Into thin air

Using a quantile regression approach to explore the relationship between R&D and innovation.

B Ebersberger, Orietta Marsili, T. Reichstein, A Salter

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Applying quantile regression to 760 Finnish firms, we show that the relationship between R&D and firm performance is less straight forward than so far assumed. OLS regression analysis fails to capture the effect of R&D expenditure at different locations on the performance distribution. We reveal that R&D matters, especially on the medium quantiles, while regressing against the upper quantiles of the economic gains from innovation distribution exhibit decreasing returns scale in R&D. Our results confirm that Gaussian statistics fail to capture the most interesting part of the distribution – namely the extreme observations
Original languageEnglish
Pages (from-to)95-102
Number of pages8
JournalInternational Review of Applied Economics
Volume24
Issue number1
Early online date27 Jan 2010
DOIs
Publication statusPublished - Jan 2010

Fingerprint

Quantile regression
Air
Innovation
Quantile
Regression analysis
Finnish firms
Economics
Statistics
Firm performance
Expenditure

Cite this

Into thin air : Using a quantile regression approach to explore the relationship between R&D and innovation. / Ebersberger, B; Marsili, Orietta; Reichstein, T. ; Salter, A.

In: International Review of Applied Economics, Vol. 24, No. 1, 01.2010, p. 95-102.

Research output: Contribution to journalArticle

@article{e47c4c54ec4748b5a0a25bb39926e521,
title = "Into thin air: Using a quantile regression approach to explore the relationship between R&D and innovation.",
abstract = "Applying quantile regression to 760 Finnish firms, we show that the relationship between R&D and firm performance is less straight forward than so far assumed. OLS regression analysis fails to capture the effect of R&D expenditure at different locations on the performance distribution. We reveal that R&D matters, especially on the medium quantiles, while regressing against the upper quantiles of the economic gains from innovation distribution exhibit decreasing returns scale in R&D. Our results confirm that Gaussian statistics fail to capture the most interesting part of the distribution – namely the extreme observations",
author = "B Ebersberger and Orietta Marsili and T. Reichstein and A Salter",
year = "2010",
month = "1",
doi = "10.1080/02692170903424448",
language = "English",
volume = "24",
pages = "95--102",
journal = "International Review of Applied Economics",
issn = "0269-2171",
publisher = "Routledge",
number = "1",

}

TY - JOUR

T1 - Into thin air

T2 - Using a quantile regression approach to explore the relationship between R&D and innovation.

AU - Ebersberger, B

AU - Marsili, Orietta

AU - Reichstein, T.

AU - Salter, A

PY - 2010/1

Y1 - 2010/1

N2 - Applying quantile regression to 760 Finnish firms, we show that the relationship between R&D and firm performance is less straight forward than so far assumed. OLS regression analysis fails to capture the effect of R&D expenditure at different locations on the performance distribution. We reveal that R&D matters, especially on the medium quantiles, while regressing against the upper quantiles of the economic gains from innovation distribution exhibit decreasing returns scale in R&D. Our results confirm that Gaussian statistics fail to capture the most interesting part of the distribution – namely the extreme observations

AB - Applying quantile regression to 760 Finnish firms, we show that the relationship between R&D and firm performance is less straight forward than so far assumed. OLS regression analysis fails to capture the effect of R&D expenditure at different locations on the performance distribution. We reveal that R&D matters, especially on the medium quantiles, while regressing against the upper quantiles of the economic gains from innovation distribution exhibit decreasing returns scale in R&D. Our results confirm that Gaussian statistics fail to capture the most interesting part of the distribution – namely the extreme observations

UR - http://www.scopus.com/inward/record.url?scp=75849116312&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1080/02692170903424448

U2 - 10.1080/02692170903424448

DO - 10.1080/02692170903424448

M3 - Article

VL - 24

SP - 95

EP - 102

JO - International Review of Applied Economics

JF - International Review of Applied Economics

SN - 0269-2171

IS - 1

ER -