Advanced

Stock Volatility In Various Financial Institutions: Case Study of Germany with GARCH Estimations

Sandström, Paul LU (2011) NEKM01 20111
Department of Economics
Abstract
This study will try to determine the volatility of the stock returns of various financial institutions in Germany during the time period 1998-2007. The reasoning behind targeting Germany is that it is commonly known as one of the most stable and reliable economies in Europe, where Germany has been chosen as a representative case. The study employs a multifactor model, which incorporates interest rate (long and short being estimated separately) along with the exchange rate index EER-40. The estimation methods for determining the stock volatility are the GARCH-M and EGARCH methods. The study concludes that there is a great insignificance in the mean equation, which can be interpreted as showing one of several things: that the model is bad,... (More)
This study will try to determine the volatility of the stock returns of various financial institutions in Germany during the time period 1998-2007. The reasoning behind targeting Germany is that it is commonly known as one of the most stable and reliable economies in Europe, where Germany has been chosen as a representative case. The study employs a multifactor model, which incorporates interest rate (long and short being estimated separately) along with the exchange rate index EER-40. The estimation methods for determining the stock volatility are the GARCH-M and EGARCH methods. The study concludes that there is a great insignificance in the mean equation, which can be interpreted as showing one of several things: that the model is bad, that data is corrupt, or that there is an insignificant relationship between the explanatory variables and the depending variables. Although the study does often find significant GARCH-M and EGARCH coefficients, which tends to confirm (ignoring the insignificance of the mean equation) the common financial notion that
the analysis of stock returns is best done under the assumption of conditional variance, meaning that the variance (volatility, risk) varies over time. (Less)
Please use this url to cite or link to this publication:
author
Sandström, Paul LU
supervisor
organization
course
NEKM01 20111
year
type
H1 - Master's Degree (One Year)
subject
keywords
Stock Volatility, Financial Institutions, Germany, GARCH-M, EGARCH, Conditional Variance
language
English
id
2152623
date added to LUP
2011-09-27 13:17:04
date last changed
2011-09-27 13:17:04
@misc{2152623,
  abstract     = {This study will try to determine the volatility of the stock returns of various financial institutions in Germany during the time period 1998-2007. The reasoning behind targeting Germany is that it is commonly known as one of the most stable and reliable economies in Europe, where Germany has been chosen as a representative case. The study employs a multifactor model, which incorporates interest rate (long and short being estimated separately) along with the exchange rate index EER-40. The estimation methods for determining the stock volatility are the GARCH-M and EGARCH methods. The study concludes that there is a great insignificance in the mean equation, which can be interpreted as showing one of several things: that the model is bad, that data is corrupt, or that there is an insignificant relationship between the explanatory variables and the depending variables. Although the study does often find significant GARCH-M and EGARCH coefficients, which tends to confirm (ignoring the insignificance of the mean equation) the common financial notion that
the analysis of stock returns is best done under the assumption of conditional variance, meaning that the variance (volatility, risk) varies over time.},
  author       = {Sandström, Paul},
  keyword      = {Stock Volatility,Financial Institutions,Germany,GARCH-M,EGARCH,Conditional Variance},
  language     = {eng},
  note         = {Student Paper},
  title        = {Stock Volatility In Various Financial Institutions: Case Study of Germany with GARCH Estimations},
  year         = {2011},
}