显示样式： 排序： IF:  GO 导出

Local polynomial expectile regression Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210505
C. Adam, I. GijbelsThis paper studies local polynomial estimation of expectile regression. Expectiles and quantiles both provide a full characterization of a (conditional) distribution function, but have each their own merits and inconveniences. Local polynomial fitting as a smoothing technique has a major advantage of being simple, allowing for explicit expressions and henceforth advantages when doing inference theory

Variable selection for functional linear models with strong heredity constraint Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210428
Sanying Feng, Menghan Zhang, Tiejun TongIn this paper, we consider the variable selection problem in functional linear regression with interactions. Our goal is to identify relevant main effects and corresponding interactions associated with the response variable. Heredity is a natural assumption in many statistical models involving twoway or higherorder interactions. Inspired by this, we propose an adaptive group Lasso method for the

On the usage of randomized pvalues in the Schweder–Spjøtvoll estimator Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210428
AnhTuan Hoang, Thorsten DickhausWe consider multiple test problems with composite null hypotheses and the estimation of the proportion \(\pi _{0}\) of true null hypotheses. The Schweder–Spjøtvoll estimator \({\hat{\pi }}_0\) utilizes marginal pvalues and relies on the assumption that pvalues corresponding to true nulls are uniformly distributed on [0, 1]. In the case of composite null hypotheses, marginal pvalues are usually computed

Search for minimum aberration designs with uniformity Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210416
Bochuan Jiang, Yaping Wang, Mingyao AiUniform designs have been widely applied in engineering and sciences’ innovation. When a lot of quantitative factors are investigated with as few runs as possible, a supersaturated uniform design with good overall and projection uniformity is needed. By combining combinatorial methods and stochastic algorithms, such uniform designs with flexible numbers of columns are constructed in this article under

The finite sample properties of sparse Mestimators with pseudoobservations Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210408
Benjamin Poignard, JeanDavid FermanianWe provide finite sample properties of general regularized statistical criteria in the presence of pseudoobservations. Under the restricted strong convexity assumption of the unpenalized loss function and regularity conditions on the penalty, we derive nonasymptotic error bounds on the regularized Mestimator. This penalized framework with pseudoobservations is then applied to the Mestimation of

Broken adaptive ridge regression for rightcensored survival data Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210405
Zhihua Sun, Yi Liu, Kani Chen, Gang LiBroken adaptive ridge (BAR) is a computationally scalable surrogate to \(L_0\)penalized regression, which involves iteratively performing reweighted \(L_2\) penalized regressions and enjoys some appealing properties of both \(L_0\) and \(L_2\) penalized regressions while avoiding some of their limitations. In this paper, we extend the BAR method to the semiparametric accelerated failure time (AFT)

Asymptotic behavior of the number of distinct values in a sample from the geometric stickbreaking process Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210403
Pierpaolo De Blasi, Ramsés H. Mena, Igor PrünsterDiscrete random probability measures are a key ingredient of Bayesian nonparametric inference. A sample generates ties with positive probability and a fundamental object of both theoretical and applied interest is the corresponding number of distinct values. The growth rate can be determined from the rate of decay of the small frequencies implying that, when the decreasingly ordered frequencies admit

Empirical likelihood metaanalysis with publication bias correction under Copaslike selection model Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210327
Mengke Li, Yukun Liu, Pengfei Li, Jing QinMetaanalysis is commonly used to synthesize multiple results from individual studies. However, its validation is usually threatened by publication bias and betweenstudy heterogeneity, which can be captured by the Copas selection model. Existing inference methods under this model are all based on conditional likelihood and may not be fully efficient. In this paper, we propose a full likelihood approach

Asymptotic linear expansion of regularized Mestimators Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210324
Tino WernerParametric highdimensional regression requires regularization terms to get interpretable models. The respective estimators correspond to regularized Mfunctionals which are naturally highly nonlinear. Their Gâteaux derivative, i.e., their influence curve linearizes the asymptotic bias of the estimator, but only up to a remainder term which is not guaranteed to tend (sufficiently fast) to zero uniformly

A threestep local smoothing approach for estimating the mean and covariance functions of spatiotemporal Data Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210320
Kai Yang, Peihua QiuSpatiotemporal data are common in practice. Existing methods for analyzing such data often employ parametric modelling with different sets of model assumptions. However, spatiotemporal data in practice often have complicated structures, including complex spatial and temporal data variation, latent spatiotemporal data correlation, and unknown data distribution. Because such data structures reflect

