Article
Statistics & Probability
Methsarani Premathilaka, Rong Liu
Summary: Repeated/clustered data are gaining popularity in research studies. This study introduces an asymptotic Wald-type simultaneous confidence bands (SCBs) method for nonparametric functions in the presence of within-cluster error correlation. Simulation studies support the theoretical performance of the proposed method. The method is also applied to a real dataset on test scores.
Article
Economics
Roger Koenker
Summary: Stochastic frontier models and methods, pioneered by Schmidt and others in the late 1970s, offer a rare departure from the conventional focus on conditional means in econometrics. These methods also played a key role in the early development of quantile regression. This paper provides a brief introduction to Hotelling tube methods for constructing confidence bands in nonparametric quantile regression, and then presents strengthened performance guarantees for these bands based on recent advances in conformal inference. These methods offer an idiosyncratic approach to nonparametric inference for stochastic frontier models.
EMPIRICAL ECONOMICS
(2023)
Article
Mathematical & Computational Biology
Jianan Peng, Wei Liu, Frank Bretz, A. J. Hayter
Summary: This study extends the research on finite comparisons of several univariate linear regression models to finite comparisons of several multivariate linear regression models using simultaneous confidence tubes. The simultaneous confidence tubes provide more informative inferences for the comparison of multiple multivariate linear regression models than the current approach of hypotheses testing. The methods are demonstrated with examples.
BIOMETRICAL JOURNAL
(2022)
Article
Social Sciences, Mathematical Methods
David M. Drukker
Summary: Stata estimation commands produce output tables with multiple tests and confidence intervals. Each test and interval provides valid inference on the null hypothesis for each parameter individually, but using multiple tests or intervals simultaneously exceeds the specified error rate.
Article
Statistics & Probability
Fabian J. E. Telschow, Armin Schwartzman
Summary: The study proposes a method to construct simultaneous confidence bands (SCBs) for functional parameters over arbitrary dimensional compact domains using the Gaussian Kinematic formula of t-processes (tGKF). It shows that a central limit theorem (CLT) for the parameter of interest is sufficient to obtain asymptotically precise covering even if the observations are non-Gaussian processes. Through theoretical work and simulation studies, the tGKF is found to outperform state-of-the-art methods for constructing SCBs with precise covering for small sample sizes, and it is computationally fast even for domains of dimension greater than one. Applications to diffusion tensor imaging (DTI) fibers and spatio-temporal temperature data are discussed.
JOURNAL OF STATISTICAL PLANNING AND INFERENCE
(2022)
Article
Biology
A. Mccloskey
Summary: I propose a new type of confidence interval that allows correct asymptotic inference after model selection without assuming any model is correctly specified. This hybrid confidence interval combines techniques from selective inference and post-selection inference to provide a short interval across various data realizations. The results show that hybrid confidence intervals have correct asymptotic coverage over a broad class of probability distributions with no bound on scaled model parameters. Monte Carlo experiments and an empirical application on diabetes disease progression predictors demonstrate the desirable length and coverage properties of these confidence intervals in small samples.
Article
Mathematics, Applied
M. Burger, A. Hauptmann, T. Helin, N. Hyvonen, J. P. Puska
Summary: This work applies Bayesian experimental design to select optimal projection geometries in (discretized) parallel beam x-ray tomography with Gaussian prior and additive noise. The introduced greedy exhaustive optimization algorithm proceeds sequentially, allowing redefining the region of interest after each projection and considering both A and D-optimality. Two-dimensional numerical experiments demonstrate the functionality of the approach.
Review
Cardiac & Cardiovascular Systems
Xuan Wang, Brian Lee Claggett, Lu Tian, Marcus Vinicius Bolivar Malachias, Marc A. Pfeffer, Lee-Jen Wei
Summary: For personalized or stratified medicine, it is crucial to establish a reliable and efficient prediction model for a clinical outcome of interest. However, commonly used metrics like C statistics do not accurately assess the model's prediction accuracy. This article highlights the importance of finding a clinically interpretable measure that quantifies prediction accuracy for improved model selection and evaluation.
Article
Statistics & Probability
Fabian J. E. Telschow, Samuel Davenport, Armin Schwartzman
Summary: In this study, we construct random processes, called functional delta residuals, which have the same covariance structure as the limit process of the functional delta method, based on the functional central limit theorem (fCLT) and parameter transformation. We explicitly construct these residuals for transformations of moment-based estimators and prove a multiplier bootstrap fCLT for them. The developed construction is applied to estimate the quantiles of the maximum of the limit process and construct asymptotically valid simultaneous confidence bands for the transformed functional parameters.
