研究园简易版 · 经典书籍 · 期刊文章 · 有原文 · 完整版(可多选筛选、搜索) · 首页
2021 年的期刊文章 · 第 22 页
共 1542 篇,按发表时间排,新的在前,每页 40 篇。这一页是 2021-04-12 到 2021-04-01。
按期刊、按主题看 →
JASA Meta-Analysis & Data Integration Optimization & Learning Theory · 发表于 2021-04-12
Xi Chen, Weidong Liu, Yichen Zhang
摘要
This article studies distributed estimation and inference for a general statistical problem with a convex loss that could be nondifferentiable. For the purpose of efficient computation, we restrict ourselves to stochastic first-order optimization, which enjoys low per-iteration complexity. To motivate the proposed method, we first investigate the theoretical properties of a straightforward divide-and-conquer stochastic gradient descent approach. Our theory shows that there is a restriction on the number of machines and this restriction becomes more stringent when the dimension p is large. To overcome this limitation, this article proposes a new multi-round distributed estimation procedure that approximates the Newton step only using stochastic subgradient. The key component in our method is the proposal of a computationally efficient estimator of Σ−1w, where Σ is the population Hessian matrix and w is any given vector. Instead of estimating Σ (or Σ−1) that usually requires the second-order differentiability of the loss, the proposed first-order Newton-type estimator (FONE) directly estimates the vector of interest Σ−1w as a whole and is applicable to nondifferentiable losses. Our estimator also facilitates the inference for the empirical risk minimizer. It turns out that the key term in the limiting covariance has the form of Σ−1w, which can be estimated by FONE. *(abstract via OpenAlex)*
SiM Clinical Trials Bayesian Methods · 发表于 2021-04-12
Masahiro Kojima
摘要
Phase I cancer clinical trials have been proposed novel designs such as algorithm‐based, model‐based, and model‐assisted designs. Model‐based and model‐assisted designs have a higher identification rate of maximum tolerated dose (MTD) than algorithm‐based designs, but are limited by the fact that the sample size is fixed. Hence, it would be very attractive to estimate the MTD with sufficient accuracy and complete the trial early. O'Quigley proposed the early completion of a trial with the continual reassessment method among model‐based designs when the MTD is estimated with sufficient accuracy. However, the proposed early completion method based on the binary outcome trees has a problem that the calculation cost is high when the number of remaining patients is large. Among model‐assisted designs, the Bayesian optimal interval (BOIN) design provides the simplest approach for dose adjustment. We propose the novel early completion method for the clinical trials with the BOIN design when the MTD is estimated with sufficient accuracy. This completion method can be easily calculated. In addition, the method does not require many more patients treated for the determination of early completion. We confirm that the BOIN design applying the early completion method has almost the same MTD identification rate compared to the BOIN design through simulations conducted based on over 30 000 scenarios.
SiM Bayesian Methods Networks & Graphs · 发表于 2021-04-12
Hao Li, Daeyoung Lim, Ming‐Hui Chen, Joseph G. Ibrahim, Sungduk Kim, Arvind K. Shah, Jianxin Lin
摘要
Network meta‐analysis (NMA) is gaining popularity in evidence synthesis and network meta‐regression allows us to incorporate potentially important covariates into network meta‐analysis. In this article, we propose a Bayesian network meta‐regression hierarchical model and assume a general multivariate t distribution for the random treatment effects. The multivariate t distribution is desired for heavy‐tailed random effects and converges to the multivariate normal distribution when the degrees of freedom go to infinity. Moreover, in NMA, some treatments are compared only in a single study. To overcome such sparsity, we propose a log‐linear regression model for the variances of the random effects and incorporate aggregate covariates into modeling the variance components. We develop a Markov chain Monte Carlo sampling algorithm to sample from the posterior distribution via the collapsed Gibbs technique. We further use the deviance information criterion and the logarithm of the pseudo‐marginal likelihood for model comparison. A simulation study is conducted and a detailed analysis from our motivating case study is carried out to further demonstrate the proposed methodology.
SiM High-Dimensional · 发表于 2021-04-11
Tianshu Feng, Linda Ng Boyle
摘要
Motor vehicle crashes are a global public health concern. Most analysis have used zero‐inflated count models for examining crash counts. However, few methods are available to account for safety metrics that have semi‐continuous observations. This article considers the problem of variable selection for the semi‐continuous zero‐inflated (SCZI) models. These models include two parts: a zero‐inflated part and a nonzero continuous part. A special group regularization is designed to accommodate the unique structure of two‐part SCZI models, and a type of Bayesian information criterion is proposed to select tuning parameters. We illustrate the variable selection process of the proposed model using lane position data from a driving simulator study. In the study, drivers stay in the intended lane for the majority of their drive (zero‐inflated part). On occasion, some drivers do drift out of their intended driving lane (nonzero continuous part). Our findings show that individual differences can be captured with the proposed model, which has implications for driving safety and the design of in‐vehicle alerting systems.
