Journal of Statistical Planning and Inference最新文献

Integrative analysis plays a critical role in integrating heterogeneous data from multiple datasets to provide a comprehensive view of the overall data features. However, in multiple datasets, outliers and heavy-tailed data can render least squares estimation unreliable. In response, we propose a Robust Integrative Analysis via Quantile Regression (RIAQ) that accounts for homogeneity and sparsity in multiple datasets. The RIAQ approach is not only able to identify latent homogeneous coefficient structures but also recover the sparsity of high-dimensional covariates via double penalty terms. The integration of sample information across multiple datasets improves estimation efficiency, while a sparse model improves model interpretability. Furthermore, quantile regression allows the detection of subgroup structures under different quantile levels, providing a comprehensive picture of the relationship between response and high-dimensional covariates. We develop an efficient alternating direction method of multipliers (ADMM) algorithm to solve the optimization problem and study its convergence. We also derive the parameter selection consistency of the modified Bayesian information criterion. Numerical studies demonstrate that our proposed estimator has satisfactory finite-sample performance, especially in heavy-tailed cases.

In studies on lifetimes, occasionally, the population contains statistical units that are born before the data collection has started. Left-truncated are units that deceased before this start. For all other units, the age at the study start often is recorded and we aim at testing whether this second measurement is independent of the genuine measure of interest, the lifetime. Our basic model of dependence is the one-parameter Gumbel–Barnett copula. For simplicity, the marginal distribution of the lifetime is assumed to be Exponential and for the age-at-study-start, namely the distribution of birth dates, we assume a Uniform. Also for simplicity, and to fit our application, we assume that units that die later than our study period, are also truncated. As a result from point process theory, we can approximate the truncated sample by a Poisson process and thereby derive its likelihood. Identification, consistency and asymptotic distribution of the maximum-likelihood estimator are derived. Testing for positive truncation dependence must include the hypothetical independence which coincides with the boundary of the copula’s parameter space. By non-standard theory, the maximum likelihood estimator of the exponential and the copula parameter is distributed as a mixture of a two- and a one-dimensional normal distribution. For the proof, the third parameter, the unobservable sample size, is profiled out. An interesting result is, that it differs to view the data as truncated sample, or, as simple sample from the truncated population, but not by much. The application are 55 thousand double-truncated lifetimes of German businesses that closed down over the period 2014 to 2016. The likelihood has its maximum for the copula parameter at the parameter space boundary so that the $p$-value of test is 0.5. The life expectancy does not increase relative to the year of foundation. Using a Farlie–Gumbel–Morgenstern copula, which models positive and negative dependence, finds that life expectancy of German enterprises even decreases significantly over time. A simulation under the condition of the application suggests that the tests retain the nominal level and have good power.

Row–column designs that provide unconfounded estimation of all main effects and the maximum number of two-factor interactions (2fi’s) are called 2fi-optimal. This issue has been paid great attention recently for its wide application in industrial or physical experiments. The constructions of 2fi-optimal two-level and three-level full factorial and fractional factorial row–column designs have been proposed. However, the results for higher prime levels have not been achieved yet. In this paper, we give theoretical constructions of 2fi-optimal $s^n$ full factorial row–column designs for any odd prime level $s$ and any parameter combination, and theoretical constructions of 2fi-optimal $s^{n-1}$ fractional factorial row–column designs for any prime level $s$ and any parameter combination.

The beta regression model is tailored for responses that assume values in the standard unit interval. It comprises two submodels, one for the mean response and another for the precision parameter. We develop tests of correct specification for such a model. The tests are based on the information matrix equality, which holds when the model is correctly specified. We establish the validity of the tests in the class of varying precision beta regressions, provide closed-form expressions for the quantities used in the test statistics, and present simulation evidence on the tests’ null and non-null behavior. We show that it is possible to achieve very good control of the type I error probability when data resampling is employed and that the tests are able to reliably detect incorrect model specification, especially when the sample size is not small. An empirical application is presented and discussed.

A self-normalized approach for testing the stationarity of a $d$-dimensional random field is considered in this paper. Because the discrete Fourier transforms (DFT) at fundamental frequencies of a second-order stationary random field are asymptotically uncorrelated (see Bandyopadhyay and Subba Rao, 2017), one can construct a stationarity test based on the sample covariance of the DFTs. Such a test is usually inferior because it involves an overestimated scale parameter that leads to low size and power. To circumvent this shortcoming, this paper proposes two self-normalized statistics based on extreme value and partial sum of the sample covariance of the DFTs. Under certain regularity conditions, it is shown that the proposed tests converge to functionals of Brownian motion. Simulations and a data analysis demonstrate the outstanding performance of the proposed tests.