JOURNAL OF MULTIVARIATE ANALYSIS
(2022)
Review
Chemistry, Analytical
Alexis Barrios-Ulloa, Dora Cama-Pinto, Johan Mardini-Bovea, Jorge Diaz-Martinez, Alejandro Cama-Pinto
Summary: The implementation process of 5G in Colombia has been slow, but there is hope for synergy with IoT to drive development in sectors such as agriculture, tourism, healthcare, environment, and industry. The goal of promoting these technologies is to improve the quality of life for residents and stimulate economic growth.
Article
Social Sciences, Mathematical Methods
Jia Li, Zhipeng Liao, Wenyu Zhou
Summary: In this article, we introduce a command xtnpsreg that implements a uniform nonparametric inference procedure for possibly unbalanced panel datasets with spatiotemporal dependence. We demonstrate its applications in nonparametric estimation, constructing confidence bands, performing specification tests, and estimating functional coefficients in semi-nonparametric models.
Article
Mathematical & Computational Biology
Michael P. Fay, Keith Lumbard
Summary: This article presents a method based on sign test for handling paired data and calculating effect estimates and confidence intervals. It proposes a confidence interval compatible with exact sign test, and supports the conjecture of guaranteed coverage through extensive numerical calculations.
STATISTICS IN MEDICINE
(2021)
Article
Statistics & Probability
Lorenzo Cappello, Oscar Hernan Madrid Padilla, Julia A. Palacios
Summary: We investigate the use of spike-and-slab priors for estimating the number and locations of change points consistently. By leveraging recent findings in the field of variable selection, we demonstrate that an estimator based on spike-and-slab priors achieves the optimal localization rate in the multiple offline change point detection problem. Building upon this estimator, we propose a Bayesian change point detection method that is among the fastest Bayesian methodologies. Empirical analysis shows that our approach outperforms state-of-the-art benchmarks and exhibits robustness to misspecification of error terms.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2023)
Article
Evolutionary Biology
Robert C. Thomson, Jeremy M. Brown
Summary: The growing scale of data sets has provided researchers with a wealth of information for inferring evolutionary history. However, standard approaches to assessing confidence in those inferences are outdated and cannot handle the challenges posed by modern genomic data. New methods are needed to evaluate the confidence and uncertainty in data sets.
SYSTEMATIC BIOLOGY
(2022)
Article
Statistics & Probability
John C. Duchi, Hongseok Namkoong
Summary: A distributionally robust stochastic optimization framework is developed and analyzed, which learns a model providing good performance against perturbations to the data-generating distribution, with a convex formulation for the problem and convergence guarantees. Finite-sample minimax upper and lower bounds are proved, showing that distributional robustness sometimes comes at a cost in convergence rates. Limit theorems for the learned parameters are provided, with fully specified limiting distribution for computing confidence intervals.
ANNALS OF STATISTICS
(2021)
Article
Economics
Zhongjian Lin, Yingyao Hu
Summary: This paper proposes a binary choice model with misclassification and social interactions to address the misclassification problems in social interactions studies. The identification of the conditional choice probability of the latent dependent variable is achieved using repeated measurements and a monotonicity condition. The complete likelihood function is constructed from the two repeated measurements, and a nested pseudo likelihood algorithm is proposed for estimation. Consistency and asymptotic normality results are shown for the proposed estimation method.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Ji Hyung Lee, Yuya Sasaki, Alexis Akira Toda, Yulong Wang
Summary: Administrative data, often presented as tabulated summaries for confidentiality reasons, can be more easily accessed in this form. In this study, the authors propose a novel nonparametric density estimation method based on maximum entropy and demonstrate its consistent results. The method does not require tuning parameters and provides a closed-form density for further analysis. The authors apply this method to estimate the income distribution using tabulated summary data from U.S. tax returns.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Di Wang, Yao Zheng, Guodong Li
Summary: This paper proposes a new modeling framework for modeling and forecasting high-dimensional tensor-valued time series using the autoregression method. By considering a low-rank Tucker decomposition, this method can flexibly capture the underlying low-dimensional tensor dynamics, achieving dimension reduction and multidimensional dynamic factor interpretations. The paper also studies different estimation methods and their non-asymptotic properties under different low-rank settings.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Hongfei Wang, Binghui Liu, Long Feng, Yanyuan Ma
Summary: This study addresses the problem of testing mutual independence of high-dimensional random vectors and proposes a series of high-dimensional rank-based max-sum tests. Through extensive simulations and real data analysis, the superiority of these tests is demonstrated.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Julian Martinez-Iriarte, Gabriel Montes-Rojas, Yixiao Sun
Summary: This paper analyzes the unconditional effects of a general policy intervention, including location-scale shifts and simultaneous shifts. The study finds that failing to account for these shifts may lead to incorrect assessment of the potential policy effects on the outcome variable of interest.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Karim Chalak