SiM Genetics & Omics High-Dimensional · 发表于 2021-04-11
Yong He, Pengfei Liu, Xinsheng Zhang, Wang Zhou
摘要
Microbial communities analysis is drawing growing attention due to the rapid development fire of high‐throughput sequencing techniques nowadays. The observed data has the following typical characteristics: it is high‐dimensional, compositional (lying in a simplex) and even would be leptokurtic and highly skewed due to the existence of overly abundant taxa, which makes the conventional correlation analysis infeasible to study the co‐occurrence and co‐exclusion relationship between microbial taxa. In this article, we address the challenges of covariance estimation for this kind of data. Assuming the basis covariance matrix lying in a well‐recognized class of sparse covariance matrices, we adopt a proxy matrix known as centered log‐ratio covariance matrix in the literature. We construct a Median‐of‐Means estimator for the centered log‐ratio covariance matrix and propose a thresholding procedure that is adaptive to the variability of individual entries. By imposing a much weaker finite fourth moment condition compared with the sub‐Gaussianity condition in the literature, we derive the optimal rate of convergence under the spectral norm. In addition, we also provide theoretical guarantee on support recovery. The adaptive thresholding procedure of the MOM estimator is easy to implement and gains robustness when outliers or heavy‐tailedness exist. Thorough simulation studies are conducted to show the advantages of the proposed procedure over some state‐of‐the‐arts methods. At last, we apply the proposed method to analyze a microbiome dataset in human gut.
SiM Other · 发表于 2021-04-11
Jialiang Li, Yaguang Li, Baisuo Jin, Michael R. Kosorok
摘要
We propose a multithreshold change plane regression model which naturally partitions the observed subjects into subgroups with different covariate effects. The underlying grouping variable is a linear function of observed covariates and thus multiple thresholds produce change planes in the covariate space. We contribute a novel two‐stage estimation approach to determine the number of subgroups, the location of thresholds, and all other regression parameters. In the first stage we adopt a group selection principle to consistently identify the number of subgroups, while in the second stage change point locations and model parameter estimates are refined by a penalized induced smoothing technique. Our procedure allows sparse solutions for relatively moderate‐ or high‐dimensional covariates. We further establish the asymptotic properties of our proposed estimators under appropriate technical conditions. We evaluate the performance of the proposed methods by simulation studies and provide illustrations using two medical data examples. Our proposal for subgroup identification may lead to an immediate application in personalized medicine.
SiM Missing Data & Measurement Error Diagnostics & Prediction · 发表于 2021-04-11
Pin Li, Jeremy M. G. Taylor, Daniel E. Spratt, R. Jeffery Karnes, Matthew J. Schipper
摘要
In medical research, the Brier score (BS) and the area under the receiver operating characteristic (ROC) curves (AUC) are two common metrics used to evaluate prediction models of a binary outcome, such as using biomarkers to predict the risk of developing a disease in the future. The assessment of an existing prediction models using data with missing covariate values is challenging. In this article, we propose inverse probability weighted (IPW) and augmented inverse probability weighted (AIPW) estimates of AUC and BS to handle the missing data. An alternative approach uses multiple imputation (MI), which requires a model for the distribution of the missing variable. We evaluated the performance of IPW and AIPW in comparison with MI in simulation studies under missing completely at random, missing at random, and missing not at random scenarios. When there are missing observations in the data, MI and IPW can be used to obtain unbiased estimates of BS and AUC if the imputation model for the missing variable or the model for the missingness is correctly specified. MI is more efficient than IPW. Our simulation results suggest that AIPW can be more efficient than IPW, and also achieves double robustness from miss‐specification of either the missingness model or the imputation model. The outcome variable should be included in the model for the missing variable under all scenarios, while it only needs to be included in missingness model if the missingness depends on the outcome. We illustrate these methods using an example from prostate cancer.
SiM Other · 发表于 2021-04-11
Jean‐Benoît Rossel, Valentin Rousson, Yves Eggli
摘要
We consider the non‐trivial problem of estimating a health cost repartition among diseases from patients' hospital stays' global costs in the presence of multimorbidity, that is, when the patients may suffer from more than one disease. The problem is even harder in the presence of interactions among the disease costs, that is, when the costs of having, for example, two diseases simultaneously do not match the sum of the basic costs of having each disease alone, generating an extra cost which might be either positive or negative. In such a situation, there might be no “true solution” and the choice of the method to be used to solve the problem will depend on how one wishes to allocate the extra costs among the diseases. In this article, we study mathematically how different methods proceed in this regard, namely ordinary least squares (OLS), generalized linear models (GLM), and an iterative proportional repartition (IPR) algorithm, in a simple case with only two diseases. It turned out that only IPR allowed to retrieve the total costs and the unambiguous solution that one would have in a setting without interaction, that is, when no extra cost has to be allocated, while OLS and GLM may produce some negative health costs. Also, contrary to OLS, IPR is taking into account the basic costs of the diseases for the allocation of the extra cost. We conclude that IPR seems to be the most natural method to solve the problem, at least among those considered.
SMMR Survival Analysis Causal Inference Bayesian Methods · 发表于 2021-04-09
Xiaoxiao Zhou, Xinyuan Song
摘要
Mediation analysis aims to decompose a total effect into specific pathways and investigate the underlying causal mechanism. Although existing methods have been developed to conduct mediation analysis in the context of survival models, none of these methods accommodates the existence of a substantial proportion of subjects who never experience the event of interest, even if the follow-up is sufficiently long. In this study, we consider mediation analysis for the mixture of Cox proportional hazards cure models that cope with the cure fraction problem. Path-specific effects on restricted mean survival time and survival probability are assessed by introducing a partially latent group indicator and applying the mediation formula approach in a three-stage mediation framework. A Bayesian approach with P-splines for approximating the baseline hazard function is developed to conduct analysis. The satisfactory performance of the proposed method is verified through simulation studies. An application of the Alzheimer’s disease (AD) neuroimaging initiative dataset investigates the causal effects of APOE-[Formula: see text] allele on AD progression.
