Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

Forecast volatility with GARCH(1,1)

Loading...

Sign in or sign up now!
Alert icon
Upgrade to the latest Flash Player for improved playback performance. Upgrade now or more info.
30,864
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Feb 13, 2008

We can forecast volatility with GARCH(1,1). The key parameter is persistence (alpha + beta): high persistence implies slow decay toward the long run average

Category:

Education

Tags:

License:

Standard YouTube License

Link to this comment:

Share to:

Uploader Comments (bionicturtledotcom)

  • another useless finance formula that you will never use in real life

  • @quicken02 thanks for the constructive input, i really owe you one ...

  • @bionicturtledotcom no need to take offense, I am just saying it how it is, your videos are great, i watch them all the time, i am subscribed

  • @quicken02 How do you know what it is ... such that you can say how it is? Rob Engle won the Nobel Prize for the ARCH class and spawned a entire field that continues 30 years later. The current applications ... won't ... fit ... on ... this ... page. And the math is beautiful. I'm not offended, I just don't understand how somebody can be incurious.

  • Very good video, makes it a lot more understandable. My question is: how would I use this to forecast future stock prices ($7, $8, ?forecast).

  • @EHDuke29 what i meant is: by making the limiting assumptions that returns are normal, the GARCH implicitly assumes the price has a drift (mu), which is a forecast

Top Comments

  • Thank you,very helpfull video.

  • @EHDuke29 Thank you! You can't use GARCH(p,q) to forecast prices, it makes a limiting assumption that conditional returns are normal. And, in practice, volatility is less difficult to predict.

see all

All Comments (21)

Sign In or Sign Up now to post a comment!
  • @bionicturtledotcom ok, is GARCH ever used in combination with ARIMA as a way of deciding the 95% prediction bounds? Or this is not possible because of heteroskedasticity? Hope my question makes sense.

  • @bionicturtledotcom May I ask what degree(s) you have? Seems like you have a Ph.D in math, stats or finance.. I'm having trouble following your videos. Is there any other way I could figure out what exactly this model is and how it works?

  • You really should sell this stuff. It is good. Check out VideotutorA2Z.

Loading...

Alert icon
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more