
Bayesian confidence intervals for variance of deltalognormal distribution with an application to rainfall dispersion Stat. Interface (IF 0.412) Pub Date : 20210101
Patcharee Maneerat, Suparat Niwitpong, SaAat NiwitpongFor climate studies in agriculture, rainfall records often involve data which contain zeros and highly nonzero skewness. This is mostly used in models for prediction or that use the mean for approximation. Rainfall dispersion is also important in evaluations as it can vary enormously, and it is a natural phenomenon which can lead to drought or flood. Herein, the goal of this paper is to propose a

Robust regression model for ordinal response Stat. Interface (IF 0.412) Pub Date : 20210101
Ao Yuan, Chongyang Duan, Ming T. TanOrdinal outcome data with covariates occur frequently in statistical practice including applications from biomedicine to marketing research. Most existing methods for this type of data have relied on subjectively specified models that allow order restriction. There are also some semiparametric ordinal models which are more flexible than parametric ones, with fixed link function, they are still not

Extracting scalar measures from functional data with applications to placebo response Stat. Interface (IF 0.412) Pub Date : 20210101
Thaddeus Tarpey, Eva Petkova, Adam Ciarleglio, Robert Todd OgdenIn controlled and observational studies, outcome measures are often observed longitudinally. Such data are difficult to compare among units directly because there is no natural ordering of curves. This is relevant not only in clinical trials, where typically the goal is to evaluate the relative efficacy of treatments on average, but also in the growing and increasingly important area of personalized

A test against the stratified additive hazards model Stat. Interface (IF 0.412) Pub Date : 20210101
Yanqin Feng, Xin Yuan, Shishun ZhaoStratified data are commonly encountered in practice. An interesting problem for this type of data is to test the existence of stratum effect. This paper discusses hypothesis testing of stratum effect for intervalcensored data with informative observation times under the stratified additive hazards model. We construct a test statistic for this test problem, and show that the test statistic is asymptotically

Community detection for statistical citation network by DSCORE Stat. Interface (IF 0.412) Pub Date : 20210101
Tianchen Gao, Rui Pan, Siyu Wang, Yuehan Yang, Yan ZhangWith the wide application of statistics, it is important to identify research trends and the development of statistics. In this paper, we analyze a citation network of the top 4 statistical journals from 2001 to 2018, applying the directed spectral clustering on the ratioofeigenvectors (DSCORE) method to detect the community structure of citation network. We find that statistical researchers are

Residualbased tree for clustered binary data Stat. Interface (IF 0.412) Pub Date : 20210101
Rong Xia, Christopher R. Friese, Mousumi BanerjeeTreebased methods are widely used for classification in health sciences research, where data are often clustered. In this paper, we propose a variant of the standard classification and regression tree paradigm (CART) to handle clustered binary outcomes. Using residuals from a null generalized linear mixed model as the response, we build a regression tree to partition the covariate space into rectangles

A model checking method for the additive hazards model with multivariate current status data Stat. Interface (IF 0.412) Pub Date : 20210101
Yanqin Feng, Cheng Zhang, Jieli DingThis paper presents a class of graphical and numerical techniques to check the overall fitting adequacy of the marginal additive hazards model to multivariate current status data. The proposed testing methods are based on the supremum of the stochastic processes derived from the cumulative sum of martingalebased residuals over time and covariates. The distributions of the proposed stochastic processes

Inference in a mixture additive hazards cure model Stat. Interface (IF 0.412) Pub Date : 20210101
Dongxiao Han, Haijin He, Liuquan Sun, Xinyuan Song, Wei XuWe propose a mixture additive hazards (AH) cure model for survival data with a cure fraction. The proposed model integrates a logistic regression model for the proportion of patients cured of disease and an AH model for the uncured patients. Generalized estimating equations are developed for parameter estimation, and the asymptotic properties of the resulting estimators are established. In addition

Generalized Newton–Raphson algorithm for high dimensional LASSO regression Stat. Interface (IF 0.412) Pub Date : 20210101
Yueyong Shi, Jian Huang, Yuling Jiao, Yicheng Kang, Hu ZhangThe least absolute shrinkage and selection operator (LASSO) penalized regression is a stateoftheart statistical method in high dimensional data analysis, when the number of predictors exceeds the number of observations. The commonly used Newton–Raphson algorithm is not very successful in solving the nonsmooth optimization in LASSO. In this paper, we propose a fast generalized Newton–Raphson (GNR)

