \in \Theta _{k,r}} \,\vert R_{2}(\vartheta ) \vert =0\). \(\square \)
Lemma A.4
Let f be an absolutely continuous \([\mathbf{x}_{0},\mathbf{x}_{1}] \rightarrow {{\mathbb {R}}}\) function with \(\Vert {\dot{f}}\Vert <\infty \) and g be \([\mathbf{x}_{0},\mathbf{x}_{1}] \rightarrow {{\mathbb {R}}}\) a step-wise function \( g(z)=\sum _{j=1}^{n}\,c_{j}\,\chi _{(z_{j-1},z_{j}]}(z)\), where \(c_{j}\) are some constants and the sequence \((z_{j})_{0\le j\le n}\) is given in (3.1). Then, for any \( {\widetilde{\varepsilon }}>0\), the function \(\Delta =f-g\) satisfies the following inequalities
The proof is given in Lemma A.2 from Konev and Pergamenshchikov (2015).
1.3 Properties of the trigonometric basis
Lemma A.5
For any \(1\le j\le n\) and any \({\widetilde{\varepsilon }}>0\), the discrete trigonometric Fourier coefficients \((\theta _{j,n})_{1\le j\le n}\) introduced in (4.3) for \(S\in W_{k,r}\) are bounded as
where the coefficients \(\theta _{j}\) are defined in (5.5).
Proof
First we represent the function S in \({{\mathcal {L}}}[\mathbf{x}_{0},\,\mathbf{x}_{1}]\) as
Since \( \theta _{j,n}=(S,\phi _{j})_{n} =\theta _{j} + (\Delta _{n},\phi _{j})_{n}\), we get, that for any \(0<{\widetilde{\varepsilon }}<1\),
Moreover, through Lemma A.4 and the definition (5.5) we deduce
Taking into account here that \(2[l/2]\ge l-1\) for \(l\ge 2\), we get
Similarly, for any \(n\ge 1\),
Hence Lemma A.5. \(\square \)
Lemma A.6
For any \(n\ge 2\), \(1\le m< n\) and \(r>0\), the coefficients \((\theta _{j,n})_{1\le j\le n}\) of functions S from the class \(W_{k,r}\) satisfy, for any \({\widetilde{\varepsilon }}>0\), the following inequality
where \({\check{r}}_{1}=r{\check{\mathbf{x}}}^{2k}/\pi ^{2(k-1)}\).
Proof
First we note that
where the function \(\Delta _{m}(\cdot )\) is defined in (A.5). By applying Lemma A.4 with \(f=\Delta _{m}, g=0\), and taking into account the inequality (A.6), we obtain the bound (A.7). Hence Lemma A.6\(\square \)
Lemma A.7
For any \(k\ge 1\),
where \(\overline{\phi }_{l}(x)={\check{\mathbf{x}}}\phi ^2_{l}(x)-1\).
Proof of this result is given in Lemma A.2 from Galtchouk and Pergamenshchikov (2009a).
Rights and permissions
About this article
Cite this article
Galtchouk, L.I., Pergamenshchikov, S.M. Adaptive efficient analysis for big data ergodic diffusion models. Stat Inference Stoch Process 25, 127–158 (2022). https://doi.org/10.1007/s11203-021-09241-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11203-021-09241-9
Keywords
- Adaptive nonparametric drift estimation
- Asymptotic efficiency
- Discrete time data
- Nonasymptotic estimation
- Model selection
- Quadratic risk
- Sharp oracle inequality