A Sequential Framework for Composite Hypothesis Testing

This paper addresses the problem of classification via composite sequential hypothesis testing. We focus on two possible schemes for the hypotheses: non-nested and nested. For the first case, we present the generalized sequential probability ratio test (GSPRT) and provide an analysis of its asymptotic optimality. Yet, for the nested case, this algorithm is shown to be inconsistent. Consequently, an alternative solution is derived based on Bayesian considerations, similar to the ones used for the Bayesian information criterion and asymptotic maximum a posteriori probability criterion for model order selection. The proposed test, named penalized GSPRT (PGSPRT), is based on restraining the exponential growth of the GSPRT with respect to the sequential probability ratio test. Furthermore, the commonly used performance measure for sequential tests, known as the average sample number, is evaluated for the PGSPRT under each of the hypotheses. Simulations are carried out to compare the performance measures of the proposed algorithms for two nested model order selection problems.

[1]  Abdelhak M. Zoubir,et al.  Bootstrap based sequential probability ratio tests , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  T. Lai.  Nearly Optimal Sequential Tests of Composite Hypotheses , 1988 .

[3]  Y. Selen,et al.  Model-order selection: a review of information criterion rules , 2004, IEEE Signal Processing Magazine.

[4]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[5]  J. Andel.  Sequential Analysis , 2022, The SAGE Encyclopedia of Research Design.

[6]  Alexander G. Tartakovsky,et al.  Asymptotic Optimality of Certain Multihypothesis Sequential Tests: Non‐i.i.d. Case , 1998 .

[7]  Philippe Forster,et al.  Threshold performance analysis of maximum likelihood DOA estimation , 2004, IEEE Transactions on Signal Processing.

[8]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[9]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[10]  R. Khas'minskii,et al.  Sequential Testing for Several Signals in Gaussian White Noise , 1984 .

[11]  Jorma Rissanen,et al.  Fisher information and stochastic complexity , 1996, IEEE Trans. Inf. Theory.

[12]  Joseph Tabrikian,et al.  Waveform design for sequential detection with subspace interference , 2012, 2012 IEEE 7th Sensor Array and Multichannel Signal Processing Workshop (SAM).

[13]  David Middleton,et al.  Optimum sequential detection of signals in noise , 1955, IRE Trans. Inf. Theory.

[14]  Alexander G. Tartakovsky.  Asymptotically optimal sequential tests for nonhomogeneous processes , 1998 .

[15]  Sawasd Tantaratana,et al.  Relative efficiency of the sequential probability ratio test in signal detection , 1978, IEEE Trans. Inf. Theory.

[16]  G. Casella,et al.  Statistical Inference , 2003, Encyclopedia of Social Network Analysis and Mining.

[17]  T. Lai.  Asymptotic Optimality of Invariant Sequential Probability Ratio Tests , 1981 .

[18]  H. Chernoff.  Sequential Analysis and Optimal Design , 1987 .

[19]  Petar M. Djuric,et al.  Asymptotic MAP criteria for model selection , 1998, IEEE Trans. Signal Process..

[20]  M. Kulldorff,et al.  A Maximized Sequential Probability Ratio Test for Drug and Vaccine Safety Surveillance , 2011 .

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

[22]  R. Khan,et al.  Sequential Tests of Statistical Hypotheses. , 1972 .

[23]  P. Armitage.  Sequential Analysis with More than Two Alternative Hypotheses, and its Relation to Discriminant Function Analysis , 1950 .

[24]  B. Bhat,et al.  On the Method of Maximum-Likelihood for Dependent Observations , 1974 .

[25]  A. V. D. Vaart.  Asymptotic Statistics: Delta Method , 1998 .

[26]  N. V. Verdenskaya,et al.  Asymptotically Optimal Sequential Testing of Multiple Hypotheses for Nonhomogeneous Gaussian Processes in Asymmetric Case , 1992 .

[27]  Joseph Tabrikian,et al.  Adaptive waveform design for target detection with sequential composite hypothesis testing , 2016, 2016 IEEE Statistical Signal Processing Workshop (SSP).

[28]  Fazlollah M. Reza,et al.  Introduction to Information Theory , 2004, Lecture Notes in Electrical Engineering.

[29]  C. R. Rao,et al.  Information and the Accuracy Attainable in the Estimation of Statistical Parameters , 1992 .

[30]  T. Lai.  SEQUENTIAL ANALYSIS: SOME CLASSICAL PROBLEMS AND NEW CHALLENGES , 2001 .

[31]  H. Vincent Poor,et al.  Asymptotic efficiencies of truncated sequential tests , 1982, IEEE Trans. Inf. Theory.

[32]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[33]  L. Brown,et al.  A Unified Conditional Frequentist and Bayesian Test for Fixed and Sequential Simple Hypothesis Testing , 1994 .

[34]  Yaakov Bar-Shalom,et al.  On the Asymptotic Properties of the Maximum-Likelihood Estimate Obtained from Dependent Observations , 1971 .

[35]  Joseph Tabrikian,et al.  Bayesian Estimation in the Presence of Deterministic Nuisance Parameters—Part II: Estimation Methods , 2015, IEEE Transactions on Signal Processing.

[36]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[37]  L. Wasserman,et al.  A Reference Bayesian Test for Nested Hypotheses and its Relationship to the Schwarz Criterion , 1995 .

[38]  A. Wald.  On Cumulative Sums of Random Variables , 1944 .

[39]  H. White.  Maximum Likelihood Estimation of Misspecified Models , 1982 .

[40]  Alexander G. Tartakovsky.  MINIMAX INVARIANT REGRET SOLUTION TO THE N-SAMPLE SLIPPAGE PROBLEM , 1997 .

[41]  C. C. Lee,et al.  A modified sequential detection procedure , 1984, IEEE Trans. Inf. Theory.

[42]  Joseph Tabrikian.  Adaptive waveform design for target enumeration in cognitive radar , 2013, 2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[43]  J. Cavanaugh,et al.  The Bayesian information criterion: background, derivation, and applications , 2012 .

[44]  Pushpa N. Rathie,et al.  On the entropy of continuous probability distributions (Corresp.) , 1978, IEEE Trans. Inf. Theory.

[45]  H. Cramér.  Mathematical methods of statistics , 1947 .

[46]  Venugopal V. Veeravalli,et al.  Asymptotic efficiency of a sequential multihypothesis test , 1995, IEEE Trans. Inf. Theory.

[47]  A. McQuarrie,et al.  Regression and Time Series Model Selection , 1998 .

[48]  S. Silvey.  A Note on Maximum‐Likelihood in the Case of Dependent Random Variables , 1961 .

[49]  D. Cox,et al.  Asymptotic techniques for use in statistics , 1989 .

[50]  Venugopal V. Veeravalli,et al.  Multihypothesis sequential probability ratio tests - Part I: Asymptotic optimality , 1999, IEEE Trans. Inf. Theory.