I need to perform a cointegration analysis between several market indexes. Should I use the raw data or the logarithm of the data? I've noticed that in most research the log is used but why?
Thank you
Co-integration
Moderators: EViews Gareth, EViews Moderator
Re: Co-integration
We usually use logarithm in time series data in order eliminate the non-stationary of the variance and to reduce the sum squared resid.
Return to “Econometric Discussions”
Who is online
Users browsing this forum: No registered users and 2 guests
