GARCH detrend return data

Dear All,
I am trying to GARCH detrend return data, that is, as my series exhibits conditional heteroscedasdcity I want to take it out, in order to have stationary data. Let "archtimeseries" be a vector of about 4000 observations of returns for a company.
Mdl = garch(1,1);
EstMdl = estimate(Mdl,archtimeseries);
variance = infer(EstMdl,archtimeseries);
archtimeseries = archtimeseries./sqrt(variance);
But Matlab returns HUGE standard errots (10^5-10^12) and warns that:
Warning: Linear inequality constraints are active; standard errors may be inaccurate.
Did anyone ever run into this problem and knows a solution?
thanks in advance!

回答(0 个)

类别

帮助中心File Exchange 中查找有关 Conditional Variance Models 的更多信息

提问:

2016-5-29

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by