JASA Spatial & Time Series · 发表于 2021-04-08
Andrew Zammit-Mangion, Tin Lok James Ng, Quan Vu, Maurizio Filippone
摘要
Spatial processes with nonstationary and anisotropic covariance structure are often used when modeling, analyzing, and predicting complex environmental phenomena. Such processes may often be expressed as ones that have stationary and isotropic covariance structure on a warped spatial domain. However, the warping function is generally difficult to fit and not constrained to be injective, often resulting in “space-folding.” Here, we propose modeling an injective warping function through a composition of multiple elemental injective functions in a deep-learning framework. We consider two cases; first, when these functions are known up to some weights that need to be estimated, and, second, when the weights in each layer are random. Inspired by recent methodological and technological advances in deep learning and deep Gaussian processes, we employ approximate Bayesian methods to make inference with these models using graphics processing units. Through simulation studies in one and two dimensions we show that the deep compositional spatial models are quick to fit, and are able to provide better predictions and uncertainty quantification than other deep stochastic models of similar complexity. We also show their remarkable capacity to model nonstationary, anisotropic spatial data using radiances from the MODIS instrument aboard the Aqua satellite. *(abstract via OpenAlex)*
Biometrics Causal Inference · 发表于 2021-04-07
Jiangang Liao, Charles Rohde
摘要
The propensity methodology is widely used in medical research to compare different treatments in designs with a nonrandomized treatment allocation. The inverse probability weighted (IPW) estimators are a primary tool for estimating the average treatment effect but the large variance of these estimators is often a significant concern for their reliable use in practice. Inspired by Rao‐Blackwellization, this paper proposes a method to smooth an IPW estimator by replacing the weights in the original estimator by their mean over a distribution of the potential treatment assignment. In our simulation study, the smoothed IPW estimator achieves a substantial variance reduction over its original version with only a small increased bias, for example two‐to‐sevenfold variance reduction for the three IPW estimators in Lunceford and Davidian [Statistics in Medicine, 23(19), 2937–2960]. In addition, our proposed smoothing can also be applied to the locally efficient and doubly robust estimator for added protection against model misspecification. An implementation in R is provided.
SiM Longitudinal Data Latent Variables & Mixtures · 发表于 2021-04-07
Amna Klich, René Ecochard, Fabien Subtil
摘要
Trajectory classification has become frequent in clinical research to understand the heterogeneity of individual trajectories. The standard classification model for trajectories assumes no between‐individual variance within groups. However, this assumption is often not appropriate, which may overestimate the error variance of the model, leading to a biased classification. Hence, two extensions of the standard classification model were developed through a mixed model. The first one considers an equal between‐individual variance across groups, and the second one considers unequal between‐individual variance. Simulations were performed to evaluate the impact of these considerations on the classification. The simulation results showed that the first extended model gives a lower misclassification percentage (with differences up to 50%) than the standard one in case of presence of a true variance between individuals inside groups. The second model decreases the misclassification percentage compared with the first one (up to 11%) when the between‐individual variance is unequal between groups. However, these two extensions require high number of repeated measurements to be adjusted correctly. Using human chorionic gonadotropin trajectories after curettage for hydatidiform mole, the standard classification model classified trajectories mainly according to their levels whereas the two extended models classified them according to their patterns, which provided more clinically relevant groups. In conclusion, for studies with a nonnegligible number of repeated measurements, the use, in first instance, of a classification model that considers equal between‐individual variance across groups rather than a standard classification model, appears more appropriate. A model that considers unequal between‐individual variance may find its place thereafter.
SMMR Clinical Trials · 发表于 2021-04-07
Fan Li, Guangyu Tong
SMMR Survival Analysis Nonparametric & Semiparametric · 发表于 2021-04-07
Zhiping Qiu, Huijuan Ma, Jianwei Chen, Gregg E Dinse
摘要
The quantile regression model has increasingly become a useful approach for analyzing survival data due to its easy interpretation and flexibility in exploring the dynamic relationship between a time-to-event outcome and the covariates. In this paper, we consider the quantile regression model for survival data with missing censoring indicators. Based on the augmented inverse probability weighting technique, two weighted estimating equations are developed and corresponding easily implemented algorithms are suggested to solve the estimating equations. Asymptotic properties of the resultant estimators and the resampling-based inference procedures are established. Finally, the finite sample performances of the proposed approaches are investigated in simulation studies and a real data application.
