Weighted classical variogram estimation for data with clustering

Cavan Reilly, Andrew Gelman

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


The classical variogram estimate is convenient but can be unacceptable variable. Improved estimators are possible, especially when the locations of the available data are highly clustered. Using a simple theoretical example, we demonstrate that weighting can dramatically increase the efficiency of classical variogram estimates from clustered data. We give expressions for the weights that lead to minimal variance estimators and indicate some obstacles to the use of these weights, We then introduce a simple iterative weighting scheme intended to approximate optimal weighting. We apply the new weighting to the example that motivated this research-estimating the variogram of home radon levels-and demonstrate its performance in a simulation study.

Original languageEnglish (US)
Pages (from-to)184-194
Number of pages11
Issue number2
StatePublished - May 2007

Bibliographical note

Funding Information:
We thank the National Science Foundation for grants SBR-9708424, SES-99-87748, and Young Investigator Award DMS-97-96129. We thank Phillip Price for discussions and Jon Miles from the U.K. National Radiation Protection Board for the data.


  • Clustered data
  • Spatial statistics
  • Variogram
  • Weighting


Dive into the research topics of 'Weighted classical variogram estimation for data with clustering'. Together they form a unique fingerprint.

Cite this