You never explained why c1 is 0.5 Did you choose it randomly ? Is it the y intercept ? Why 0.5, why not another value, like a whole number ? What about negative numbers?
It's just a coefficient of how seriously we shoud be considered error from the previous step. -0.5 means we will take the prediction error from the previous step and consider to move our next prediction towards the half of the error value. To be honest, with all the love to the channel owner, he is explaining things in a very clumsy way
Does a negative value for Pearson's coefficient indicate a reverse proportionality or does it mean that there is no relation/dependency between the variables considered? What happens if in the ACF/PACF plot the graph extends to the negative axis beyond the error band? How do you take that into the order consideration?
Just figured it out, y(t) is the actual value, and ŷ (t) is the predicted value. ŷ (t) = c1*E(t-1) + c2*. However, the actual value is the predicted value plus the error at that time which is E(t) so y(t) = ŷ (t) + E(t) = c1*E(t-1) + c2* + E(t)
![Lp. Сердце Вселенной #60 РОЖДЕНИЕ ЛОЛОЛОШКИ [Финал] • Майнкрафт](http://i.ytimg.com/vi/YoR0pAV9FVQ/mqdefault.jpg)
Man, I have never understood Time Series so smoothly. Thanks!
Your explanations are terrific - simple and straight to the point. Thanks alot for this smooth style!
i love u man...my proff had phd and is twice your age but his explanation was no where near your's..
Means a lot, thanks!
I don't usually comment on videos. But this one is a Great video
You never explained why c1 is 0.5
Did you choose it randomly ? Is it the y intercept ?
Why 0.5, why not another value, like a whole number ? What about negative numbers?
It's just a coefficient of how seriously we shoud be considered error from the previous step.
-0.5 means we will take the prediction error from the previous step and consider to move our next prediction towards the half of the error value.
To be honest, with all the love to the channel owner, he is explaining things in a very clumsy way
Thank you for the video, sir, how do you get the error for the current prediction "et" when you havent made the prediction yet?
Recursive method...
Hi, why do we use Acf plot lags for Moving average order and Pacf plot lags for Auto regression order?
Nice explanation
Does a negative value for Pearson's coefficient indicate a reverse proportionality or does it mean that there is no relation/dependency between the variables considered?
What happens if in the ACF/PACF plot the graph extends to the negative axis beyond the error band? How do you take that into the order consideration?
in the last example: the predicction value for 4th n 5th itergation are 7 and 7.5 , but in graph its 10 and 9??
Excellent explanation!!
How do we know the current error (epsilon t) if we are forecasting the current value?
Just figured it out, y(t) is the actual value, and ŷ (t) is the predicted value. ŷ (t) = c1*E(t-1) + c2*. However, the actual value is the predicted value plus the error at that time which is E(t) so y(t) = ŷ (t) + E(t) = c1*E(t-1) + c2* + E(t)
Thanks bhai .Explained it very clearly
Hey, Hi I cant see your video part 2, it shows private video?
Yeah, I had received a copyright claim on it because of the intro music used. I will reupload it tomorrow.
@@NachiketaHebbar thanks man!! Wonderful explanation and inspiring as well!
@@NachiketaHebbar You haven't uploaded it till now, please upload
I already uploaded it 4 days back
Superb explanation!!
excellent content!
why 0.5
clear explanation
Why is mean 4 here?
part 2?
👍