SMMR Causal Inference Survival Analysis Econometrics & Economics · 发表于 2021-04-07
Andrew J Spieker, Nicholas Illenberger, Jason A Roy, Nandita Mitra
摘要
Considerations regarding clinical effectiveness and cost are essential in comparing the overall value of two treatments. There has been growing interest in methodology to integrate cost and effectiveness measures in order to inform policy and promote adequate resource allocation. The net monetary benefit aggregates information on differences in mean cost and clinical outcomes; the cost-effectiveness acceptability curve was developed to characterize the extent to which the strength of evidence regarding net monetary benefit changes with fluctuations in the willingness-to-pay threshold. Methods to derive insights from characteristics of the cost/clinical outcomes besides mean differences remain undeveloped but may also be informative. We propose a novel probabilistic measure of cost-effectiveness based on the stochastic ordering of the individual net benefit distribution under each treatment. Our approach is able to accommodate features frequently encountered in observational data including confounding and censoring, and complements the net monetary benefit in the insights it provides. We conduct a range of simulations to evaluate finite-sample performance and illustrate our proposed approach using simulated data based on a study of endometrial cancer patients.
Biometrics Longitudinal Data Bayesian Methods · 发表于 2021-04-07
Simon N. Wood
摘要
The number of new infections per day is a key quantity for effective epidemic management. It can be estimated relatively directly by testing of random population samples. Without such direct epidemiological measurement, other approaches are required to infer whether the number of new cases is likely to be increasing or decreasing: for example, estimating the pathogen‐effective reproduction number, R, using data gathered from the clinical response to the disease. For coronavirus disease 2019 (Covid‐19/SARS‐Cov‐2), such R estimation is heavily dependent on modelling assumptions, because the available clinical case data are opportunistic observational data subject to severe temporal confounding. Given this difficulty, it is useful to retrospectively reconstruct the time course of infections from the least compromised available data, using minimal prior assumptions. A Bayesian inverse problem approach applied to UK data on first‐wave Covid‐19 deaths and the disease duration distribution suggests that fatal infections were in decline before full UK lockdown (24 March 2020), and that fatal infections in Sweden started to decline only a day or two later. An analysis of UK data using the model of Flaxman et al. gives the same result under relaxation of its prior assumptions on R, suggesting an enhanced role for non‐pharmaceutical interventions short of full lockdown in the UK context. Similar patterns appear to have occurred in the subsequent two lockdowns.
SMMR Survival Analysis Missing Data & Measurement Error Causal Inference · 发表于 2021-04-07
Yingrui Yang, Molin Wang
摘要
In epidemiology, identifying the effect of exposure variables in relation to a time-to-event outcome is a classical research area of practical importance. Incorporating propensity score in the Cox regression model, as a measure to control for confounding, has certain advantages when outcome is rare. However, in situations involving exposure measured with moderate to substantial error, identifying the exposure effect using propensity score in Cox models remains a challenging yet unresolved problem. In this paper, we propose an estimating equation method to correct for the exposure misclassification-caused bias in the estimation of exposure-outcome associations. We also discuss the asymptotic properties and derive the asymptotic variances of the proposed estimators. We conduct a simulation study to evaluate the performance of the proposed estimators in various settings. As an illustration, we apply our method to correct for the misclassification-caused bias in estimating the association of PM2.5 level with lung cancer mortality using a nationwide prospective cohort, the Nurses’ Health Study. The proposed methodology can be applied using our user-friendly R program published online.
SMMR Bayesian Methods · 发表于 2021-04-07
Zvifadzo Matsena Zingoni, Tobias F Chirwa, Jim Todd, Eustasius Musenge
摘要
There are numerous fields of science in which multistate models are used, including biomedical research and health economics. In biomedical studies, these stochastic continuous-time models are used to describe the time-to-event life history of an individual through a flexible framework for longitudinal data. The multistate framework can describe more than one possible time-to-event outcome for a single individual. The standard estimation quantities in multistate models are transition probabilities and transition rates which can be mapped through the Kolmogorov-Chapman forward equations from the Bayesian estimation perspective. Most multistate models assume the Markov property and time homogeneity; however, if these assumptions are violated, an extension to non-Markovian and time-varying transition rates is possible. This manuscript extends reviews in various types of multistate models, assumptions, methods of estimation and data features compatible with fitting multistate models. We highlight the contrast between the frequentist (maximum likelihood estimation) and the Bayesian estimation approaches in the multistate modeling framework and point out where the latter is advantageous. A partially observed and aggregated dataset from the Zimbabwe national ART program was used to illustrate the use of Kolmogorov-Chapman forward equations. The transition rates from a three-stage reversible multistate model based on viral load measurements in WinBUGS were reported.
SMMR Diagnostics & Prediction · 发表于 2021-04-07
Yalda Zarnegarnia, Shari Messinger
摘要
Receiver operating characteristic curves are widely used in medical research to illustrate biomarker performance in binary classification, particularly with respect to disease or health status. Study designs that include related subjects, such as siblings, usually have common environmental or genetic factors giving rise to correlated biomarker data. The design could be used to improve detection of biomarkers informative of increased risk, allowing initiation of treatment to stop or slow disease progression. Available methods for receiver operating characteristic construction do not take advantage of correlation inherent in this design to improve biomarker performance. This paper will briefly review some developed methods for receiver operating characteristic curve estimation in settings with correlated data from case–control designs and will discuss the limitations of current methods for analyzing correlated familial paired data. An alternative approach using conditional receiver operating characteristic curves will be demonstrated. The proposed approach will use information about correlation among biomarker values, producing conditional receiver operating characteristic curves that evaluate the ability of a biomarker to discriminate between affected and unaffected subjects in a familial paired design.
