Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Kriging with nonparametric variance function estimation.

J D Opsomer1, D Ruppert, M P Wand

  • 1Department of Statistics, Iowa State University, Ames, USA. jopsomer@iastate.edu

Biometrics
|April 21, 2001
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Fast and Accurate Binary Response Mixed Model Analysis Via Expectation Propagation.

Journal of the American Statistical Association·2022
Same author

Streamlined variational inference for higher level group-specific curve models.

Statistical modelling·2022
Same author

Effective sizes and time to migration-drift equilibrium in geographically subdivided populations.

Theoretical population biology·2016
Same author

Metapopulation effective size and conservation genetic goals for the Fennoscandian wolf (Canis lupus) population.

Heredity·2016
Same author

Latent factor regression models for grouped outcomes.

Biometrics·2013
Same author

Marginal longitudinal semiparametric regression via penalized splines.

Statistics & probability letters·2010
Same journal

Fast penalized generalized estimating equations for large longitudinal functional datasets.

Biometrics·2026
Same journal

Causally-interpretable random-effects meta-analysis.

Biometrics·2026
Same journal

Statistical inference for mean function of partially observed functional time series.

Biometrics·2026
Same journal

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026
Same journal

Finite mixtures of linear quantile regressions with concomitant variables: a solution to endogeneity in longitudinal data modeling.

Biometrics·2026
Same journal

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
See all related articles

This study introduces a novel regression method to accurately model spatial data with varying variance. The approach corrects for heteroskedasticity, improving correlation estimates for environmental applications.

Area of Science:

  • Environmental Science
  • Statistical Modeling
  • Geostatistics

Background:

  • Ignoring non-constant variance (heteroskedasticity) in regression can bias spatial correlation estimates.
  • Accurate modeling of spatial data requires addressing both correlation and variance structures.
  • Previous methods often oversimplify or ignore heteroskedasticity, leading to inaccurate variogram fitting.

Purpose of the Study:

  • To develop and demonstrate a robust method for fitting regression models to data with spatial correlation and heteroskedasticity.
  • To eliminate bias in estimated correlation functions caused by unmodeled variance.
  • To improve the accuracy of spatial statistical models in environmental applications.

Main Methods:

  • A combined parametric and nonparametric regression approach is used for iterative model fitting.

Related Experiment Videos

  • The model incorporates three components: a linear mean function (generalized least squares), a local and spatial variance function (local linear regression), and a parametric variogram for spatial correlation.
  • Data standardization by estimated standard deviations corrects for heteroskedasticity before variogram estimation.

    • Main Results:

    • The proposed method effectively models both spatial correlation and heteroskedasticity.
    • Bias in correlation function estimation is eliminated by accounting for non-constant variance.
    • The new model demonstrates a superior fit to a large dataset of agricultural nitrogen runoff compared to models that ignore heteroskedasticity.

    Conclusions:

    • The developed regression method provides a more accurate analysis of spatially correlated data with heteroskedasticity.
    • Accounting for heteroskedasticity is crucial for reliable geostatistical modeling and environmental predictions.
    • This approach offers significant improvements for analyzing complex environmental datasets, such as nitrogen runoff predictions.