Highdimensional correlation matrix estimation for Gaussian data: a Bayesian perspective Stat. Interface (IF 0.412) Pub Date : 20210101
Chaojie Wang, Xiaodan FanGaussian covariance or precision matrix estimation is a classical problem in highdimensional data analyses. For precision matrix estimation, the graphical lasso provides an efficient approach by optimizing the loglikelihood function with $L_1$norm penalty. Inspired by the success of graphical lasso, researchers pursue analogous outcomes for covariance matrix estimation. However, it suffers from

Penalized empirical likelihood for highdimensional generalized linear models Stat. Interface (IF 0.412) Pub Date : 20210101
Xia Chen, Liyue MaoWe develop penalized empirical likelihood for parameter estimation and variable selection in highdimensional generalized linear models. By using adaptive lasso penalty function, we show that the proposed estimator has the oracle property. Also, we consider the problem of testing hypothesis, and show that the nonparametric profiled empirical likelihood ratio statistic has asymptotic chisquare distribution

Spatial regression models for bounded response variables with evaluation of the degree of dependence Stat. Interface (IF 0.412) Pub Date : 20210101
Sandra E. Flores, Marcos O. Prates, Jorge L. Bazán, Heleno B. BolfarineBounded response variables such as percentages, proportions, or rates are common in applications involving social and educational datasets, including rates of poverty or rates of achievement by municipalities, counties or provinces. New regression models have been proposed in recent years by considering distributions such as the Beta, Simplex and Kumaraswamy models for this type of data. However, to

Relating parameters in conditional, marginalized, and marginal logistic models when the mediator is binary Stat. Interface (IF 0.412) Pub Date : 20210101
Kai WangStanghellini and Doretti (2019) studied the exact formulae relating parameters in conditional and marginalized logistic models when the mediator is binary. Those formulae generally do not hold for the reduced model as the reduced model is generally not the same as the marginalized model. For a conditional model that allows for treatmentmediator interaction, I present 1) alternative exact formulae relating

Information diffusion with network structures Stat. Interface (IF 0.412) Pub Date : 20210101
Zhu Xuening, Rui Pan, Yuxuan Zhang, Yu Chen, Wenquan Mi, Hansheng WangInformation diffusion refers to the process about passing certain information from one subject to another. It is a typical and critical phenomenon observed in large scale social networks. To statistically model such a phenomenon, a network diffusion model is proposed and studied. The diffusion process is then investigated under the modeling framework from both the short term and long term perspectives

Lead time distribution for individuals with a screening history Stat. Interface (IF 0.412) Pub Date : 20210101
Ruiqi Liu, Dongfeng Wu, Shesh N. RaiWe derived the distribution of lead time for periodic screening in the future when an individual has a screening history with negative results. It is a mixture of a point mass at zero and a positive subPDF. The motivation comes from the reality that for people in older age, they may already have some screening exams for targeted cancer before and still look healthy and are asymptomatic at their current

Bayesian zeroinflated growth mixture models with application to health risk behavior data Stat. Interface (IF 0.412) Pub Date : 20210101
Si Yang, Gavino PuggioniThis paper focuses on developing latent class models for longitudinal data with zeroinflated count response variables. The goals are to model discrete longitudinal patterns of rare events counts (for instance, healthrisky behavior), and to identify individualspecific covariates associated with latent class probabilities. Two discrete latent structures are present in this type of model: a latent

Estimation and diagnostics for partially linear censored regression models based on heavytailed distributions Stat. Interface (IF 0.412) Pub Date : 20210101
Marcela Nuñez Lemus, Victor H. Lachos, Christian E. Galarza, Larissa A. MatosIn many studies, limited or censored data are collected. This occurs, in several practical situations, for reasons such as limitations of measuring instruments or due to experimental design. So, the responses can be either left, interval or right censored. On the other hand, partially linear models are considered as a flexible generalizations of linear regression models by including a nonparametric

Estimating equation estimators of quantile differences for one sample with lengthbiased and rightcensored data Stat. Interface (IF 0.412) Pub Date : 20210101
Dehui Wang, Li Xun, Guangchao Zhang, Yong ZhouThis paper estimates quantile differences for one sample with lengthbiased and rightcensored (LBRC) data. To ensure the asymptotic unbiasedness of the estimator, the estimating equation method is adopted. To improve the efficiency of the estimator, in the sense of having a lower mean squared error, the kernelsmoothed approach is employed. To make full use of the features of LBRC data, the augmented