JASA Nonparametric & Semiparametric Latent Variables & Mixtures · 发表于 2021-04-06
Nabarun Deb, Sujayam Saha, Adityanand Guntuboyina, Bodhisattva Sen
摘要
In this article, we study a generalization of the two-groups model in the presence of covariates—a problem that has recently received much attention in the statistical literature due to its applicability in multiple hypotheses testing problems. The model we consider allows for infinite dimensional parameters and offers flexibility in modeling the dependence of the response on the covariates. We discuss the identifiability issues arising in this model and systematically study several estimation strategies. We propose a tuning parameter-free nonparametric maximum likelihood method, implementable via the expectation-maximization algorithm, to estimate the unknown parameters. Further, we derive the rate of convergence of the proposed estimators—in particular we show that the finite sample Hellinger risk for every ‘approximate’ nonparametric maximum likelihood estimator achieves a near-parametric rate (up to logarithmic multiplicative factors). In addition, we propose and theoretically study two ‘marginal’ methods that are more scalable and easily implementable. We demonstrate the efficacy of our procedures through extensive simulation studies and relevant data analyses—one arising from neuroscience and the other from astronomy. We also outline the application of our methods to multiple testing. The companion R package NPMLEmix implements all the procedures proposed in this article. *(abstract via OpenAlex)*
JASA Other · 发表于 2021-04-06
Thomas W. Yee
摘要
The Wald test remains ubiquitous in statistical practice despite shortcomings such as its inaccuracy in small samples and lack of invariance under reparameterization. This article develops on another but lesser-known shortcoming called the Hauck–Donner effect (HDE) whereby a Wald test statistic is no longer monotone increasing as a function of increasing distance between the parameter estimate and the null value. Resulting in an upward biased p-value and loss of power, the aberration can lead to very damaging consequences such as in variable selection. The HDE afflicts many types of regression models and corresponds to estimates near the boundary of the parameter space. This article presents several new results, and its main contributions are to (i) propose a very general test for detecting the HDE in the class of vector generalized linear models (VGLMs), regardless of the underlying cause; (ii) fundamentally characterize the HDE by pairwise ratios of Wald and Rao score and likelihood ratio test statistics for 1-parameter distributions with large samples; (iii) show that the parameter space may be partitioned into an interior encased by at least 5 HDE severity measures (faint, weak, moderate, strong, extreme); (iv) prove that a necessary condition for the HDE in a 2 by 2 table is a log odds ratio of at least 2; (v) give some practical guidelines about HDE-free hypothesis testing. Overall, practical post-fit tests can now be conducted potentially to any model estimated by iteratively reweighted least squares, especially the GLM and VGLM classes, the latter which encompasses many popular regression models. *(abstract via OpenAlex)*
Biometrics Missing Data & Measurement Error Machine Learning · 发表于 2021-04-06
Daniel O. Scharfstein, Jon Steingrimsson, Aidan McDermott, Chenguang Wang, Souvik Ray, Aimee Campbell, Edward Nunes, Abigail Matthews
摘要
In this paper, we present a method for conducting global sensitivity analysis of randomized trials in which binary outcomes are scheduled to be collected on participants at prespecified points in time after randomization and these outcomes may be missing in a nonmonotone fashion. We introduce a class of missing data assumptions, indexed by sensitivity parameters, which are anchored around the missing not at random assumption introduced by Robins (Statistics in Medicine, 1997). For each assumption in the class, we establish that the joint distribution of the outcomes is identifiable from the distribution of the observed data. Our estimation procedure uses the plug‐in principle, where the distribution of the observed data is estimated using random forests. We establish asymptotic properties for our estimation procedure. We illustrate our methodology in the context of a randomized trial designed to evaluate a new approach to reducing substance use, assessed by testing urine samples twice weekly, among patients entering outpatient addiction treatment. We evaluate the finite sample properties of our method in a realistic simulation study. Our methods have been implemented in an R package entitled slabm.
