On the effective geographic sample size

Jonathan Acosta, Ronny Vallejos, Daniel Griffth

Journal of Statistical Computation and Simulation · 2018 · 13 citations · 20 references

Concepts

Abstract

Griffith [Effective geographic sample size in the presence of spatial autocorrelation. Ann Assoc Amer Geogr. 2005;95:740–760] suggested a formula to compute the effective sample size, say n∗, for georeferenced data. In this article, we provide mathematical support that enhances the use of this definition in practice. We prove that n∗∈[1,n] and that n∗ is increasing in n. We also prove the asymptotic normality of the maximum likelihood estimate of n∗ for an increasing domain sampling framework. Asymptotic normality leads to an approximate hypothesis testing that establishes whether redundant information exists in a sample.

References

20