A nonmarginal variable screening method for the varying coefficient Cox model Stat. Interface (IF 0.412) Pub Date : 20210101
Lianqiang Qu, Liuquan SunThe varying coefficient model has become a very popular statistical tool for describing the dynamic effects of covariates on the response. In this article, we develop a new variable screening method for the varying coefficient Cox model based on the kernel smoothing and group learning methods. The sure screening property is established for ultrahighdimensional settings. In addition, an iterative

Grouped variable selection with prior information via the prior group bridge method Stat. Interface (IF 0.412) Pub Date : 20210101
Kai Li, Meng Mei, Yuan JiangIn a multiple regression with grouped predictors, it is usually desired to select important groups as well as to select important variables within a group simultaneously. To achieve this socalled “bilevel selection,” group bridge has been developed as a combination of grouplevel bridge and variablelevel lasso penalties. However, in many scientific areas, prior knowledge is available about the importance

The timing and effectiveness of implementing mild interventions of COVID19 in large industrial regions via a synthetic control method Stat. Interface (IF 0.412) Pub Date : 20210101
Ting Tian, Wenxiang Luo, Jianbin Tan, Yukang Jiang, Minqiong Chen, Wenliang Pan, Songpan Yang, Jiashu Zhao, Xueqin Wang, Heping ZhangThe outbreak of novel coronavirus disease (COVID19) has spread around the world since it was detected in December 2019. The Chinese government executed a series of interventions to curb the pandemic. The “battle” against COVID19 in Shenzhen, China is valuable because populated industrial cities are the epic centres of COVID19 in many regions. We made use of synthetic control methods to create a

Discussion on “The timing and effectiveness of implementing mild interventions of COVID19 in large industrial regions via a synthetic control method” by Tian et al. Stat. Interface (IF 0.412) Pub Date : 20210101
Kun Chen, Fei WangThe ongoing pandemic of the novel coronavirus disease 2019 (COVID19) has impacted tens of millions of people and caused a huge economic loss. Most of the impacted countries have implemented different nonpharmaceutical interventions (NPIs) to control and prevent the spreading of SARSCov2, which is the virus causing COVID19. With the coming flu season in the northern hemisphere, many countries are

Discussion on “The timing and effectiveness of implementing mild interventions of COVID19 in large industrial regions via a synthetic control method” by Tian et al. Stat. Interface (IF 0.412) Pub Date : 20210101
Yifan ZhuThis article provides an overview and discussion of the recent published paper from Tian et al. on modeling the differences of COVID19 outbreak between Shenzhen and a synthetic population constructed from 68 US counties.

Discussion on “The timing and effectiveness of implementing mild interventions of COVID19 in large industrial regions via a synthetic control method” by Tian et al. Stat. Interface (IF 0.412) Pub Date : 20210101
Soumik Purkayastha, Peter SongIt is a pleasure to have the opportunity to comment on this contribution by [6]. The authors use a matching technique called the synthetic control method (SCM) [1] to compare the spread of the COVID19 pandemic in Shenzhen, China with a synthetic reference population in the USA that matches certain characteristics of Shenzhen, as chosen by the authors. The primary goal of this analysis is to examine

Discussion on “The timing and effectiveness of implementing mild interventions of COVID19 in large industrial regions via a synthetic control method” by Tian et al. Stat. Interface (IF 0.412) Pub Date : 20210101
Debashree Ray, Rupam Bhattacharyya, Bhramar MukherjeeTian et al. ought to be commended for their approach of using synthetic control methodology (SCM) to evaluate effectiveness of mild intervention strategies (e.g. wearing masks, isolation of overseas travelers, etc.) in controlling the spread of COVID19 in industrial regions. The authors use Shenzhen in the Guangdong province of China as an example and compare it with several control counties in the

The need to incorporate communities in compartmental models Stat. Interface (IF 0.412) Pub Date : 20210101
Michael J. Kane, Owais GilaniTian et al. provide a framework for assessing populationlevel interventions of disease outbreaks through the construction of counterfactuals in a largescale, natural experiment assessing the efficacy of mild, but early interventions compared to delayed interventions. The technique is applied to the recent SARSCoV2 outbreak with the population of Shenzhen, China acting as the mildbutearly treatment

