Clear Filters
Clear Filters

Forecasting returns using a GARCH model

2 views (last 30 days)
Jzbucki
Jzbucki on 25 Aug 2015
Hi!
I am struggling with correctly understanding how to forecast stock returns using GARCH models in MATLAB. Specifically I want to estimate a GJR-GARCH(1,1) model. I am assuming the following specifications of returns
r_{t} = mu + h_{t} z_{t}
where z is N(0,1). To obtain the one period ahead stock returns forecasts I firstly use the ARMAX-GARCH-K toolbox to obtain the mean and variance forecasts. This is where I am not sure how to obtain the predicted stock returns from my partial results. I am attaching a piece of reproducible code.
load Data_EquityIdx
nasdaq = Dataset.NASDAQ;
r = price2ret(nasdaq);
[MF, VF] = garchfor(r, 'GJR', 'GAUSSIAN', 0, 0, 1, 1, 1);
I would appreciate any kind of help :)

Answers (0)

Categories

Find more on Conditional Variance Models in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!