Wasserstein statistics in onedimensional location scale models Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210315
Shunichi Amari, Takeru MatsudaWasserstein geometry and information geometry are two important structures to be introduced in a manifold of probability distributions. Wasserstein geometry is defined by using the transportation cost between two distributions, so it reflects the metric of the base manifold on which the distributions are defined. Information geometry is defined to be invariant under reversible transformations of the

Nonparametric regression with warped wavelets and strong mixing processes Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210313
Luz M. Gómez, Rogério F. Porto, Pedro A. MorettinWe consider the situation of a univariate nonparametric regression where either the Gaussian error or the predictor follows a stationary strong mixing stochastic process and the other term follows an independent and identically distributed sequence. Also, we estimate the regression function by expanding it in a wavelet basis and applying a hard threshold to the coefficients. Since the observations

Distributionfree testing in linear and parametric regression Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210308
Estate V. KhmaladzeRecently, a distributionfree approach for testing parametric hypotheses based on unitary transformations has been suggested in Khmaladze (Ann Stat 41:2979–2993, 2013, Bernoulli 22:563–588, 2016) and further studied in Nguyen (Metrika 80:153–170, 2017) and Roberts (Stat Probab Lett 150:47–53, 2019). In this paper, we show that the transformation takes very simple form in distributionfree testing of

Efficient estimation methods for nonGaussian regression models in continuous time Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210303
Evgeny Pchelintsev, Serguei Pergamenshchikov, Maria PovzunIn this paper, we develop an efficient nonparametric estimation theory for continuous time regression models with nonGaussian Lévy noises in the case when the unknown functions belong to Sobolev ellipses. Using the Pinsker’s approach, we provide a sharp lower bound for the normalized asymptotic mean square accuracy. However, the main result obtained by Pinsker for the Gaussian white noise model is

Smooth distribution function estimation for lifetime distributions using Szasz–Mirakyan operators Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210220
Ariane Hanebeck, Bernhard KlarIn this paper, we introduce a new smooth estimator for continuous distribution functions on the positive real halfline using Szasz–Mirakyan operators, similar to Bernstein’s approximation theorem. We show that the proposed estimator outperforms the empirical distribution function in terms of asymptotic (integrated) meansquared error and generally compares favorably with other competitors in theoretical

Determining the number of canonical correlation pairs for highdimensional vectors Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210212
Jiasen Zheng, Lixing ZhuFor two random vectors whose dimensions are both proportional to the sample size, we in this paper propose two ridge ratio criteria to determine the number of canonical correlation pairs. The criteria are, respectively, based on eigenvalue differencebased and centered eigenvaluebased ridge ratios. Unlike existing methods, the criteria make the ratio at the index we want to identify stick out to show

Global jump filters and quasilikelihood analysis for volatility Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210116
Haruhiko Inatsugu, Nakahiro YoshidaWe propose a new estimation scheme for estimation of the volatility parameters of a semimartingale with jumps based on a jump detection filter. Our filter uses all of the data to analyze the relative size of increments and to discriminate jumps more precisely. We construct quasimaximum likelihood estimators and quasiBayesian estimators and show limit theorems for them including \(L^p\)estimates

A permutation test for the twosample rightcensored model Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210112
Grzegorz WyłupekThe paper presents a novel approach to solve a classical twosample problem with rightcensored data. As a result, an efficient procedure for verifying equality of the two survival curves is developed. It generalizes, in a natural manner, a wellknown standard, that is, the logrank test. Under the null hypothesis, the new test statistic has an asymptotic Chisquare distribution with one degree of

Efficient likelihoodbased inference for the generalized Pareto distribution Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210111
Hideki Nagatsuka, N. BalakrishnanIt is well known that inference for the generalized Pareto distribution (GPD) is a difficult problem since the GPD violates the classical regularity conditions in the maximum likelihood method. For parameter estimation, most existing methods perform satisfactorily only in the limited range of parameters. Furthermore, the interval estimation and hypothesis tests have not been studied well in the literature