A novel intervention recurrent autoencoder for real time forecasting and nonpharmaceutical intervention selection to curb the spread of Covid19 in the world Stat. Interface (IF 0.412) Pub Date : 20210101
Qiyang Ge, Zixin Hu, Shudi Li, Wei Lin, Li Jin, Momiao XiongAs the Covid19 pandemic soars around the world, there is urgent need to forecast the number of cases worldwide at its peak, the length of the pandemic before receding and implement public health interventions to significantly stop the spread of Covid19. Widely used statistical and computer methods for modeling and forecasting the trajectory of Covid19 are epidemiological models. Although these epidemiological

A robust nonlinear mixedeffects model for COVID19 death data Stat. Interface (IF 0.412) Pub Date : 20210101
Fernanda L. Schumacher, Clécio S. Ferreira, Marcos O. Prates, Alberto Lachos, Victor H. LachosThe analysis of complex longitudinal data such as COVID19 deaths is challenging due to several inherent features: (i) similarlyshaped profiles with different decay patterns; (ii) unexplained variation among repeated measurements within each country, possibly interpreted as clustered data since they are obtained from the same country at roughly the same time; and (iii) skewness, outliers or skewed

Forecasting confirmed cases of the COVID19 pandemic with a migrationbased epidemiological model Stat. Interface (IF 0.412) Pub Date : 20210101
Xinyu Wang, Lu Yang, Hong Zhang, Zhouwang Yang, Catherine LiuThe unprecedented coronavirus disease 2019 (COVID19) pandemic is still a worldwide threat to human life since its invasion into the daily lives of the public in the first several months of 2020. Predicting the size of confirmed cases is important for countries and communities to make proper prevention and control policies so as to effectively curb the spread of COVID19. Different from the 2003 SARS

Heterogeneity learning for SIRS model: an application to the COVID19 Stat. Interface (IF 0.412) Pub Date : 20210101
Guanyu Hu, Junxian GengWe propose a Bayesian Heterogeneity Learning approach for SusceptibleInfectedRemovalSusceptible (SIRS) model that allows underlying clustering patterns for transmission rate, recovery rate, and loss of immunity rate for the latest corona virus (COVID19) among different regions. Our proposed method provides simultaneously inference on parameter estimation and clustering information which contains

On evidence cycles in network metaanalysis. Stat. Interface (IF 0.412) Pub Date : 20200731
Lifeng Lin,Haitao Chu,James S HodgesAs an extension of pairwise metaanalysis of two treatments, network metaanalysis has recently attracted many researchers in evidencebased medicine because it simultaneously synthesizes both direct and indirect evidence from multiple treatments and thus facilitates better decision making. The Bayesian hierarchical model is a popular method to implement network metaanalysis, and it is generally considered

Bayesian metaregression model using heavytailed randomeffects with missing sample sizes for selfthinning metadata Stat. Interface (IF 0.412) Pub Date : 20200731
Zhihua Ma, MingHui Chen, Yi TangMotivated by the selfthinning metadata, a randomeffects metaanalysis model with unknown precision parameters is proposed with a truncated Poisson regression model for missing sample sizes. The random effects are assumed to follow a heavytailed distribution to accommodate outlying aggregate values in the response variable. The logarithm of the pseudomarginal likelihood (LPML) is used for model

Statistical methods for quantifying betweenstudy heterogeneity in metaanalysis with focus on rare binary events Stat. Interface (IF 0.412) Pub Date : 20200731
Chiyu Zhang, Min Chen, Xinlei WangMetaanalysis, the statistical procedure for combining results from multiple independent studies, has been widely used in medical research to evaluate intervention efficacy and drug safety. In many practical situations, treatment effects vary notably among the collected studies, and the variation, often modeled by the betweenstudy variance parameter $\tau^2$, can greatly affect the inference of the

Metaanalysis of peptides to detect protein significance Stat. Interface (IF 0.412) Pub Date : 20200731
Yuping Zhang, Zhengqing Ouyang, WeiJun Qian, Richard D. Smith, Wing Hung Wong, Ronald W. DavisShotgun assays are widely used in biotechnologies to characterize large molecules, which are hard to be measured as a whole directly. For instance, in Liquid Chromatography–Mass Spectrometry (LC–MS) shotgun experiments, proteins in biological samples are digested into peptides, and then peptides are separated and measured. However, in proteomics study, investigators are usually interested in the performance

