Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

The Impact of ESG performance on Idiosyncratic Volatility

Pedersen, Sebastian Pickering LU (2024) DABN01 20241
Department of Economics
Department of Statistics
Abstract
Environment, social and governance (ESG) ratings are of interest for both investors and researchers for its effect on stock performance. Previous literature has found mixed results with regard to this relationship and few papers are concerned with the volatility of ESG stocks. This paper explores the relationship between ESG scores and idiosyncratic risk. Using monthly news-based, AI generated ESG scores, I apply portfolio sorting of stocks on the S&P1500 according to ESG and perform firm-level factor regressions using six common market factors to adjust for systemic risk, followed by implementing a GARCH-MIDAS equation for modelling the conditional variance of the idiosyncratic risk. I compare high and low aggregate ESG, as well as... (More)
Environment, social and governance (ESG) ratings are of interest for both investors and researchers for its effect on stock performance. Previous literature has found mixed results with regard to this relationship and few papers are concerned with the volatility of ESG stocks. This paper explores the relationship between ESG scores and idiosyncratic risk. Using monthly news-based, AI generated ESG scores, I apply portfolio sorting of stocks on the S&P1500 according to ESG and perform firm-level factor regressions using six common market factors to adjust for systemic risk, followed by implementing a GARCH-MIDAS equation for modelling the conditional variance of the idiosyncratic risk. I compare high and low aggregate ESG, as well as portfolios sorted on individual environmental, social and governance scores. The findings show no major differences in conditional variance between high and low ESG portfolios, though small differences in short-term volatility persistence and asymmetric effects are observed. I expand the model to include ESG (and individual E, S, G) scores in the long- term component of GARCH-MIDAS and find ESG scores to be weakly significant for the portfolios sorted on environmental score. Inclusion of ESG is shown to have an overall model improving effect. Further research may benefit from using (AI-based) ESG scores in modelling idiosyncratic volatility in other types of models. (Less)
Please use this url to cite or link to this publication:
author
Pedersen, Sebastian Pickering LU
supervisor
organization
course
DABN01 20241
year
type
H1 - Master's Degree (One Year)
subject
keywords
ESG, idiosyncratic volatility, GARCH-MIDAS
language
English
id
9156945
date added to LUP
2024-09-24 08:36:05
date last changed
2024-09-24 08:36:05
@misc{9156945,
  abstract     = {{Environment, social and governance (ESG) ratings are of interest for both investors and researchers for its effect on stock performance. Previous literature has found mixed results with regard to this relationship and few papers are concerned with the volatility of ESG stocks. This paper explores the relationship between ESG scores and idiosyncratic risk. Using monthly news-based, AI generated ESG scores, I apply portfolio sorting of stocks on the S&P1500 according to ESG and perform firm-level factor regressions using six common market factors to adjust for systemic risk, followed by implementing a GARCH-MIDAS equation for modelling the conditional variance of the idiosyncratic risk. I compare high and low aggregate ESG, as well as portfolios sorted on individual environmental, social and governance scores. The findings show no major differences in conditional variance between high and low ESG portfolios, though small differences in short-term volatility persistence and asymmetric effects are observed. I expand the model to include ESG (and individual E, S, G) scores in the long- term component of GARCH-MIDAS and find ESG scores to be weakly significant for the portfolios sorted on environmental score. Inclusion of ESG is shown to have an overall model improving effect. Further research may benefit from using (AI-based) ESG scores in modelling idiosyncratic volatility in other types of models.}},
  author       = {{Pedersen, Sebastian Pickering}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{The Impact of ESG performance on Idiosyncratic Volatility}},
  year         = {{2024}},
}