Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Residual Spatial Correlation in Two-Way Error Panel Data Models

Flöhr, Adam LU (2018) STAN40 20182
Department of Statistics
Abstract
This thesis examines the spatial autocorrelation in residuals of two-way error panel data models. Three types of models are examined: the standard linear panel data model, the dynamic panel data model, and the spatial lag panel data model. A known theoretical result for the linear model, that the within estimator applied to independent observations results in a spatial correlation in the residuals which is proportional to the inverse of the number of observed individual units, is supported in a Monte Carlo study. Similar Monte Carlo results are shown for the dynamic and spatial models. The Monte Carlo study shows the effect of residual correlation on the maximum likelihood estimation of the spatial model and on residual tests for spatial... (More)
This thesis examines the spatial autocorrelation in residuals of two-way error panel data models. Three types of models are examined: the standard linear panel data model, the dynamic panel data model, and the spatial lag panel data model. A known theoretical result for the linear model, that the within estimator applied to independent observations results in a spatial correlation in the residuals which is proportional to the inverse of the number of observed individual units, is supported in a Monte Carlo study. Similar Monte Carlo results are shown for the dynamic and spatial models. The Monte Carlo study shows the effect of residual correlation on the maximum likelihood estimation of the spatial model and on residual tests for spatial correlation. Randomization tests for spatial correlation are formulated and their properties are evaluated. The results suggest that a randomization test for local spatial autocorrelation is the most suitable test for samples large in number of individual regions and small in number of time points.

The model estimation methods and tests for residual spatial autocorrelation are applied in an empirical examination of regional unemployment in Southern Sweden. The study shows that the spatial lag model is sensitive to choice of spatial weight matrix and indicates the presence of a spatial structure which is not fully captured by the applied models and weight matrices. (Less)
Abstract (Swedish)
Denna uppsats behandlar förekomsten av rumslig autokorrelation i residualer till paneldatamodeller med tvåvägsfel. Tre modelltyper undersöks: den linjära paneldatamodellen, en dynamisk paneldatamodell och en spatial paneldatamodell. Ett känt resultat för den linjära modellen, att minsta kvadrat-skattaren tillämpad på oberoende observationer resulterar i en rumslig korrelation i residualserien vars storlek är proportionell till inversen av antalet observerade individer, undersöks i en Monte Carlo-studie. Liknande simuleringsresultat ges för de dynamiska och rumsliga modellerna. Monte Carlo-studien visar effekten av residualkorrelation på maximum likelihood-skattningen av den rumsliga modellen och på hypotestester för rumslig korrelation.... (More)
Denna uppsats behandlar förekomsten av rumslig autokorrelation i residualer till paneldatamodeller med tvåvägsfel. Tre modelltyper undersöks: den linjära paneldatamodellen, en dynamisk paneldatamodell och en spatial paneldatamodell. Ett känt resultat för den linjära modellen, att minsta kvadrat-skattaren tillämpad på oberoende observationer resulterar i en rumslig korrelation i residualserien vars storlek är proportionell till inversen av antalet observerade individer, undersöks i en Monte Carlo-studie. Liknande simuleringsresultat ges för de dynamiska och rumsliga modellerna. Monte Carlo-studien visar effekten av residualkorrelation på maximum likelihood-skattningen av den rumsliga modellen och på hypotestester för rumslig korrelation. Randomiseringstest för rumslig korrelation formuleras och testas. Resultaten pekar mot att ett randomiseringstest för lokal rumslig autokorrelation är det lämpligaste testet för stickprov över ett stort antal regioner och ett lågt antal tidpunkter.

De tre typerna av paneldatamodeller skattas i en empirisk undersökning av regional arbetslöshet i södra Sverige (Skåne). Tester för rumslig autokorrelation tillämpas på modellernas residualer. Studien visar att den rumsliga paneldatamodellen är känslig för val av viktmatris och pekar på förekomsten av en rumslig struktur som inte helt fångas av de tillämpade modellerna och viktmatriserna. (Less)
Please use this url to cite or link to this publication:
author
Flöhr, Adam LU
supervisor
organization
course
STAN40 20182
year
type
H1 - Master's Degree (One Year)
subject
keywords
Panel data models, Spatial statistics, Spatial autocorrelation
language
English
id
8959251
date added to LUP
2018-10-08 09:43:19
date last changed
2018-10-08 09:43:19
@misc{8959251,
  abstract     = {{This thesis examines the spatial autocorrelation in residuals of two-way error panel data models. Three types of models are examined: the standard linear panel data model, the dynamic panel data model, and the spatial lag panel data model. A known theoretical result for the linear model, that the within estimator applied to independent observations results in a spatial correlation in the residuals which is proportional to the inverse of the number of observed individual units, is supported in a Monte Carlo study. Similar Monte Carlo results are shown for the dynamic and spatial models. The Monte Carlo study shows the effect of residual correlation on the maximum likelihood estimation of the spatial model and on residual tests for spatial correlation. Randomization tests for spatial correlation are formulated and their properties are evaluated. The results suggest that a randomization test for local spatial autocorrelation is the most suitable test for samples large in number of individual regions and small in number of time points.

The model estimation methods and tests for residual spatial autocorrelation are applied in an empirical examination of regional unemployment in Southern Sweden. The study shows that the spatial lag model is sensitive to choice of spatial weight matrix and indicates the presence of a spatial structure which is not fully captured by the applied models and weight matrices.}},
  author       = {{Flöhr, Adam}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Residual Spatial Correlation in Two-Way Error Panel Data Models}},
  year         = {{2018}},
}