JASA Bayesian Methods High-Dimensional · 发表于 2021-04-06
Daniel R. Kowal
摘要
Prediction is critical for decision-making under uncertainty and lends validity to statistical inference. With targeted prediction, the goal is to optimize predictions for specific decision tasks of interest, which we represent via functionals. Although classical decision analysis extracts predictions from a Bayesian model, these predictions are often difficult to interpret and slow to compute. Instead, we design a class of parametrized actions for Bayesian decision analysis that produce optimal, scalable, and simple targeted predictions. For a wide variety of action parametrizations and loss functions-including linear actions with sparsity constraints for targeted variable selection-we derive a convenient representation of the optimal targeted prediction that yields efficient and interpretable solutions. Customized out-of-sample predictive metrics are developed to evaluate and compare among targeted predictors. Through careful use of the posterior predictive distribution, we introduce a procedure that identifies a set of near-optimal, or acceptable targeted predictors, which provide unique insights into the features and level of complexity needed for accurate targeted prediction. Simulations demonstrate excellent prediction, estimation, and variable selection capabilities. Targeted predictions are constructed for physical activity data from the National Health and Nutrition Examination Survey (NHANES) to better predict and understand the characteristics of intraday physical activity. *(abstract via PubMed)*
JASA Meta-Analysis & Data Integration · 发表于 2021-04-06
Xi Chen, Jason D. Lee, He Li, Yun Yang
摘要
The growing size of modern datasets brings many challenges to the existing statistical estimation approaches, which calls for new distributed methodologies. This article studies distributed estimation for a fundamental statistical machine learning problem, principal component analysis (PCA). Despite the massive literature on top eigenvector estimation, much less is presented for the top-L-dim (L > 1) eigenspace estimation, especially in a distributed manner. We propose a novel multi-round algorithm for constructing top-L-dim eigenspace for distributed data. Our algorithm takes advantage of shift-and-invert preconditioning and convex optimization. Our estimator is communication-efficient and achieves a fast convergence rate. In contrast to the existing divide-and-conquer algorithm, our approach has no restriction on the number of machines. Theoretically, the traditional Davis–Kahan theorem requires the explicit eigengap assumption to estimate the top-L-dim eigenspace. To abandon this eigengap assumption, we consider a new route in our analysis: instead of exactly identifying the top-L-dim eigenspace, we show that our estimator is able to cover the targeted top-L-dim population eigenspace. Our distributed algorithm can be applied to a wide range of statistical problems based on PCA, such as principal component regression and single index model. Finally, we provide simulation studies to demonstrate the performance of the proposed distributed estimator. *(abstract via OpenAlex)*
SiM Bayesian Methods · 发表于 2021-04-05
Andrew Gelman, Matthijs Vákár
摘要
It is not always clear how to adjust for control data in causal inference, balancing the goals of reducing bias and variance. We show how, in a setting with repeated experiments, Bayesian hierarchical modeling yields an adaptive procedure that uses the data to determine how much adjustment to perform. The result is a novel analysis with increased statistical efficiency compared with the default analysis based on difference estimates. We demonstrate this procedure on two real examples, as well as on a series of simulated datasets. We show that the increased efficiency can have real‐world consequences in terms of the conclusions that can be drawn from the experiments. We also discuss the relevance of this work to causal inference and statistical design and analysis more generally.
SiM Survival Analysis Longitudinal Data · 发表于 2021-04-05
Guohai Zhou, Lang Wu
摘要
Nonlinear mixed‐effects (NLME) models are commonly used in longitudinal studies such as pharmacokinetics and HIV viral dynamics studies. NLME models are often derived based on underlying data‐generating mechanisms, therefore the parameters in these models often have natural physical interpretations that may suggest reasonable constraints on certain parameters. For example, the HIV viral decay rates for populations receiving anti‐HIV treatments may be reasonably expected to be nonnegative. Hypothesis testing for these parameters should incorporate practically reasonable constraints to increase statistical power. Motivated from HIV viral dynamic models, in this article we propose multiparameter one‐sided or constrained tests for NLME models with censored responses, for example, viral dynamic models with viral loads subject to lower detection limits. We propose approximate likelihood‐based tests that are computationally efficient. We evaluate the tests via simulations and show that the proposed tests are more powerful than the corresponding two‐sided or unrestricted tests. We apply the proposed tests to two AIDS datasets with new findings.
SiM Latent Variables & Mixtures Survival Analysis High-Dimensional · 发表于 2021-04-05
Beilin Jia, Donglin Zeng, Jason J. Z. Liao, Guanghan F. Liu, Xianming Tan, Guoqing Diao, Joseph G. Ibrahim
摘要
In cancer studies, it is important to understand disease heterogeneity among patients so that precision medicine can particularly target high‐risk patients at the right time. Many feature variables such as demographic variables and biomarkers, combined with a patient's survival outcome, can be used to infer such latent heterogeneity. In this work, we propose a mixture model to model each patient's latent survival pattern, where the mixing probabilities for latent groups are modeled through a multinomial distribution. The Bayesian information criterion is used for selecting the number of latent groups. Furthermore, we incorporate variable selection with the adaptive lasso into inference so that only a few feature variables will be selected to characterize the latent heterogeneity. We show that our adaptive lasso estimator has oracle properties when the number of parameters diverges with the sample size. The finite sample performance is evaluated by the simulation study, and the proposed method is illustrated by two datasets.
SMMR Clinical Trials Survival Analysis · 发表于 2021-04-05
Yongqiang Tang
摘要
Log-rank tests have been widely used to compare two survival curves in biomedical research. We describe a unified approach to power and sample size calculation for the unweighted and weighted log-rank tests in superiority, noninferiority and equivalence trials. It is suitable for both time-driven and event-driven trials. A numerical algorithm is suggested. It allows flexible specification of the patient accrual distribution, baseline hazards, and proportional or nonproportional hazards patterns, and enables efficient sample size calculation when there are a range of choices for the patient accrual pattern and trial duration. A confidence interval method is proposed for the trial duration of an event-driven trial. We point out potential issues with several popular sample size formulae. Under proportional hazards, the power of a survival trial is commonly believed to be determined by the number of observed events. The belief is roughly valid for noninferiority and equivalence trials with similar survival and censoring distributions between two groups, and for superiority trials with balanced group sizes. In unbalanced superiority trials, the power depends also on other factors such as data maturity. Surprisingly, the log-rank test usually yields slightly higher power than the Wald test from the Cox model under proportional hazards in simulations. We consider various nonproportional hazards patterns induced by delayed effects, cure fractions, and/or treatment switching. Explicit power formulae are derived for the combination test that takes the maximum of two or more weighted log-rank tests to handle uncertain nonproportional hazards patterns. Numerical examples are presented for illustration.