Conditional tail expectation (CTE) is a coherent risk measure defined as the mean of the loss distribution above a high quantile. The existence of the CTE as well as the asymptotic properties of associated estimators however require integrability conditions that may be violated when dealing with heavy-tailed distributions. We introduce Box–Cox transforms of the CTE that have two benefits. First, they alleviate these theoretical issues. Second, they enable to recover a number of risk measures such as conditional tail expectation, expected shortfall, conditional value-at-risk or conditional tail variance. The construction of dedicated estimators is based on the investigation of the asymptotic relationship between Box–Cox transforms of the CTE and quantiles at extreme probability levels, as well as on an extrapolation formula established in the heavy-tailed context. We quantify and estimate the bias induced by the use of these approximations and then introduce reduced-bias estimators whose asymptotic properties are rigorously shown. Their finite-sample properties are assessed on a simulation study and illustrated on real data, highlighting the practical interest of both the bias reduction and the Box–Cox transform.

Parent-of-origin effect plays an important role in mammal development and disorder. Case-control mother–child pair genotype data can be used to detect parent-of-origin effect and is often convenient to collect in practice. Most existing methods for assessing parent-of-origin effect do not incorporate any covariates, which may be required to control for confounding factors. We propose to model the parent-of-origin effect through a logistic regression model, with predictors including maternal and child genotypes, parental origins, and covariates. The parental origins may not be fully inferred from genotypes of a target genetic marker, so we propose to use genotypes of markers tightly linked to the target marker to increase inference efficiency. A robust statistical inference procedure is developed based on a modified profile log-likelihood in a retrospective way. A computationally feasible expectation–maximization algorithm is devised to estimate all unknown parameters involved in the modified profile log-likelihood. This algorithm differs from the conventional expectation–maximization algorithm in the sense that it is based on a modified instead of the original profile log-likelihood function. The convergence of the algorithm is established under some mild regularity conditions. This expectation–maximization algorithm also allows convenient handling of missing child genotypes. Large sample properties, including weak consistency, asymptotic normality, and asymptotic efficiency, are established for the proposed estimator under some mild regularity conditions. Finite sample properties are evaluated through extensive simulation studies and the application to a real dataset.

The current paper aims to complement the recent development of the observation-driven models of dynamic counts with a parametric-driven one for a general case, particularly discrete two parameters exponential family distributions. The current paper proposes a finite semiparametric exponential mixture of SETAR processes of the conditional mean of counts to capture the nonlinearity and complexity. Because of the intrinsic latency of the conditional mean, the general additive state-space representation of dynamic counts is firstly proposed then stationarity and geometric ergodicity are established under a mild set of conditions. We also propose to estimate the unknown parameters by using quasi maximum likelihood estimation and establishes the asymptotic properties of the quasi maximum likelihood estimators (QMLEs), particularly $\sqrt{T}$-consistency and normality under the relatively mild set of conditions. Furthermore, the finite sample properties of the QMLEs are investigated via simulation exercises and an illustration of the proposed process is presented by applying the proposed method to the intraday transaction counts per minute of AstraZeneca stock.

We present a proof of consistency of the maximum likelihood estimator (MLE) of population tree in a previously proposed coalescent model. As the model involves tree-topology as a parameter, the standard proof of consistency for continuous parameters does not directly apply. In addition to proving that a consistent sequence of MLE exists, we also prove that the overall MLE, computed by maximizing the likelihood over all tree-topologies, is also consistent. Thus, the MLE of tree-topology is consistent as well. The last result is important because local maxima occur in the likelihood of population trees, especially while maximizing the likelihood separately for each tree-topology. Even though MLE is known to be a dependable estimator under this model, our work proves its effectiveness with mathematical certainty.

The Wasserstein distance is a fundamental tool for comparing probability distributions and has found broad applications in various fields, including image generation using generative adversarial networks. Despite its useful properties, the performance of the Wasserstein distance decreases when data is high-dimensional, known as the curse of dimensionality. To mitigate this issue, an extension of the Wasserstein distance has been developed, such as the sliced Wasserstein distance using one-dimensional projection. However, such an extension loses information on the original data, due to the linear projection onto the one-dimensional space. In this paper, we propose novel distances named augmented projection Wasserstein distances (APWDs) to address these issues, which utilize multi-dimensional projection with a nonlinear surface by a neural network. The APWDs employ a two-step procedure; it first maps data onto a nonlinear surface by a neural network, then linearly projects the mapped data into a multidimensional space. We also give an algorithm to select a subspace for the multi-dimensional projection. The APWDs are computationally effective while preserving nonlinear information of data. We theoretically confirm that the APWDs mitigate the curse of dimensionality from data. Our experiments demonstrate the APWDs’ outstanding performance and robustness to noise, particularly in the context of nonlinear high-dimensional data.