Exploring the spatially varying innovation capacity of the US counties in the framework of Griliches’ knowledge production function: a mixed GWR approach

Dongwoo Kang, Sandy Dall’erba

Research output: Research - peer-reviewArticle

  • 2 Citations

Abstract

Griliches’ knowledge production function has been increasingly adopted at the regional level where location-specific conditions drive the spatial differences in knowledge creation dynamics. However, the large majority of such studies rely on a traditional regression approach that assumes spatially homogenous marginal effects of knowledge input factors. This paper extends the authors’ previous work (Kang and Dall’erba in Int Reg Sci Rev, 2015. doi:10.1177/0160017615572888) to investigate the spatial heterogeneity in the marginal effects by using nonparametric local modeling approaches such as geographically weighted regression (GWR) and mixed GWR with two distinct samples of the US Metropolitan Statistical Area (MSA) and non-MSA counties. The results indicate a high degree of spatial heterogeneity in the marginal effects of the knowledge input variables, more specifically for the local and distant spillovers of private knowledge measured across MSA counties. On the other hand, local academic knowledge spillovers are found to display spatially homogenous elasticities in both MSA and non-MSA counties. Our results highlight the strengths and weaknesses of each county’s innovation capacity and suggest policy implications for regional innovation strategies.

LanguageEnglish (US)
Pages125-157
Number of pages33
JournalJournal of Geographical Systems
Volume18
Issue number2
DOIs
StatePublished - Apr 1 2016
Externally publishedYes

Fingerprint

innovation capacity
production function
knowledge production
regression
innovation
county
effect
elasticity
modeling
policy
innovation strategy
knowledge

Keywords

  • Knowledge production function
  • Knowledge spillovers
  • Mixed geographically weighted regression (MGWR)
  • Spatial heterogeneity

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Earth-Surface Processes

Cite this

@article{425cc9ea53644ea7bc255dfd592da201,
title = "Exploring the spatially varying innovation capacity of the US counties in the framework of Griliches’ knowledge production function: a mixed GWR approach",
abstract = "Griliches’ knowledge production function has been increasingly adopted at the regional level where location-specific conditions drive the spatial differences in knowledge creation dynamics. However, the large majority of such studies rely on a traditional regression approach that assumes spatially homogenous marginal effects of knowledge input factors. This paper extends the authors’ previous work (Kang and Dall’erba in Int Reg Sci Rev, 2015. doi:10.1177/0160017615572888) to investigate the spatial heterogeneity in the marginal effects by using nonparametric local modeling approaches such as geographically weighted regression (GWR) and mixed GWR with two distinct samples of the US Metropolitan Statistical Area (MSA) and non-MSA counties. The results indicate a high degree of spatial heterogeneity in the marginal effects of the knowledge input variables, more specifically for the local and distant spillovers of private knowledge measured across MSA counties. On the other hand, local academic knowledge spillovers are found to display spatially homogenous elasticities in both MSA and non-MSA counties. Our results highlight the strengths and weaknesses of each county’s innovation capacity and suggest policy implications for regional innovation strategies.",
keywords = "Knowledge production function, Knowledge spillovers, Mixed geographically weighted regression (MGWR), Spatial heterogeneity",
author = "Dongwoo Kang and Sandy Dall’erba",
year = "2016",
month = "4",
doi = "10.1007/s10109-016-0228-8",
volume = "18",
pages = "125--157",
journal = "Journal of Geographical Systems",
issn = "1435-5930",
publisher = "Springer Verlag",
number = "2",

}

TY - JOUR

T1 - Exploring the spatially varying innovation capacity of the US counties in the framework of Griliches’ knowledge production function

T2 - Journal of Geographical Systems

AU - Kang,Dongwoo

AU - Dall’erba,Sandy

PY - 2016/4/1

Y1 - 2016/4/1

N2 - Griliches’ knowledge production function has been increasingly adopted at the regional level where location-specific conditions drive the spatial differences in knowledge creation dynamics. However, the large majority of such studies rely on a traditional regression approach that assumes spatially homogenous marginal effects of knowledge input factors. This paper extends the authors’ previous work (Kang and Dall’erba in Int Reg Sci Rev, 2015. doi:10.1177/0160017615572888) to investigate the spatial heterogeneity in the marginal effects by using nonparametric local modeling approaches such as geographically weighted regression (GWR) and mixed GWR with two distinct samples of the US Metropolitan Statistical Area (MSA) and non-MSA counties. The results indicate a high degree of spatial heterogeneity in the marginal effects of the knowledge input variables, more specifically for the local and distant spillovers of private knowledge measured across MSA counties. On the other hand, local academic knowledge spillovers are found to display spatially homogenous elasticities in both MSA and non-MSA counties. Our results highlight the strengths and weaknesses of each county’s innovation capacity and suggest policy implications for regional innovation strategies.

AB - Griliches’ knowledge production function has been increasingly adopted at the regional level where location-specific conditions drive the spatial differences in knowledge creation dynamics. However, the large majority of such studies rely on a traditional regression approach that assumes spatially homogenous marginal effects of knowledge input factors. This paper extends the authors’ previous work (Kang and Dall’erba in Int Reg Sci Rev, 2015. doi:10.1177/0160017615572888) to investigate the spatial heterogeneity in the marginal effects by using nonparametric local modeling approaches such as geographically weighted regression (GWR) and mixed GWR with two distinct samples of the US Metropolitan Statistical Area (MSA) and non-MSA counties. The results indicate a high degree of spatial heterogeneity in the marginal effects of the knowledge input variables, more specifically for the local and distant spillovers of private knowledge measured across MSA counties. On the other hand, local academic knowledge spillovers are found to display spatially homogenous elasticities in both MSA and non-MSA counties. Our results highlight the strengths and weaknesses of each county’s innovation capacity and suggest policy implications for regional innovation strategies.

KW - Knowledge production function

KW - Knowledge spillovers

KW - Mixed geographically weighted regression (MGWR)

KW - Spatial heterogeneity

UR - http://www.scopus.com/inward/record.url?scp=84961655007&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961655007&partnerID=8YFLogxK

U2 - 10.1007/s10109-016-0228-8

DO - 10.1007/s10109-016-0228-8

M3 - Article

VL - 18

SP - 125

EP - 157

JO - Journal of Geographical Systems

JF - Journal of Geographical Systems

SN - 1435-5930

IS - 2

ER -