SiM Diagnostics & Prediction Clinical Trials Bayesian Methods · 发表于 2021-04-04
Konstantinos Pateras, Stavros Nikolakopoulos, Kit C. B. Roes
摘要
In drug development programs, proof‐of‐concept Phase II clinical trials typically have a biomarker as a primary outcome, or an outcome that can be observed with relatively short follow‐up. Subsequently, the Phase III clinical trials aim to demonstrate the treatment effect based on a clinical outcome that often needs a longer follow‐up to be assessed. Early‐phase outcomes or biomarkers are typically associated with late‐phase outcomes and they are often included in Phase III trials. The decision to proceed to Phase III development is based on analysis of the early‐Phase II outcome data. In rare diseases, it is likely that only one Phase II trial and one Phase III trial are available. In such cases and before drug marketing authorization requests, positive results of the early‐phase outcome of Phase II trials are then likely seen as supporting (or even replicating) positive Phase III results on the late‐phase outcome, without a formal retrospective combined assessment and without accounting for between‐study differences. We used double‐regression modeling applied to the Phase II and Phase III results to numerically mimic this informal retrospective assessment. We provide an analytical solution for the bias and mean square error of the overall effect that leads to a corrected double‐regression. We further propose a flexible Bayesian double‐regression approach that minimizes the bias by accounting for between‐study differences via discounting the Phase II early‐phase outcome when they are not in line with the Phase III biomarker outcome results. We illustrate all methods with an orphan drug example for Fabry disease.
JASA High-Dimensional · 发表于 2021-04-03
Xiaohan Yan, Jacob Bien
摘要
It is common in modern prediction problems for many predictor variables to be counts of rarely occurring events. This leads to design matrices in which many columns are highly sparse. The challenge posed by such “rare features” has received little attention despite its prevalence in diverse areas, ranging from natural language processing (e.g., rare words) to biology (e.g., rare species). We show, both theoretically and empirically, that not explicitly accounting for the rareness of features can greatly reduce the effectiveness of an analysis. We next propose a framework for aggregating rare features into denser features in a flexible manner that creates better predictors of the response. Our strategy leverages side information in the form of a tree that encodes feature similarity. We apply our method to data from TripAdvisor, in which we predict the numerical rating of a hotel based on the text of the associated review. Our method achieves high accuracy by making effective use of rare words; by contrast, the lasso is unable to identify highly predictive words if they are too rare. A companion R package, called rare, implements our new estimator, using the alternating direction method of multipliers. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
JASA High-Dimensional Causal Inference · 发表于 2021-04-03
Dean Eckles, Eytan Bakshy
摘要
Peer effects, in which an individual’s behavior is affected by peers’ behavior, are posited by multiple theories in the social sciences. Randomized field experiments that identify peer effects, however, are often expensive or infeasible, so many studies of peer effects use observational data, which is expected to suffer from confounding. Here we show, in the context of information and media diffusion, that high-dimensional adjustment of a nonexperimental control group (660 million observations) using propensity score models produces estimates of peer effects statistically indistinguishable from those using a large randomized experiment (215 million observations). Compared with the experiment, naive observational estimators overstate peer effects by over 300% and commonly available variables (e.g., demographics) offer little bias reduction. Adjusting for a measure of prior behaviors closely related to the focal behavior reduces this bias by 91%, while models adjusting for over 3700 past behaviors provide additional bias reduction, reducing bias by over 97%, which is statistically indistinguishable from unbiasedness. This demonstrates how detailed records of behavior can improve studies of social influence, information diffusion, and imitation; these results are encouraging for the credibility of some studies but also cautionary for studies of peer effects in rare or new behaviors. More generally, these results show how large, high-dimensional datasets and statistical learning can be used to improve causal inference. Supplementary materials for this article are available online. *(abstract via OpenAlex)*
JASA Networks & Graphs Bayesian Methods Longitudinal Data · 发表于 2021-04-03
Joshua Lukemire, Suprateek Kundu, Giuseppe Pagnoni, Ying Guo
摘要
Investigating the similarity and changes in brain networks under different mental conditions has become increasingly important in neuroscience research. A standard separate estimation strategy fails to pool information across networks and hence has reduced estimation accuracy and power to detect between-network differences. Motivated by a fMRI Stroop task experiment that involves multiple related tasks, we develop an integrative Bayesian approach for jointly modeling multiple brain networks that provides a systematic inferential framework for network comparisons. The proposed approach explicitly models shared and differential patterns via flexible Dirichlet process-based priors on edge probabilities. Conditional on edges, the connection strengths are modeled via Bayesian spike and slab prior on the precision matrix off-diagonals. Numerical simulations illustrate that the proposed approach has increased power to detect true differential edges while providing adequate control on false positives and achieves greater network estimation accuracy compared to existing methods. The Stroop task data analysis reveals greater connectivity differences between task and fixation that are concentrated in brain regions previously identified as differentially activated in Stroop task, and more nuanced connectivity differences between exertion and relaxed task. In contrast, penalized modeling approaches involving computationally burdensome permutation tests reveal negligible network differences between conditions that seem biologically implausible. *(abstract via PubMed)*
