Practical Proposals for Specifying k-Nearest Neighbours Weights Matrices

Research output: Contribution to journalArticleScientificpeer-review

7 Citations (Scopus)

Abstract

In this article we introduce and evaluate testing procedures for specifying the number k of nearest neighbours in the weights matrix of a spatial econometric model. An increasing and a decreasing neighbours testing procedure are suggested. Kelejian's J-test for non-nested spatial models is used in the testing procedures. The testing procedures give formal justification for the choice of k, something which has been lacking in the classical spatial econometric literature. Simulations show that the testing procedures can be used in large samples to determine k. An empirical example involving house price data is provided.
Original languageEnglish
Article number2
Peer-reviewed scientific journalSpatial Economic Analysis
Volume9
Issue number3
Pages (from-to)260-283
Number of pages24
DOIs
Publication statusPublished - 30.08.2014
MoE publication typeA1 Journal article - refereed

Keywords

  • 112 Statistics and probability
  • Econometrics
  • Model specification
  • Spatial J-test
  • Weights matrix
  • 511 Economics
  • Housing
  • Urban Economics
  • KOTA2014

Fingerprint Dive into the research topics of 'Practical Proposals for Specifying k-Nearest Neighbours Weights Matrices'. Together they form a unique fingerprint.

  • Projects

    SPATIAL ECONOMETRICS AND HOUSE PRICE MODELS

    Gerkman, L., Ahlgren, N. & Rosenqvist, G.

    07.01.200531.12.2010

    Project: Externally funded project

    Cite this