Smallstudy effects: current practice and challenges for future research Stat. Interface (IF 0.412) Pub Date : 20200731
Arielle MarksAnglin, Yong ChenMetaanalyses and systematic reviews are highly valued as evidence for clinical decision and policymaking. However, inference in these settings may be invalid if the studies do not come from the same underlying distribution. Small study effects is one form of heterogeneity that can lead to biased estimates, particularly if it arises due to the selective publishing of studies, a phenomenon known as

Bayesian flexible hierarchical skew heavytailed multivariate meta regression models for individual patient data with applications. Stat. Interface (IF 0.412) Pub Date : 20200731
Sungduk Kim,MingHui Chen,Joseph Ibrahim,Arvind Shah,Jianxin LinA flexible class of multivariate metaregression models are proposed for Individual Patient Data (IPD). The methodology is well motivated from 26 pivotal Merck clinical trials that compare statins (cholesterol lowering drugs) in combination with ezetimibe and statins alone on treatmentnaïve patients and those continuing on statins at baseline. The research goal is to jointly analyze the multivariate

Model selection between the fixedeffects model and the randomeffects model in metaanalysis Stat. Interface (IF 0.412) Pub Date : 20200731
Ke Yang, HiuYee Kwan, Zhiling Yu, Tiejun TongThe commoneffect model and the randomeffects model are the two most popular models for metaanalysis in the literature. To choose a proper model between them, the $Q$ statistic and the $I^2$ statistic are commonly used as the criteria. Recently, it is recognized that the fixedeffects model is also essential for metaanalysis, especially when the number of studies is small. With this new model, the

Sample size estimation for future studies using Bayesian multivariate network metaanalysis Stat. Interface (IF 0.412) Pub Date : 20200731
Stacia M. Desantis, Hyunsoo HwangAlthough systematic reviews of randomized clinical trials (RCTs) are considered the pinnacle of evidencebased medicine, RCTs are often designed to reach a desired level of power for a prespecified effect size, independent of the current body of evidence. Evidence indicates that sample size calculations for a new RCT should be conducted in the context of a systematic review and metaanalysis of the

Estimating the mean and variance from the fivenumber summary of a lognormal distribution Stat. Interface (IF 0.412) Pub Date : 20200731
Jiandong Shi, Tiejun Tong, Yuedong Wang, Marc G. GentonIn the past several decades, metaanalysis has been widely used to pool multiple studies for evidencebased practice. To conduct a metaanalysis, the mean and variance from each study are often required; whereas in certain studies, the fivenumber summary may instead be reported that consists of the median, the first and third quartiles, and/or the minimum and maximum values. To transform the fivenumber

A CDbased mapping method for combining multiple related parameters from heterogeneous intervention trials. Stat. Interface (IF 0.412) Pub Date : 20200731
Yang Jiao,EunYoung Mun,Thomas A Trikalinos,Minge XieEffect size can differ as a function of the elapsed time since treatment or as a function of other key covariates, such as sex or age. In evidence synthesis, a better understanding of the precise conditions under which treatment does work or does not work well has been highly valued. With increasingly accessible individual patient or participant data (IPD), more precise and informative inference can

Fully Bayesian $L_{1/2}$penalized linear quantile regression analysis with autoregressive errors Stat. Interface (IF 0.412) Pub Date : 20200422
Yuzhu Tian, Xinyuan SongIn the quantile regression framework, we incorporate Bayesian $L_{1/2}$ and adaptive $L_{1/2}$ penalties into quantile linear regression models with autoregressive (AR) errors to conduct statistical inference. A Bayesian joint hierarchical model is established using the working likelihood of the asymmetric Laplace distribution (ALD). On the basis of the mixture representations of ALD and the generalized

Evaluation of bias for outcome adaptive randomization designs with binary endpoints Stat. Interface (IF 0.412) Pub Date : 20200422
Yaping Wang, Hongjian Zhu, J. Jack LeeClinical trial designs applying outcome adaptive randomization (OAR) sequentially change randomization probabilities basing on observed outcomes. Compared to the conventional equal randomization procedure, OAR has the feature to assign more patients to the better treatment arm and yield higher overall response rates for patients in the trial. However, the true response rates tend to be underestimated

Computerized adaptive test using raw responses for item selection: Theoretical results and applications for the upanddown method Stat. Interface (IF 0.412) Pub Date : 20200422
ChengDer Fuh, Edward Haksing Ip, ShyhHuei ChenModern computerized adaptive testing (CAT) is finding applications that contain more intensive assessments, collected over nontraditional devices such as tablets and smartphones. In this paper, we introduce an CAT algorithm that uses raw responses to adaptively select items and does not require updating the ability estimate at every administration of an item. The proposed algorithm is especially useful