Identifying shifts between two regression curves Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210106
Holger Dette, Subhra Sankar Dhar, Weichi WuThis article studies the problem whether two convex (concave) regression functions modelling the relation between a response and covariate in two samples differ by a shift in the horizontal and/or vertical axis. We consider a nonparametric situation assuming only smoothness of the regression functions. A graphical tool based on the derivatives of the regression functions and their inverses is proposed

Improper versus finitely additive distributions as limits of countably additive probabilities Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210103
Pierre Druilhet, Erwan Saint Loubert BiéThe Bayesian paradigm with proper priors can be extended either to improper distributions or to finitely additive probabilities (FAPs). Improper distributions and diffuse FAPs can be seen as limits of proper distribution sequences for specific convergence modes. In this paper, we compare these two kinds of limits. We show that improper distributions and FAPs represent two distinct features of the limit

Robust test for structural instability in dynamic factor models Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210102
Byungsoo Kim, Junmo Song, Changryong BaekIn this paper, we consider a robust test for structural breaks in dynamic factor models. The proposed framework considers structural changes when the underlying highdimensional time series is contaminated by outlying observations, which are often observed in many real applications such as fMRI, economics and finance. We propose a test based on the robust estimation of a vector autoregressive model

A universal approach to estimate the conditional variance in semimartingale limit theorems Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210101
Mathias VetterThe typical central limit theorems in highfrequency asymptotics for semimartingales are results on stable convergence to a mixed normal limit with an unknown conditional variance. Estimating this conditional variance usually is a hard task, in particular when the underlying process contains jumps. For this reason, several authors have recently discussed methods to automatically estimate the conditional

Asymptotic behavior of mean density estimators based on a single observation: the Boolean model case Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210101
Federico Camerlenghi, Claudio Macci, Elena VillaThe mean density estimation of a random closed set in \(\mathbb {R}^d\), based on a single observation, is a crucial problem in several application areas. In the case of stationary random sets, a common practice to estimate the mean density is to take the ndimensional volume fraction with observation window as large as possible. In the present paper, we provide large and moderate deviation results

Fast estimation of multivariate spatiotemporal Hawkes processes and network reconstruction Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20210101
Baichuan Yuan, Frederic P. Schoenberg, Andrea L. BertozziWe present a fast, accurate estimation method for multivariate Hawkes selfexciting point processes widely used in seismology, criminology, finance and other areas. There are two major ingredients. The first is an analytic derivation of exact maximum likelihood estimates of the nonparametric triggering density. We develop this for the multivariate case and add regularization to improve stability and

Generalized inverseGaussian frailty models with application to TARGET neuroblastoma data Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20201124
Luiza S. C. Piancastelli, Wagner BarretoSouza, Vinícius D. MayrinkA new class of survival frailty models based on the generalized inverseGaussian (GIG) distributions is proposed. We show that the GIG frailty models are flexible and mathematically convenient like the popular gamma frailty model. A piecewiseexponential baseline hazard function is employed, yielding flexibility for the proposed class. Although a closedform observed loglikelihood function is available

Mellin–Meijer kernel density estimation on $${{\mathbb {R}}}^+$$ R + Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20201124
Gery GeenensKernel density estimation is a nonparametric procedure making use of the smoothing power of the convolution operation. Yet, it performs poorly when the density of a positive variable is estimated, due to boundary issues. So, various extensions of the kernel estimator allegedly suitable for \({\mathbb {R}}^+\)supported densities, such as those using asymmetric kernels, abound in the literature. Those

Asymptotic theory of dependent Bayesian multiple testing procedures under possible model misspecification Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20201113
Noirrit Kiran Chandra, Sourabh BhattacharyaWe study asymptotic properties of Bayesian multiple testing procedures and provide sufficient conditions for strong consistency under general dependence structure. We also consider a novel Bayesian multiple testing procedure and associated error measures that coherently accounts for the dependence structure present in the model. We advocate posterior versions of FDR and FNR as appropriate error rates

Regularized bridgetype estimation with multiple penalties Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20201109
Alessandro De Gregorio, Francesco IafrateThe aim of this paper is to introduce an adaptive penalized estimator for identifying the true reduced parametric model under the sparsity assumption. In particular, we deal with the framework where the unpenalized estimator of the structural parameters needs simultaneously multiple rates of convergence (i.e., the socalled mixedrates asymptotic behavior). We introduce a bridgetype estimator by taking