JASA Causal Inference Networks & Graphs · 发表于 2021-04-03
Eric J. Tchetgen Tchetgen, Isabel R. Fulcher, Ilya Shpitser
摘要
Methods for inferring average causal effects have traditionally relied on two key assumptions: (i) the intervention received by one unit cannot causally influence the outcome of another; and (ii) units can be organized into nonoverlapping groups such that outcomes of units in separate groups are independent. In this article, we develop new statistical methods for causal inference based on a single realization of a network of connected units for which neither assumption (i) nor (ii) holds. The proposed approach allows both for arbitrary forms of interference, whereby the outcome of a unit may depend on interventions received by other units with whom a network path through connected units exists; and long range dependence, whereby outcomes for any two units likewise connected by a path in the network may be dependent. Under network versions of consistency and no unobserved confounding, inference is made tractable by an assumption that the networks outcome, treatment and covariate vectors are a single realization of a certain chain graph model. This assumption allows inferences about various network causal effects via the auto-g-computation algorithm, a network generalization of Robins' well-known g-computation algorithm previously described for causal inference under assumptions (i) and (ii). Supplementary materials for this article are available online. *(abstract via PubMed)*
SiM Networks & Graphs Bayesian Methods · 发表于 2021-04-02
Ravi Goyal, Victor De Gruttola
摘要
A Bayesian approach to conduct network model selection is presented for a general class of network models referred to as the congruence class models (CCMs). CCMs form a broad class that includes as special cases several common network models, such as the Erdős‐Rényi‐Gilbert model, stochastic block model, and many exponential random graph models. Due to the range of models that can be specified as CCMs, our proposed method is better able to select models consistent with generative mechanisms associated with observed networks than are current approaches. In addition, our approach allows for incorporation of prior information. We illustrate the use of this approach to select among several different proposed mechanisms for the structure of patient‐sharing networks; such networks have been found to be associated with the cost and quality of medical care. We found evidence in support of heterogeneity in sociality but not selective mixing by provider type or degree.
AoS Nonparametric & Semiparametric · 发表于 2021-04-01
Steven R. Howard, Aaditya Ramdas, Jon McAuliffe, Jasjeet Sekhon
摘要
A confidence sequence is a sequence of confidence intervals that is uniformly valid over an unbounded time horizon. Our work develops confidence sequences whose widths go to zero, with nonasymptotic coverage guarantees under nonparametric conditions. We draw connections between the Cramér–Chernoff method for exponential concentration, the law of the iterated logarithm (LIL) and the sequential probability ratio test—our confidence sequences are time-uniform extensions of the first; provide tight, nonasymptotic characterizations of the second; and generalize the third to nonparametric settings, including sub-Gaussian and Bernstein conditions, self-normalized processes and matrix martingales. We illustrate the generality of our proof techniques by deriving an empirical-Bernstein bound growing at a LIL rate, as well as a novel upper LIL for the maximum eigenvalue of a sum of random matrices. Finally, we apply our methods to covariance matrix estimation and to estimation of sample average treatment effect under the Neyman–Rubin potential outcomes model.
AoS Other · 发表于 2021-04-01
Fritjof Freise, Norbert Gaffke, Rainer Schwabe
摘要
For a nonlinear regression model, the information matrices of designs depend on the parameter of the model. The adaptive Wynn algorithm for D-optimal design estimates the parameter at each step on the basis of the observed responses and employed design points so far, and selects the next design point as in the classical Wynn algorithm for D-optimal design. The name “Wynn algorithm” is in honor of Henry P. Wynn who established the latter “classical” algorithm in his 1970 paper (Ann. Math. Stat. 41 (1970) 1655–1664). The asymptotics of the sequences of designs and maximum likelihood estimates generated by the adaptive algorithm is studied for an important class of nonlinear regression models: generalized linear models whose (univariate) response variables follow a distribution from a one-parameter exponential family. Under the assumptions of compactness of the experimental region and of the parameter space together with some natural continuity assumptions, it is shown that the adaptive ML-estimators are strongly consistent and the design sequence is asymptotically locally D-optimal at the true parameter point. If the true parameter point is an interior point of the parameter space, then under some smoothness assumptions the asymptotic normality of the adaptive ML-estimators is obtained.
AoS Survival Analysis Bayesian Methods · 发表于 2021-04-01
Federico Camerlenghi, Antonio Lijoi, Igor Prünster
摘要
Hierarchical nonparametric processes are popular tools for defining priors on collections of probability distributions, which induce dependence across multiple samples. In survival analysis problems, one is typically interested in modeling the hazard rates, rather than the probability distributions themselves, and the currently available methodologies are not applicable. Here, we fill this gap by introducing a novel, and analytically tractable, class of multivariate mixtures whose distribution acts as a prior for the vector of sample-specific baseline hazard rates. The dependence is induced through a hierarchical specification of the mixing random measures that ultimately corresponds to a composition of random discrete combinatorial structures. Our theoretical results allow to develop a full Bayesian analysis for this class of models, which can also account for right-censored survival data and covariates, and we also show posterior consistency. In particular, we emphasize that the posterior characterization we achieve is the key for devising both marginal and conditional algorithms for evaluating Bayesian inferences of interest. The effectiveness of our proposal is illustrated through some synthetic and real data examples.