Hi, as i suppose to know in a stationary GARCH(1,1) model the sum of alpha and beta has to be smaller than 1. But if i use the garchfit() function from the package fGarch for my timeseries the sum is bigger than 1. The adf.test tells me a p-value smaller than 0.01 instead. What does this mean for me? Can i trust in the coefficients in this case? mfg user84 -- View this message in context: http://r.789695.n4.nabble.com/alpha-1-beta-1-1-in-GARCH-1-1-tp4088342p4088342.html Sent from the R help mailing list archive at Nabble.com.
alpha_1 + beta_1 >1 in GARCH(1,1)
2 messages · user84, Patrick Burns
This would have been a more appropriate question on r-sig-finance. The short answer is: no, you can't trust the coefficients. You don't say how much data you have, but this situation is common when you don't have much data (meaning fewer than 2000 daily observations). The sum of those two parameters is saying how fast shocks dissipate (in the variance). If it looks like there is a trend in volatility over the in-sample period, then a reasonable answer given that information is that the shocks do not dissipate -- meaning the sum of the parameters is greater than 1.
On 20/11/2011 10:25, user84 wrote:
Hi, as i suppose to know in a stationary GARCH(1,1) model the sum of alpha and beta has to be smaller than 1. But if i use the garchfit() function from the package fGarch for my timeseries the sum is bigger than 1. The adf.test tells me a p-value smaller than 0.01 instead. What does this mean for me? Can i trust in the coefficients in this case? mfg user84 -- View this message in context: http://r.789695.n4.nabble.com/alpha-1-beta-1-1-in-GARCH-1-1-tp4088342p4088342.html Sent from the R help mailing list archive at Nabble.com.
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Patrick Burns pburns at pburns.seanet.com twitter: @portfolioprobe http://www.portfolioprobe.com/blog http://www.burns-stat.com (home of 'Some hints for the R beginner' and 'The R Inferno')