Hasil untuk "math.ST"

Yasuyuki Hamura

Conditions for Bayesian posterior robustness have been examined in recent literature. However, many of the proofs seem to be long and complicated. In this paper, we first summarize some basic lemmas that have been applied implicitly or explicitly. Then, using them, we give a simple proof of posterior robustness. Our sufficient condition is new and practically relevant.

Charles Arnal

In this note, we show that the convolution of a discrete symmetric log-concave distribution and a discrete symmetric bimodal distribution can have any strictly positive number of modes. A similar result is proved for smooth distributions.

Michael Boldin

We consider a stationary $AR(p)$ model. The autoregression parameters are unknown as well as the distribution of innovations. Based on the residuals from the parameter estimates, an analog of empirical distribution function is defined and the tests of Kolmogorov's and $ω^2$ type is constructed for testing hypotheses on the normality of innovations. We obtain the asymptotic power of these tests under local alternatives.

Fang Xie, Zhijie Xiao

We prove the consistency of the $\ell_1$ penalized negative binomial regression (NBR). A real data application about German health care demand shows that the $\ell_1$ penalized NBR produces a more concise but more accurate model, comparing to the classical NBR.

Maciej Skorski

We revisit the problem of \emph{missing mass concentration}, developing a new method of estimating concentration of heterogenic sums, in spirit of celebrated Rosenthal's inequality. As a result we slightly improve the state-of-art bounds due to Ben-Hamou at al., and simplify the proofs.

Faith Zhang, Xiongzhi Chen

For a weighted false discovery rate (FDR) procedure for multiple testing the means of equicorrelated normal random variables, we provide an analytic, non-asymptotic, uniform FDR upper bound for its FDR. Two additional and related results are also provided.

Ulrich Djemby Bivigou, Guy Martial Nkiet

We consider a robust version of multiple-set linear canonical analysis obtained by using a S-estimator of covariance operator. The related influence functions are derived. Asymptotic properties of this robust method are obtained and a robust test for mutual non-correlation is introduced.

Gauri Sankar Datta, Brunero Liseo

Discussion of Overall Objective Priors by James O. Berger, Jose M. Bernardo, Dongchu Sun [arXiv:1504.02689].

Ery Arias-Castro, Bruno Pelletier

Rosenbaum (2005) proposed the crossmatch test for two-sample goodness-of-fit testing in arbitrary dimensions. We prove that the test is consistent against all fixed alternatives. In the process, we develop a general consistency result based on (Henze & Penrose, 1999) that applies more generally.

Jung Hun Han

Fractional renewal processes as a generalization of Poisson process are already in the literature. In this paper, by introducing a new concept of generalized density function, the authors construct new fractional renewal processes in the $α$-fractional space and show that it is another interesting and useful generalization of Poisson process.

Georgios Fellouris

Certain renewal theorems are extended to the case that the rate of the renewal process goes to 0 and, more generally, to the case that the drift of the random walk goes to infinity. These extensions are motivated by and applied to the problem of decentralized parameter estimation under severe communication constraints.

Radhendushka Srivastava, Ping Li

We study the effect of stochastic sampling on the estimation of the drift parameter of continuous time AR(1) process. A natural distribution free moment estimator is considered for the drift based on stochastically observed time points. The effect of the constraint of the minimum separation between successive samples on the estimation of the drift is studied.

Yu. Golubev

We consider the problem of recovering an unknown vector from noisy data with the help of projection estimates. The goal is to find a convex combination of these estimates with the minimal risk. We study an aggregation method based on the so-called exponential weighting and provide a new upper bound for the mean square risk of this method.

Krzysztof A. Meissner

We propose a simple way of testing whether a given set of observations can come from a given theoretical cumulative distribution. In the test more weight is attached to the tails of the distribution than in the usual Kolmogorov or Smirnov tests. The respective probability distribution is derived.

Dong Li, Shiqing Ling, Howell Tong

Moving average models, linear or nonlinear, are characterized by their short memory. This paper shows that, in the presence of feedback in the dynamics, the above characteristic can disappear.

Paulo C. Marques F., Carlos A. de B. Pereira

A tractable nonparametric prior over densities is introduced which is closed under sampling and exhibits proper posterior asymptotics.

Philipp Arbenz, Paul Embrechts, Giovanni Puccetti

We propose a new algorithm to compute numerically the distribution function of the sum of $d$ dependent, non-negative random variables with given joint distribution.

Matyas Barczy, Marton Ispany, Gyula Pap

In this paper the asymptotic behavior of conditional least squares estimators of the autoregressive parameter for nonprimitive unstable integer-valued autoregressive models of order 2 (INAR(2)) is described.

Matthieu Lerasle

We build confidence balls for the common density $s$ of a real valued sample $X_1,...,X_n$. We use resampling methods to estimate the projection of $s$ onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all $n\geq2$ and the balls are adaptive over a collection of linear spaces.

N. Chernov

We study a nonlinear regression problem of fitting a circle (or a circular arc) to scattered data. We prove that under any standard assumptions on the statistical distribution of errors that are commonly adopted in the literature, the estimates of the circle center and radius have infinite moments. We also discuss methodological implications of this fact.