Gaussian graphical models with toric vanishing ideals Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20201102
Pratik Misra, Seth SullivantGaussian graphical models are semialgebraic subsets of the cone of positive definite covariance matrices. They are widely used throughout natural sciences, computational biology and many other fields. Computing the vanishing ideal of the model gives us an implicit description of the model. In this paper, we resolve two conjectures given by Sturmfels and Uhler. In particular, we characterize those

Highdimensional signconstrained feature selection and grouping Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20201012
Shanshan Qin, Hao Ding, Yuehua Wu, Feng LiuIn this paper, we propose a nonnegative feature selection/feature grouping (nnFSG) method for general signconstrained highdimensional regression problems that allows regression coefficients to be disjointly homogeneous, with sparsity as a special case. To solve the resulting nonconvex optimization problem, we provide an algorithm that incorporates the difference of convex programming, augmented

Correction to: Clustering of subsample means based on pairwise L1 regularized empirical likelihood Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20201007
Quynh Van Nong, Chi Tim NgIn the original article, the affiliations were published incorrectly.

Robust highdimensional regression for data with anomalous responses Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200930
Mingyang Ren, Sanguo Zhang, Qingzhao ZhangThe accuracy of response variables is crucially important to train regression models. In some situations, including the highdimensional case, response observations tend to be inaccurate, which would lead to biased estimators by directly fitting a conventional model. For analyzing data with anomalous responses in the highdimensional case, in this work, we adopt γdivergence to conduct variable selection

Estimation for highfrequency data under parametric market microstructure noise Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200916
Simon Clinet, Yoann PotironWe develop a general class of noiserobust estimators based on the existing estimators in the nonnoisy highfrequency data literature. The microstructure noise is a parametric function of the limit order book. The noiserobust estimators are constructed as plugin versions of their counterparts, where we replace the efficient price, which is nonobservable, by an estimator based on the raw price and

On localization of source by hidden Gaussian processes with small noise Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200909
Yury A. KutoyantsWe consider the problem of identification of the position of some source by observations of K detectors receiving signals from this source. The time of arriving of the signal to the kth detector depends of the distance between this detector and the source. The signals are observed in the presence of small Gaussian noise. The properties of the MLE and Bayesian estimators are studied in the asymptotic

Improved empirical likelihood inference and variable selection for generalized linear models with longitudinal nonignorable dropouts Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200827
Lei Wang, Wei MaIn this paper, we propose improved statistical inference and variable selection methods for generalized linear models based on empirical likelihood approach that accommodates both the withinsubject correlations and nonignorable dropouts. We first apply the generalized method of moments to estimate the parameters in the nonignorable dropout propensity based on an instrument. The inverse probability

Hypothesis tests for highdimensional covariance structures Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200801
Aki Ishii, Kazuyoshi Yata, Makoto AoshimaWe consider hypothesis testing for highdimensional covariance structures in which the covariance matrix is a (i) scaled identity matrix, (ii) diagonal matrix, or (iii) intraclass covariance matrix. Our purpose is to systematically establish a nonparametric approach for testing the highdimensional covariance structures (i)–(iii). We produce a new common test statistic for each covariance structure

Model averaging for linear models with responses missing at random Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200701
Yuting Wei, Qihua Wang, Wei LiuIn this paper, a model averaging approach is developed for the linear regression models with response missing at random. It is shown that the proposed method is asymptotically optimal in the sense of achieving the lowest possible squared error. A Monte Carlo study is conducted to investigate the finite sample performance of our proposal by comparing with some related methods, and the simulation results

Instrument search in pseudolikelihood approach for nonignorable nonresponse Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200613
Ji Chen, Jun Shao, Fang FangWith nonignorable nonresponse, an effective method to construct valid estimators of population parameters is to use a covariate vector called instrument that can be excluded from the nonresponse propensity, but are associated with the response even when other covariates are conditioned. The existing work in this approach assumes such an instrument is given, which is frequently not the case in applications

Model identification and selection for singleindex varyingcoefficient models Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200610
Peng Lai, Fangjian Wang, Tingyu Zhu, Qingzhao ZhangSingleindex varyingcoefficient models include many types of popular semiparametric models, i.e., singleindex models, partially linear models, varying coefficient models, and so on. In this paper, a twostage efficient variable selection procedure is proposed to select important nonparametric and parametric components and obtain estimators simultaneously. We also find that the proposed procedure

