In estimation of the large precision matrix, this paper suggests a new shrinkage estimator, called the linear ridge estimator. This estimator is motivated from a Bayesian aspect for a spike and slab prior distribution of the precision matrix, and has a form of convex combination of the ridge estimator and the identity matrix multiplied by scalar. The optimal parameters in the linear ridge estim...

We study biased control variates (BCVs), whose purpose is to improve the efficiency of stochastic simulation experiments. BCVs replace the control-simulation mean with an approximation; the resulting control-variate estimator is biased. This bias may not be a significant issue for finite sample sizes, however, because our estimator minimizes the more general mean-squared-error (mse), i.e., the ...

We analyze differences between two information-theoretically motivated ap­ proaches to statistical inference and model selection: the Minimum Description Length (MDL) principle, and the Minimum Message Length (MML) principle. Based on this analysis, we present two revised versions of MML: a pointwise estimator which gives the MML-optimal single parameter model, and a volumewise estimator which ...

The generalization of the maximum-likelihood-like estimator for clock skew by Leng and Wu in the above paper is erroneous because the correlation of the noise components in the model is not taken into account in the derivation of the maximum likelihood estimator, its performance bound, and the optimal selection of the gap between two subtracting time stamps. This comment investigates the issue ...

The peak of the polynomial Wigner-Ville distribution is known to be a consistent estimator of the instantaneous frequency for polynomial FM signals. In this paper, we present an algorithm for the design of an optimal time-varying window length for this estimator when noisy non-linear, not necessarily polynomial, FM signals are considered. The results obtained show that the estimator is accurate...

We give a comprehensive theoretical characterization of a nonparametric estimator for the L2 divergence between two continuous distributions. We first bound the rate of convergence of our estimator, showing that it is √ n-consistent provided the densities are sufficiently smooth. In this smooth regime, we then show that our estimator is asymptotically normal, construct asymptotic confidence int...

This paper considers distributed estimation over heterogeneous sensor networks. We propose a distributed estimation strategy based on PageRank algorithm, where the link weight depends on the edge estimation covariances. We prove that the proposed estimator obtains better estimates than one typical estimator under identical initial conditions. Motivated by the advantage of the sensors with high ...

We obtain an optimal estimator for a domain (small area) total using a linear least-squares prediction approach under a design-based model. The optimal estimator is the same as that obtained under a super-population model approach, and reproduces the classical form of the synthetic estimator in an extreme case. Using the concept of M-optimality, we generalize a well known theorem (Royall, 1976)...

We construct an on-line estimator with equidistant design for tracking a smooth function from Stone-Ibragimov-Khasminskii class. This estimator has the optimal convergence rate of risk to zero in sample size. The procedure for setting coefficients of the estimator is controlled by a single parameter and has a simple numerical solution. The off-line version of this estimator allows to eliminate ...