Bayesian sequential testing of the drift of a Brownian motion
Ekström, Erik1 ; Vaicenavicius, Juozas1
1 Uppsala University, Box 480, 75106 Uppsala, Sweden
ESAIM: Probability and Statistics, Tome 19 (2015), pp. 626-648.

We study a classical Bayesian statistics problem of sequentially testing the sign of the drift of an arithmetic Brownian motion with the 0-1 loss function and a constant cost of observation per unit of time for general prior distributions. The statistical problem is reformulated as an optimal stopping problem with the current conditional probability that the drift is non-negative as the underlying process. The volatility of this conditional probability process is shown to be non-increasing in time, which enables us to prove monotonicity and continuity of the optimal stopping boundaries as well as to characterize them completely in the finite-horizon case as the unique continuous solution to a pair of integral equations. In the infinite-horizon case, the boundaries are shown to solve another pair of integral equations and a convergent approximation scheme for the boundaries is provided. Also, we describe the dependence between the prior distribution and the long-term asymptotic behaviour of the boundaries.

DOI : 10.1051/ps/2015012
Classification : 62L10, 60G40, 62C10
Mots-clés : Bayesian analysis, sequential hypothesis testing, optimal stopping
Ekström, Erik 1 ; Vaicenavicius, Juozas 1

1 Uppsala University, Box 480, 75106 Uppsala, Sweden 
@article{PS_2015__19__626_0,
     author = {Ekstr\"om, Erik and Vaicenavicius, Juozas},
     title = {Bayesian sequential testing of the drift of a {Brownian} motion},
     journal = {ESAIM: Probability and Statistics},
     pages = {626--648},
     publisher = {EDP-Sciences},
     volume = {19},
     year = {2015},
     doi = {10.1051/ps/2015012},
     mrnumber = {3433430},
     zbl = {1369.62201},
     language = {en},
     url = {http://archive.numdam.org/articles/10.1051/ps/2015012/}
}
TY  - JOUR
AU  - Ekström, Erik
AU  - Vaicenavicius, Juozas
TI  - Bayesian sequential testing of the drift of a Brownian motion
JO  - ESAIM: Probability and Statistics
PY  - 2015
SP  - 626
EP  - 648
VL  - 19
PB  - EDP-Sciences
UR  - http://archive.numdam.org/articles/10.1051/ps/2015012/
DO  - 10.1051/ps/2015012
LA  - en
ID  - PS_2015__19__626_0
ER  - 
%0 Journal Article
%A Ekström, Erik
%A Vaicenavicius, Juozas
%T Bayesian sequential testing of the drift of a Brownian motion
%J ESAIM: Probability and Statistics
%D 2015
%P 626-648
%V 19
%I EDP-Sciences
%U http://archive.numdam.org/articles/10.1051/ps/2015012/
%R 10.1051/ps/2015012
%G en
%F PS_2015__19__626_0
Ekström, Erik; Vaicenavicius, Juozas. Bayesian sequential testing of the drift of a Brownian motion. ESAIM: Probability and Statistics, Tome 19 (2015), pp. 626-648. doi : 10.1051/ps/2015012. http://archive.numdam.org/articles/10.1051/ps/2015012/

A.D. Bain, Crisan, Fundamentals of stochastic filtering. Vol. 60 of Stoch. Model. Appl. Probab. Springer, New York (2009). | MR | Zbl

J.A. Bather, Bayes Procedures for Deciding the Sign of a Normal Mean. In vol. 58 of Proc. Camb. Philos. Soc. (1962) 599–620. | MR | Zbl

P.J. Bickel and Y.A. Yahav, On the Wiener Process Approximation to Bayesian Sequential Testing Problems. In vol. 1 of Proc. of Sixth Berkeley Symp. Math. Statist. Probab. (1972) 57–84. | MR | Zbl

J. Breakwell and H. Chernoff, Sequential tests for the mean of a normal distribution. II. (Large t). Ann. Math. Statist. 35 (1964) 162–173. | MR | Zbl

H. Chernoff, Sequential Tests for the Mean of a Normal Distribution. In vol. 1 of Proc. of 4th Berkeley Sympos. Math. Statist. Prob. (1961) 79–91. | MR | Zbl

H. Chernoff, Sequential tests for the mean of a normal distribution III (small t). Ann. Math. Statist. 36 (1965) 28–54. | MR | Zbl

H. Chernoff, Sequential tests for the mean of a normal distribution IV (discrete case). Ann. Math. Statist. 36 (1965) 55–68. | MR | Zbl

E. Ekström, Properties of American option prices. Stochastic Process. Appl. 114 (2004) 265–278. | MR | Zbl

P. Gapeev and G. Peskir, The Wiener sequential testing problem with finite horizon. Stoch. Stoch. Rep. 76 (2004) 59–75. | MR | Zbl

S. Jacka, Optimal stopping and the American put. Math. Finance 1 (1991) 1–14. | Zbl

S. Janson and J. Tysk, Volatility time and properties of option prices. Ann. Appl. Probab. 13 (2003) 890–913. | MR | Zbl

I. Karatzas and S. Shreve, Brownian Motion and Stochastic Calculus, 2nd edition. Vol. 113 of Grad. Texts Math. Springer-Verlag, New York (1991). | MR | Zbl

I. Karatzas and S. Shreve, Methods of Mathematical Finance. Vol. 39 of Appl. Math. Springer-Verlag, New York (1998). | MR | Zbl

A. Klenke, Probability Theory: A Comprehensive Course. Universitext. Springer–Verlag, London (2008). | MR | Zbl

T.L. Lai, Nearly optimal sequential tests of composite hypotheses. Ann. Statist. 16 (1988) 856–886. | MR | Zbl

T.L. Lai, On optimal stopping problems in sequential hypothesis testing. Statistica Sinica 7 (1997) 33–51. | MR | Zbl

B. Øksendal, Stochastic Differential Equations. An Introduction with Applications, 6th edition. Universitext. Springer-Verlag, Berlin (2003). | MR

G. Peskir, A change-of-variable formula with local time on curves. J. Theoret. Probab. 18 (2005) 499–535. | MR | Zbl

G. Peskir, On the American option problem. Math. Finance 15 (2005) 169–181. | MR | Zbl

G. Peskir and A. Shiryaev, Optimal Stopping and Free-Boundary Problems. Lect. Math. ETH Zürich. Birkhäuser Verlag, Basel (2006). | MR | Zbl

A.N. Shiryaev, Two problems of sequential analysis. Cybernetics 3 (1967) 63–69. | MR

M. Zhitlukhin and A. Muravlev, On Chernoff’s hypotheses testing problem for the drift of a Brownian motion. Theory Probab. Appl. 57 4 (2013) 708–717. | MR | Zbl

Cité par Sources :