Nearly Minimax One-Sided Mixture-Based Sequential Tests

@article{Fellouris2011NearlyMO,
  title={Nearly Minimax One-Sided Mixture-Based Sequential Tests},
  author={Georgios Fellouris and Alexander G. Tartakovsky},
  journal={Sequential Analysis},
  year={2011},
  volume={31},
  pages={297 - 325}
}
Abstract We focus on one-sided, mixture-based stopping rules for the problem of sequential testing a simple null hypothesis against a composite alternative. For the latter, we consider two cases—either a discrete alternative or a continuous alternative that can be embedded into an exponential family. For each case, we find a mixture-based stopping rule that is nearly minimax in the sense of minimizing the maximal Kullback–Leibler information. The proof of this result is based on finding an… 
Almost optimal sequential tests of discrete composite hypotheses
We consider the problem of sequentially testing a simple null hypothesis versus a composite alternative hypothesis that consists of a finite set of densities. We study sequential tests that are based
Minimax optimal sequential hypothesis tests for Markov processes
Under mild Markov assumptions, sufficient conditions for strict minimax optimality of sequential tests for multiple hypotheses under distributional uncertainty are derived. First, the design of
Opportunistic Detection Under a Fixed-Sample-Size Setting
TLDR
A Chernoff-Stein lemma type of characterization of the exponential decay rate of the miss probability under the Neyman-Pearson criterion is established, and consequently, a performance metric of asymptotic exponential efficiency loss is proposed and discussed.
Multichannel Sequential Detection—Part I: Non-i.i.d. Data
TLDR
An asymptotic theory for a general stochastic model, where the various data streams can be coupled and correlated, and the data in each stream can be dependent and non-identically distributed is developed.
Opportunistic Detection Rules: Finite and Asymptotic Analysis
TLDR
In the asymptotic regime, the tradeoff among the exponents of the (false alarm and miss) error probabilities and the normalized expected stopping time under the alternative hypothesis is completely characterized and proved to be tight, via an information-theoretic argument.
Sequential Hypothesis Testing and Changepoint Detection : Past and Future
1. Nearly Optimal Sequential Tests of Composite Hypotheses. Let X1, X2, . . . be a sequence of independent and identically distributed (iid) observations, and let pθ(x) be a density (parametrized by
Opportunistic detection rules
TLDR
Several key properties of ODRs are established in this paper, in both the asymptotic regime in which the maximum sample size grows without bound, and the finite regime inWhich the maximum samples size is a fixed finite number.
Discussion on “Change-Points: From Sequential Detection to Biology and Back” by David Siegmund
TLDR
This discussion expands on some of the methods and recent results of change-point detection, mostly sequential, and their scientific and historic overview.
Inferring Structure and Forecasting Dynamics on Evolving Networks
TLDR
This interdisciplinary MURI was positioned at the interface between social, mathematical and computational approaches to networks with goals of developing stable metrics for inferring network structures, forecasting dynamical social and information processes on networks, and predicting the outcomes of network interventions.
Robust Statistics for Signal Processing
K-distribution, 103, 121–123 M-estimator, 1, 5, 10–12, 19, 21, 23, 27, 46, 48, 53, 54, 61–63, 67, 100, 110–113, 117, 118, 120, 121, 140, 141, 157, 162, 167, 183, 197, 206, 214, 229, 249, 260 ARMA

References

SHOWING 1-10 OF 36 REFERENCES
Nearly-optimal sequential tests for finitely many parameter values
Combinations of one-sided sequential probability ratio tests (SPRT's) are shown to be "nearly optimal" for problems involving a finite number of possible underlying distributions. Subject to error
Asymptotic Optimality of Certain Multihypothesis Sequential Tests: Non‐i.i.d. Case
TLDR
This paper shows that two specific constructions of sequential tests asymptotically minimize not only the expected time of observation but also any positive moment of the stopping time distribution under fairly general conditions for a finite number of simple hypotheses.
Open-ended tests for Koopman-Darmois families
The generalized likelihood ratio is used to define a stopping rule for rejecting the null hypothesis θ = θ0 in favor of θ > θ0. Subject to a bound α on the probability of ever stopping in case θ =
A simple comparision of mixture vs. nonanticipating estimation
When a problem entails an unknown nuisance parameter, estimating the parameter and (alternatively) integrating it out (with respect to some probability measure) are two of the approaches commonly
Multihypothesis sequential probability ratio tests - Part II: Accurate asymptotic expansions for the expected sample size
For pt. I see ibid. vol.45, p.2448-61, 1999. We proved in pt.I that two specific constructions of multihypothesis sequential tests, which we refer to as multihypothesis sequential probability ratio
Multihypothesis sequential probability ratio tests - Part I: Asymptotic optimality
TLDR
These results provide a complete generalization of the results given by Veeravalli and Baum, where it was shown that the quasi-Bayesian MSPRT is asymptotically efficient with respect to the expected sample size for i.i.d. observations.
Integrated Risk of Asymptotically Bayes Sequential Tests
For general multiple-decision testing problems, and even two-decision problems involving more than two states of nature, how to construct sequential procedures which are optimal (e.g. minimax, Bayes,
Sequential detection of targets in multichannel systems
TLDR
The results allow us to conclude that the use of the sequential detection algorithm substantially reduces the required resources of the system compared to the best nonsequential algorithm.
Nonanticipating estimation applied to sequential analysis and changepoint detection
Suppose a process yields independent observations whose distributions belong to a family parameterized by theta E Theta. When the process is in control, the observations are i.i.d. with a known
A Nonlinear Renewal Theory with Applications to Sequential Analysis II
Abstract : An analogue of Blackwell's renewal theorem is obtained for processes Z sub n = S sub n + xi sub n, where S sub n is the nth partial sum of a sequence X1,X2,... of independent identically
...
1
2
3
4
...