Semiparametric methods for lefttruncated and rightcensored survival data with covariate measurement error Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200602
LiPang Chen, Grace Y. YiMany methods have been developed for analyzing survival data which are commonly rightcensored. These methods, however, are challenged by complex features pertinent to the data collection as well as the nature of data themselves. Typically, biased samples caused by lefttruncation (or lengthbiased sampling) and measurement error often accompany survival analysis. While such data frequently arise in

Copula and composite quantile regressionbased estimating equations for longitudinal data Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200525
Kangning Wang, Wen ShanComposite quantile regression (CQR) is a powerful complement to the usual mean regression and becomes increasingly popular due to its robustness and efficiency. In longitudinal studies, it is necessary to consider the intrasubject correlation among repeated measures to improve the estimation efficiency. This paper proposes a new approach that uses copula to account for intrasubject dependence in

Poles of pair correlation functions: When they are real? Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200509
Ka Yiu Wong, Dietrich StoyanThe most common standard estimator of the pair correlation function (PCF) of a point process has a pole at zero, which is in most cases a statistical artifact. However, sometimes it makes sense to assume that a pole really exists. We propose two independent approaches for the proof of existence of a PCF’s pole and for the determination of its order. In the first, we use a summary characteristic F that

Multiresolution analysis of point processes and statistical thresholding for Haar waveletbased intensity estimation Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200508
Youssef Taleb, Edward A. K. CohenWe take a waveletbased approach to the analysis of point processes and the estimation of the firstorder intensity under a continuoustime setting. A Haar wavelet multiresolution analysis is formulated which motivates the definition of homogeneity at different scales of resolution, termed Jth level homogeneity. Further to this, the activity in a point process’ firstorder behaviour at different scales

Nonparametric estimation of the kernel function of symmetric stable moving average random functions Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200407
Jürgen Kampf, Georgiy Shevchenko, Evgeny SpodarevWe estimate the kernel function of a symmetric alpha stable (\(S\alpha S\)) moving average random function which is observed on a regular grid of points. The proposed estimator relies on the empirical normalized (smoothed) periodogram. It is shown to be weakly consistent for positive definite kernel functions, when the grid mesh size tends to zero and at the same time the observation horizon tends

On the power of some sequential multiple testing procedures Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200402
Shiyun Chen, Ery AriasCastroWe study an online multiple testing problem where the hypotheses arrive sequentially in a stream. The test statistics are independent and assumed to have the same distribution under their respective null hypotheses. We investigate two recently proposed procedures LORD and LOND, which are proved to control the FDR in an online manner. In some (static) model, we show that LORD is optimal in some asymptotic

Multivariate matrix Mittag–Leffler distributions Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200328
Hansjörg Albrecher, Martin Bladt, Mogens BladtWe extend the construction principle of multivariate phasetype distributions to establish an analytically tractable class of heavytailed multivariate random variables whose marginal distributions are of Mittag–Leffler type with arbitrary index of regular variation. The construction can essentially be seen as allowing a scalar parameter to become matrixvalued. The class of distributions is shown

Consistent multiple changepoint estimation with fused Gaussian graphical models Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200317
A. Gibberd, S. RoyWe consider the consistency properties of a regularised estimator for the simultaneous identification of both changepoints and graphical dependency structure in multivariate timeseries. Traditionally, estimation of Gaussian graphical models (GGM) is performed in an i.i.d setting. More recently, such models have been extended to allow for changes in the distribution, but primarily where changepoints

Valid p values and expectations of p values revisited Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200303
Albert VexlerWe focus on valid definitions of pvalues. A valid pvalue (VpV) statistic can be used to make a prefixed level\( \alpha \) decision. In this context, Kolmogorov–Smirnov goodnessoffit tests and the normal twosample problem are considered. We examine an issue regarding the goodnessoffit testability based on a single observation. We exemplify constructions of new test procedures, advocating practical

Estimation of an improved surrogate model in uncertainty quantification by neural networks Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200229
Benedict Götz, Sebastian Kersting, Michael KohlerQuantification of uncertainty of a technical system is often based on a surrogate model of a corresponding simulation model. In any application, the simulation model will not describe the reality perfectly, and consequently the surrogate model will be imperfect. In this article, we combine observed data from the technical system with simulated data from the imperfect simulation model in order to estimate

