A5075778250- Statistical Methods and Inference
- Statistical Methods and Bayesian Inference
- Bayesian Methods and Mixture Models
- Advanced Statistical Methods and Models
- Financial Risk and Volatility Modeling
- Agricultural risk and resilience
- Statistical Distribution Estimation and Applications
- Soil Geostatistics and Mapping
- Spatial and Panel Data Analysis
- Economic and Environmental Valuation
- Climate variability and models
- Economics of Agriculture and Food Markets
- Agricultural Economics and Practices
- Hydrology and Drought Analysis
- Statistical Methods in Clinical Trials
- Tropical and Extratropical Cyclones Research
- Stellar, planetary, and galactic studies
- Genetic and phenotypic traits in livestock
- Meteorological Phenomena and Simulations
- Agricultural Economics and Policy
- Crystallization and Solubility Studies
- Machine Learning and Data Classification
- X-ray Diffraction in Crystallography
- Spectroscopy and Chemometric Analyses
- Probabilistic and Robust Engineering Design
North Carolina State University
2016-2025
North Central State College
2010-2025
Indian Institute of Technology Bombay
1995-2024
India Meteorological Department
1964-2021
Norfolk State University
2019
Swiss Federal Institute for Forest, Snow and Landscape Research
2018
Statistical and Applied Mathematical Sciences Institute
2016-2017
Bose Institute
2012
Jagannath University
2010
Jadavpur University
2010
Journal Article Model choice: A minimum posterior predictive loss approach Get access ALAN E. GELFAND, GELFAND Department of Statistics, University ConnecticutStorrs, Connecticut 06269-3120, U.S.A.alan@stat.uconn.edu Search for other works by this author on: Oxford Academic Google Scholar SUJIT K. GHOSH North Carolina State UniversityRaleigh, Carolina, 27695-8203, U.S.A.sghosh@stat.ncsu.edu Biometrika, Volume 85, Issue 1, March 1998, Pages 1–11, https://doi.org/10.1093/biomet/85.1.1...
It is of great practical interest to simultaneously identify the important predictors that correspond both fixed and random effects components in a linear mixed-effects (LME) model. Typical approaches perform selection separately on each effect components. However, changing structure one set can lead different choices variables for other effects. We propose simultaneous factors an LME model using modified Cholesky decomposition. Our method based penalized joint log likelihood with adaptive...
One of the standard problems in statistics consists determining relationship between a response variable and single predictor through regression function. Background scientific knowledge is often available that suggests function should have certain shape (e.g. monotonically increasing or concave) but not necessarily specific parametric form. Bernstein polynomials been used to impose restrictions on functions. The are known provide smooth estimate over equidistant knots. this paper due their...
Due to the heterogeneity of randomized controlled trial (RCT) and external target populations, estimated treatment effect from RCT is not directly applicable population. For example, patient characteristics ACTG 175 HIV are significantly different that three populations interest: US early-stage patients, Thailand southern Ethiopia patients. This paper considers several methods transport beyond Most focus on continuous binary outcomes; contrary, we derive discuss for survival outcomes: an...
Abstract A fundamental endeavor in exoplanetary research is to characterize the bulk compositions of planets via measurements their masses and radii. With future sample sizes hundreds come from TESS PLATO, we develop a statistical method that can flexibly yet robustly these empirically, exoplanet M – R relation. Although relation has been explored many prior works, they mostly use power-law model, with assumptions are not flexible enough capture important features current diagrams. To...
Motivated by an imaging study, this paper develops a nonparametric testing procedure for the null hypothesis that two samples of curves observed at discrete grids and with noise have same underlying distribution. The objective is to formally compare white matter tract profiles between healthy individuals multiple sclerosis patients, as assessed conventional diffusion tensor measures. We propose decompose using functional principal component analysis mixture process, which we refer marginal...