A log Birnbaum–Saunders regression model based on the skewnormal distribution under the centred parameterization Stat. Interface (IF 0.412) Pub Date : 20200422
Nathalia L. Chaves, Caio L. N. Azevedo, Filidor VilcaLabra, Juvêncio S. NobreIn this paper we introduce a new regression model for positive and skewed data, a log Birnbaum–Saunders model based on the centred skewnormal distribution, also presenting several inference tools for this model. Initially, we developed a new version of the skewsinhnormal distribution, describing some of its properties. For the proposed regression model, we carry out, through the expectation conditional

Multidimensional classification with semiparametric mixture model Stat. Interface (IF 0.412) Pub Date : 20200422
Anqi Yin, Ao YuanCompared to nonmodel based classification methods, the model based classification has the advantage of classification together with regression analysis, and is the interest of our investigation. For robustness, we propose and study a semiparametric mixture model, in which each subdensity is only assumed unimodal. The semiparametric maximum likelihood estimate is used to estimate the parametric and

A sequential naïve Bayes method for music genre classification based on transitional information from pitch and beat Stat. Interface (IF 0.412) Pub Date : 20200422
Tunan Ren, Feifei Wang, Hansheng WangDue to the rapid development of digital music market, online music websites are widely available in our daily life. There is a practical need to develop automatic music genre classification algorithms to manage a huge amount of music. In this regard, the transitional information contained in pitches and beats should be very useful. Particularly, the transition in pitches produces a melody, and the

Semiparametric accelerated failure time modeling for multivariate failure times under multivariate outcomedependent sampling designs Stat. Interface (IF 0.412) Pub Date : 20200422
TsuiShan Lu, Sangwook Kang, Haibo ZhouResearchers working on large cohort studies are always seeking for costeffective designs due to a limited budget. An outcomedependent sampling (ODS) design, a retrospective sampling scheme where one observes covariates with a probability depending on the outcome and selects supplemental samples from more informative segments, improves the study efficiency while effectively controlling for the budget

Asymptotic theory for differentially private generalized βmodels with parameters increasing Stat. Interface (IF 0.412) Pub Date : 20200422
Yifan Fan, Huiming Zhang, Ting YanModelling edge weights play a crucial role in the analysis of network data, which reveals the extent of relationships among individuals. Due to the diversity of weight information, sharing these data has become a complicated challenge in a privacypreserving way. In this paper, we consider the case of the nondenoising process to achieve the tradeoff between privacy and weight information in the generalized

Estimation of a distribution function using Lagrange polynomials with Tchebychev–Gauss points Stat. Interface (IF 0.412) Pub Date : 20200422
Salima Helali, Yousri SlaouiThe estimation of the distribution function of a real random variable is an intrinsic topic in non parametric estimation. To this end, a distribution estimator based on Lagrange polynomials and Tchebychev–Gauss points, is introduced. Some asymptotic properties of the proposed estimator are investigated, such as its asymptotic bias, variance, mean squared error and Chung–Smirnov propriety. The asymptotic

A semiparametric joint latent class model with longitudinal and survival data Stat. Interface (IF 0.412) Pub Date : 20200422
Yue Liu, Ye Lin, Jianhui Zhou, Lei LiuIn many longitudinal studies, we are interested in both repeated measures of a biomarker and time to an event. When there exist heterogeneous patterns of the longitudinal and survival profiles, we propose a latent class joint model to identify subgroups of subjects and study the association between longitudinal and survival outcomes. The model is estimated by maximizing the full likelihood function

Bayesian HighDimensional Regression for Change Point Analysis. Stat. Interface (IF 0.412) Pub Date : 20190924
Abhirup Datta,Hui Zou,Sudipto BanerjeeIn many econometrics applications, the dataset under investigation spans heterogeneous regimes that are more appropriately modeled using piecewise components for each of the data segments separated by changepoints. We consider using Bayesian highdimensional shrinkage priors in a change point setting to understand segmentspecific relationship between the response and the covariates. Covariate selection