Summary: This paper generalizes the Gini-Frisch bounds to accommodate nonparametric heterogeneous effects and provides suitable conditions for their application in nonparametric nonseparable equations.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Koki Fusejima
Summary: In this paper, sufficient conditions for identifying treatment effects on continuous outcomes are established in endogenous and multi-valued discrete treatment settings with unobserved heterogeneity. The monotonicity assumption for multi-valued discrete treatments and instruments is employed, and the identification condition has a clear economic interpretation. Additionally, the local treatment effects in multi-valued treatment settings are identified, and closed-form expressions of the identified treatment effects are derived.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Li Hou, Baisuo Jin, Yuehua Wu
Summary: The spatiotemporal modeling of networks is highly significant in epidemiology and social network analysis. This research proposes a method for estimating the parameters of spatial dynamic panel models effectively and efficiently. The study also introduces a complex orthogonal greedy algorithm for variable selection and incorporates fixed effects into the model. Extensive simulation studies and data examples demonstrate the effectiveness of the proposed method.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Weilun Zhou, Jiti Gao, David Harris, Hsein Kew
Summary: This paper discusses the estimation of a semi-parametric single-index regression model that allows for nonlinear predictive relationships. The presence of cointegrated predictors balances the nonstationarity properties of the predictors with the stationarity properties of asset returns and avoids the curse of dimensionality. In an empirical application, it is found that using cointegrated predictors produces better out-of-sample forecasts.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Eric Beutner, Alexander Heinemann, Stephan Smeekes
Summary: This paper proposes a fixed-design residual bootstrap method for the two-step estimator associated with the conditional Value-at-Risk. The consistency of the bootstrap is proven for a general class of volatility models, and intervals are constructed for the conditional Value-at-Risk. Simulation results show that the reversed-tails bootstrap interval provides accurate coverage compared to the equal-tailed percentile bootstrap interval.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Federico M. Bandi, Davide Pirino, Roberto Reno
Summary: The article examines the staleness of asset prices, including systematic (market-wide) staleness and idiosyncratic (asset specific) staleness. The authors provide a limit theory based on joint asymptotics, utilizing increasingly-frequent observations and an increasing number of assets. They introduce novel structural estimates of systematic and idiosyncratic measures of liquidity obtained solely from transaction prices, and assess the economic signal contained in these estimates using suitable metrics.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Vassilis Hajivassiliou, Frederique Savignac
Summary: The paper develops new methods for establishing coherency and completeness conditions in Static and Dynamic Limited Dependent Variables (LDV) Models. It characterizes the two distinct problems as empty-region incoherency and overlap-region incoherency or incompleteness and shows that the two properties can co-exist. The paper focuses on the class of models that can be Simultaneously Incomplete and Incoherent (SII) and proposes estimation strategies based on Conditional Maximum Likelihood Estimation (CMLE) for simultaneous dynamic LDV models.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Thomas Macurdy, David Glick, Sonam Sherpa, Sriniketh Nagavarapu
Summary: In a successful transition from youth to adulthood, individuals go through a series of roles in school, work, and family formation, culminating in becoming self-sufficient adults. However, some disconnected youth spend significant time outside of any role that leads to adult independence. Understanding the meaning of disconnection, the number of disconnected youth, their characteristics, and how the problem has evolved is essential in assisting these youth. Using comprehensive data, a study examined disconnection spells and found that in the early 2000s, approximately 19% of young men and 25% of young women experienced disconnection before the age of 23. These rates were even higher for certain sub-groups, reaching over 30% for some. The study also revealed that the majority of disconnected youth remained disconnected for more than a year, but once reconnected, they typically stayed connected for at least three years. The findings highlight the need for targeted interventions to prevent lengthy disconnection spells.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Jean-Jacques Forneron
Summary: This paper develops an approach to detect identification failure in moment condition models by introducing a quasi-Jacobian matrix. The quasi-Jacobian matrix is singular when local and/or global identification fails, and equivalent to the usual Jacobian matrix when the model is globally and locally identified. A simple test is introduced to conduct subvector inferences allowing for various levels of identification without prior knowledge about the underlying identification structure.
JOURNAL OF ECONOMETRICS
(2024)
Article
Economics
Zhao Chen, Vivian Xinyi Cheng, Xu Liu
Summary: This paper focuses on the testing problems of high-dimensional quantile regression and proposes a new test statistic based on the quantile regression score function. The paper investigates the limiting distributions of the proposed test statistic and shows through Monte Carlo simulations and empirical analysis that the proposed method outperforms existing methods in terms of controlling error rate and power.
JOURNAL OF ECONOMETRICS
(2024)