Ensemble learning (EL) has become an essential technique in machine that can significantly enhance the predictive performance of basic models, but it also comes with increased cost computation. The primary goal proposed approach is to present a general integrative framework allows for applying active (AL) which makes use only limited budget by selecting optimal instances achieve comparable within context ensemble learning. based on two distinct approaches: (i) AL implemented following full...
ABSTRACT Consider multi‐state series and parallel systems consisting of independent components each. It is assumed that (i) each component both the take values in set , (ii) system start out state 2, perfect state, they make transition to 1, depending upon configuration, and, eventually, enters 0, failed state. This nature leads scenarios under which makes from 2 eventually 0. The joint probability function for times spent 1 obtained based on these systems. interesting note by merely...
Abstract The study encapsulates the investigation into spherical distributional characteristics of parameters relevant to Gamma-Ray Bursts (GRBs), mainly focusing on their Galactic coordinates. utilized a mixture von Mises Fisher distributions model spatial distribution GRBs in both BATSE and FERMI catalogs. Optimal numbers components were determined for different subsets GRBs, including Long Short GRBs. For catalog, it turns out that two provides good fit whole data set long short On other...
Beetles are crucial ecosystem components, serving as pollinators, decomposers, and predators. In 2023, a faunistic survey was conducted across 14 locations in Anjaw District, Arunachal Pradesh, India, region of rich biodiversity. Coleopteran specimens were collected using light traps, hand-picking D-type water nets. Identification the revealed 70 beetle species belonging to 49 genera 12 families. Among identified species, 17 represent new records for significantly enhancing our understanding...
Forecasting revenues by aggregating analyst forecasts is a fundamental problem in financial research and practice. A key objective this context to improve the accuracy of forecast optimizing two performance metrics: hit rate, which measures proportion correctly classified revenue surprise signs, win quantifies individual that outperform an equally weighted consensus benchmark. While researchers have extensively studied combination techniques, critical gaps remain: (i) estimation optimal...
Abstract Astronomers often deal with data where the covariates and dependent variable are measured heteroscedastic non-Gaussian error. For instance, while TESS Kepler datasets provide a wealth of information, addressing challenges measurement errors systematic biases is critical for extracting reliable scientific insights improving machine learning models’ performance. Although techniques have been developed estimating regression parameters these data, few exist to construct prediction...
Summary. Interval‐censored data occur in survival analysis when the time of each patient is only known to be within an interval and these censoring intervals differ from patient. For such data, we present some Bayesian discretized semiparametric models, incorporating proportional nonproportional hazards structures, along with associated statistical analyses tools for model selection using sampling‐based methods. The scope methodologies illustrated through a reanalysis breast cancer set...
This article focuses on the location, time, and spatio-temporal components associated with suitably aggregated data to improve prediction of individual asset values. Such effects are introduced in context hierarchical models, which we find more natural than attempting model covariance structure. Indeed, our cross-sectional database, a sample 7,936 transactions for 49 subdivisions over 10-year period Baton Rouge, Louisiana, precludes modeling. A wide range models arises, each fitted using...
A new approach for developing multimodel streamflow forecasts is presented. The methodology combines from individual models by evaluating their skill, represented rank probability score (RPS), contingent on the predictor state. Using average RPS estimated over chosen neighbors in state space, assigns higher weights a model that has better predictability under similar conditions. We assess performance of proposed algorithm Falls Lake Reservoir Neuse River Basin, North Carolina (NC), combining...
Model choice is one of the most crucial aspect in any statistical data analysis. It well known that models are just an approximation to true generating process but among such model approximations it our goal select "best" one. Researchers typically consider a finite number plausible applications and related inference depends on chosen model. Hence comparison required identify several candidate models. This article considers problem selection for spatial data. The issue has been addressed...
This paper presents a comprehensive analysis of students' activity characteristics and travel patterns based on the 2001 North Carolina State University Student Activity Travel Survey. Results show that undergraduate students on-campus residents are engaged in more activities than graduate off-campus students. Graduate likely to engage class work afternoon morning. There is no statistically significant difference between student groups terms proportion involved certain at hour day. Instead,...