Letter to the Editor. Stat. Interface (IF 0.412) Pub Date : 20190820
Marco GeraciGalarza, Lachos and Bandyopadhyay (2017) have recently proposed a method of estimating linear quantile mixed models (Geraci and Bottai, 2014) based on a Monte Carlo EM algorithm. They assert that their procedure represents an improvement over the numerical quadrature and nonsmooth optimization approach implemented by Geraci (2014). The objective of this note is to demonstrate that this claim is incorrect

Dynamic Structural Equation Models for Directed Cyclic Graphs: the Structural Identifiability Problem. Stat. Interface (IF 0.412) Pub Date : 20190725
Yulin Wang,Yu Luo,Hulin Wu,Hongyu MiaoNetwork systems are commonly encountered and investigated in various disciplines, and network dynamics that refer to collective node state changes over time are one area of particular interests of many researchers. Recently, dynamic structural equation model (DSEM) has been introduced into the field of network dynamics as a powerful statistical inference tool. In this study, in recognition that parameter

More accurate semiparametric regression in pharmacogenomics. Stat. Interface (IF 0.412) Pub Date : 20190301
Yaohua Rong,Sihai Dave Zhao,Ji Zhu,Wei Yuan,Weihu Cheng,Yi LiA key step in pharmacogenomic studies is the development of accurate prediction models for drug response based on individuals' genomic information. Recent interest has centered on semiparametric models based on kernel machine regression, which can flexibly model the complex relationships between gene expression and drug response. However, performance suffers if irrelevant covariates are unknowingly

Bayesian modeling and uncertainty quantification for descriptive social networks. Stat. Interface (IF 0.412) Pub Date : 20190122
Thomas Nemmers,Anjana Narayan,Sudipto BanerjeeThis article presents a simple and easily implementable Bayesian approach to model and quantify uncertainty in small descriptive social networks. While statistical methods for analyzing networks have seen burgeoning activity over the last decade or so, ranging from social sciences to genetics, such methods usually involve sophisticated stochastic models whose estimation requires substantial structure

Clinical Trial Design Using A Stopped Negative Binomial Distribution. Stat. Interface (IF 0.412) Pub Date : 20190119
Michelle DeVeaux,Michael J Kane,Daniel ZeltermanWe introduce a discrete distribution suggested by curtailed sampling rules common in earlystage clinical trials. We derive the distribution of the smallest number of independent and identically distributed Bernoulli trials needed to observe either s successes or t failures. This report provides a closedform expression for the mass function, moment generating function, and provides connections to

Additive Nonlinear Functional Concurrent Model. Stat. Interface (IF 0.412) Pub Date : 20181205
Janet S Kim,Arnab Maity,AnaMaria StaicuWe propose a flexible regression model to study the association between a functional response and multiple functional covariates that are observed on the same domain. Specifically, we relate the mean of the current response to current values of the covariates by a sum of smooth unknown bivariate functions, where each of the functions depends on the current value of the covariate and the time point

Doubly regularized estimation and selection in linear mixedeffects models for highdimensional longitudinal data. Stat. Interface (IF 0.412) Pub Date : 20181205
Yun Li,Sijian Wang,Peter XK Song,Naisyin Wang,Ling Zhou,Ji ZhuThe linear mixedeffects model (LMM) is widely used in the analysis of clustered or longitudinal data. This paper aims to address analytic challenges arising from estimation and selection in the application of the LMM to highdimensional longitudinal data. We develop a doubly regularized approach in the LMM to simultaneously select fixed and random effects. On the theoretical front, we establish large

Double Sparsity Kernel Learning with Automatic Variable Selection and Data Extraction. Stat. Interface (IF 0.412) Pub Date : 20181009
Jingxiang Chen,Chong Zhang,Michael R Kosorok,Yufeng LiuLearning in the Reproducing Kernel Hilbert Space (RKHS) has been widely used in many scientific disciplines. Because a RKHS can be very flexible, it is common to impose a regularization term in the optimization to prevent overfitting. Standard RKHS learning employs the squared norm penalty of the learning function. Despite its success, many challenges remain. In particular, one cannot directly use

Timevarying copula models for longitudinal data. Stat. Interface (IF 0.412) Pub Date : 20180425
Esra Kürüm,John Hughes,Runze Li,Saul ShiffmanWe propose a copulabased joint modeling framework for mixed longitudinal responses. Our approach permits all model parameters to vary with time, and thus will enable researchers to reveal dynamic responsepredictor relationships and responseresponse associations. We call the new class of models TIMECOP because we model dependence using a timevarying copula. We develop a onestep estimation procedure
Contents have been reproduced by permission of the publishers.