Quasilikelihood analysis and Bayestype estimators of an ergodic diffusion plus noise Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20200214
Shogo H. Nakakita, Yusuke Kaino, Masayuki UchidaWe consider adaptive maximumlikelihoodtype estimators and adaptive Bayestype ones for discretely observed ergodic diffusion processes with observation noise whose variance is constant. The quasilikelihood functions for the diffusion and drift parameters are introduced and the polynomialtype large deviation inequalities for those quasilikelihoods are shown to see the asymptotic properties of the

Discussion of “Bayesian forecasting of multivariate time series: scalability, structure uncertainty and decisions” Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191215
Jouchi NakajimaThe author focuses on the “decoupling and recoupling” idea that can critically increase both computational and forecasting efficiencies in practical problems for economic and financial data. My discussion is twofold. First, I briefly describe the idea with an example of timevarying vector autoregressions, which are widely used in the context. Second, I highlight the issue of how to assess patterns

The k th power expectile regression Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191212
Yingying Jiang, Fuming Lin, Yong ZhouCheck functions of least absolute deviation make sure quantile regression methods are robust, while squared check functions make expectiles more sensitive to the tails of distributions and more effective for the normal case than quantiles. In order to balance robustness and effectiveness, we adopt a loss function, which falls in between the above two loss functions, to introduce a new kind of expectiles

Clustering of subsample means based on pairwise L1 regularized empirical likelihood Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191212
Quynh Van Nong, Chi Tim NgTo classify a vast amount of strata or subsamples with unknown families of distributions according to their stratameans, a clustering approach is developed based on pairwise \(L_1\) regularized empirical likelihood. Under such a clustering approach, all possible contradictory conclusions are ruled out automatically. On the contrary, the decision rules based on many existing pairwise comparison procedures

Bayesian forecasting of multivariate time series: scalability, structure uncertainty and decisions Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191209
Mike WestI discuss recent research advances in Bayesian statespace modeling of multivariate time series. A main focus is on the “decouple/recouple” concept that enables application of statespace models to increasingly largescale data, applying to continuous or discrete time series outcomes. Applied motivations come from areas such as financial and commercial forecasting and dynamic network studies. Explicit

Fixed point characterizations of continuous univariate probability distributions and their applications Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191120
Steffen Betsch, Bruno EbnerBy extrapolating the explicit formula of the zerobias distribution occurring in the context of Stein’s method, we construct characterization identities for a large class of absolutely continuous univariate distributions. Instead of trying to derive characterizing distributional transformations that inherit certain structures for the use in further theoretic endeavors, we focus on explicit representations

Integral transform methods in goodnessoffit testing, II: the Wishart distributions Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191120
Elena Hadjicosta, Donald RichardsWe initiate the study of goodnessoffit testing for data consisting of positive definite matrices. Motivated by the appearance of positive definite matrices in numerous applications, including factor analysis, diffusion tensor imaging, volatility models for financial time series, wireless communication systems, and polarimetric radar imaging, we apply the method of Hankel transforms of matrix argument

On the proportional hazards model with last observation carried forward covariates Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191109
Hongyuan Cao, Jason P. FineStandard partial likelihood methodology for the proportional hazards model with timedependent covariates requires knowledge of the covariates at the observed failure times, which is not realistic in practice. A simple and commonly used estimator imputes the most recently observed covariate prior to each failure time, which is known to be biased. In this paper, we show that a weighted last observation

The debiased group Lasso estimation for varying coefficient models Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191109
Toshio HondaThere has been much attention on the debiased or desparsified Lasso. The Lasso is very useful in highdimensional settings. However, it is well known that the Lasso produces biased estimators. Therefore, several authors proposed the debiased Lasso to fix this drawback and carry out statistical inferences based on the debiased Lasso estimators. The debiased Lasso needs desirable estimators of highdimensional

Some explicit solutions of c optimal design problems for polynomial regression with no intercept Ann. Inst. Stat. Math. (IF 0.758) Pub Date : 20191107
Holger Dette, Viatcheslav B. Melas, Petr ShpilevIn this paper, we consider the optimal design problem for extrapolation and estimation of the slope at a given point, say z, in a polynomial regression with no intercept. We provide explicit solutions of these problems in many cases and characterize those values of z, where this is not possible.