Pseudo-maximization and self-normalized processes

Self-normalized processes are basic to many probabilistic and statistical studies. They arise naturally in the the study of stochastic inte- grals, martingale inequalities and limit theorems, likelihood-based methods in hypothesistesting and parameterestimation, and Studentizedpivots and bootstrap-t methods for confidence intervals. In contrast to standard nor- malization, large values of the observationsplay a lesser role as they appear both in the numerator and its self-normalized denominator, thereby mak- ing the process scale invariantand contributing to its robustness. Herein we survey a number of results for self-normalized processes in the case of de- pendentvariablesand describe a key method called "pseudo-maximization" that has been used to derive these results. In the multivariate case, self- normalization consists of multiplying by the inverse of a positive definite matrix (instead of dividing by a positive random variable as in the scalar case) and is ubiquitous in statistical applications, examples of which are given. AMS 2000 subject classifications: Primary 60K35, 60K35; secondary 60K35.

[1]  P. Erdös.  On the Law of the Iterated Logarithm , 1942 .

[2]  H. Robbins,et al.  Boundary Crossing Probabilities for the Wiener Process and Sample Sums , 1970 .

[3]  W. Stout.  A martingale analogue of Kolmogorov's law of the iterated logarithm , 1970 .

[4]  H. Robbins.  Statistical Methods Related to the Law of the Iterated Logarithm , 1970 .

[5]  C. Mallows,et al.  Limit Distributions of Self-normalized Sums , 1973 .

[6]  W. Stout.  Maximal Inequalities and the Law of the Iterated Logarithm , 1973 .

[7]  T. Lai.  Boundary Crossing Probabilities for Sample Sums and Confidence Sequences , 1976 .

[8]  V. Slavova.  Berry-Esseen bound for student's statistic , 1986 .

[9]  Marc Yor,et al.  Inequalities for a Pair of Processes Stopped at a Random Time , 1986 .

[10]  M. Yor,et al.  Continuous martingales and Brownian motion , 1990 .

[11]  J. Kuelbs,et al.  Some Extensions of the LIL Via Self-Normalizations , 1991 .

[12]  A. Dembo.  Moderate Deviations for Martingales with Bounded Jumps , 1996 .

[13]  D. Khoshnevisan.  Deviation inequalities for continuous martingales , 1996 .

[14]  F. Götze,et al.  The Berry-Esseen bound for student's statistic , 1996 .

[15]  F. Götze,et al.  A Berry-Esséen bound for student's statistic in the non-I.I.D. case , 1996 .

[16]  Friedrich Götze,et al.  When is the Student $t$-statistic asymptotically standard normal? , 1997 .

[17]  Q. Shao.  Self-normalized large deviations , 1997 .

[18]  E. Giné,et al.  On the LIL for Self-Normalized Sums of IID Random Variables , 1998 .

[19]  E. Giné,et al.  Decoupling: From Dependence to Independence , 1998 .

[20]  D. Nualart,et al.  Estimation of Densities and Applications , 1998 .

[21]  V. Peña.  A General Class of Exponential Inequalities for Martingales and Ratios , 1999 .

[22]  Xia Chen.  The Law of the Iterated Logarithm for Functionals of Harris Recurrent Markov Chains: Self Normalization , 1999 .

[23]  Vladimir Spokoiny,et al.  Deviation probability bound for martingales with applications to statistical estimation , 2000 .

[24]  Bing-Yi Jing,et al.  An Exponential Nonuniform Berry-Esseen Bound for Self-Normalized Sums , 1999 .

[25]  R. Bañuelos,et al.  Probabilistic behavior of harmonic functions , 1999 .

[26]  Tze Leung Lai,et al.  Asymptotic approximations for error probabilities of sequential or fixed sample size tests in exponential families , 1999 .

[27]  Principes de déviations modérées pour des martingales autonormalisées , 2000 .

[28]  Goran Peskir,et al.  Maximal inequalities for the Ornstein-Uhlenbeck process , 2000 .

[29]  T. Lai,et al.  Moment Bounds for Self-Normalized Martingales , 2000 .

[30]  Bernard Bercu,et al.  On large deviations in the Gaussian autoregressive process: stable, unstable and explosive cases , 2001 .

[31]  E. Rio,et al.  Concentration inequalities, large and moderate deviations for self-normalized empirical processes , 2002 .

[32]  T. Lai.  Likelihood Ratio Identities and Their Applications to Sequential Analysis , 2004 .

[33]  Bing-Yi Jing,et al.  Self-normalized Cramér-type large deviations for independent random variables , 2003 .

[34]  Q. Shao,et al.  Saddlepoint approximation for Student’s t-statistic with no moment conditions , 2004, math/0508604.

[35]  F. Götze,et al.  Limit distributions of Studentized means , 2004 .

[36]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .

[37]  Xiongzhi Chen.  Brownian Motion and Stochastic Calculus , 2008 .

[38]  P. Erdos,et al.  On the Law of the Iterated Logarithm , 1942 .