If I had to guess, it's the kind of person who is probably some math postdoc with 20 PhDs who slightly disagrees with some tiny assumption somewhere that would take an hour to explain with analysis the "rigorous" way. You're right though, and it annoys me too. This is a super helpful video and is perfect for someone trying to get their head around unit roots.
Don't know why I am only discovering your excellent content now. Great work. Clear pronunciation, properly zoomed visuals, in-focus text, well paced delivery, well thought out organization of material.
I am just getting into machine learning and this series of videos gives me all the math and stats background knowledge I need for understanding the time series, thank you!
OMG man you explain everything sooooo well and that's not easy to do because you talk about very complicated stuff !!! looking so forward to watch all your videos
firstly at first hearing I was panicked about these concepts, but this sir has nailed it and explained it in a way which made very easy to relate the situations graphically and mathematically. Kudos!!
I'm having my first time series course. Neither the lecture nor the notes and textbook give a clear introduction to key concepts in TS. Excellent video and should've watched earlier.
Just want to say that these videos are great (have only watched the VAR and the unit Root ones). Nothing new under the sun, but you are explaining them in clear ways with good/simple examples. This is something I saw the need for with Econometrics, but you are a good job, and I don't think I could add anything to what you have done so far. Looking forward to reviewing the rest of your collection, and seeing more of this content.
You're a master, thank you for sharing your knowledge with those of us with lower cognitive abilities. By the way, thank you - I understand the concept now.
mate, you just become part of my suscriptions, this termp poped up in an econometric analysis and I didn't knew what an unit root is until you, very clear and nice. thanks mate
I am greatly inspired watching this video to dig deeper about time series. Actually Imma lil' bit confused yet at this moment I got to understand unit root well. thank youuu!
1. At 3:38, where did first term a0 come from? 2, 10:20 you mentioned phi = 1 so E(at) = a0, but the whiteboard shows MOD(phi) = 1, so i'm thinking can't E(at) = - a0? (There seems to be an assumption t in power is even so (-1)(-1) = 1.) 3. 11:45 variance is getting bigger as we go rightwards. What if we limited the analysis to the 1st 1/4 of the x-axis? That looks stationary. This prompts the question do people conveniently choose the range of x to model to artificially make their results look great? Related question is how far back in history to go when building time series models?
Fantastic Ritvik. I benefitted. Normally I use the family tree to explain and understand Time Series. The grandpa grandson genealogy examples that work equally good. But this one is more direct
Man your videos are amazing and super intuitive so please keep making the thanks!!! I've got just one question. In the last example for dt = at - a_t-1, did you get dt = et using the assumption that phi=1 so the at_1 terms cancel out? If you did then would you need to first test that phi is a unit root so you can then use that as an assumption to make dt = et?
It's not "assumed" that phi = 1 coz we already know it is. Our time series isn't stationary when phi = 1. So to make it stationary, we take the first difference.
Clear explanation. Could you please explain which video you are referring to when talking about the MA infinity model? May I ask how you got the first term in the AR(1) model that you have specified? Thank you very much for your time.
Dear Anton, greetings and all the best with your use of impulse response functions. Do you still need help? I could help... A brief discussion may get you off the ground.
@@TheTijuT Cheers Tiju, I figured it out on my own by now through textbooks. Took me a while but according to my supervisor I did a good job... Thank you anyways :)
Hello Ritvik ! Thanks for the fantastic video 😄 At the end, when you compute the Lag 1 of the time series, you're left with the epsilon_t time series. While it is stationary, do you have anything left to model and predict since it's pure white noise ? Also it would be great to know how L1 applies to higher orders of AR series, but maybe it's covered in future videos, I'm still checking them out one by one ! Thanks again for the great series, wishing you the best.
Is it just me or the order of videos in this playlist is off for others too? Like in this one he refers to a previous video on how to represent an AR model as a MA model but I haven't seen that video yet...I assume it comes later?
At 5m21s you say that phi^t * a_0 is a constant, so has variance zero. But...seems to be a function of t to me? These videos have been incredibly helpful, thanks so much :)
Hi @ritvikmath could we also use tests like the ADF and Hurst Exp to determine exactly which parts of a trending timeseries could be considered stationary?
Very nice explanation and video, I subscribed! However, I think the explanation 2 is slightly incorrect - in case of phi < -1, plot of time series should jump from positive to negative values, I think, not monotonically decrease. Then in this case expected value should not even exist (+ or - Inf?). And in case 3 why you didn't go to the limit with calculating variance like in case 1 and 2? As answer t*sigma^2 is only partially correct. Happy to be corrected on everything :) Greeting from Poland!
I had a question. I'm confused on the meaning of "stationary". Besides having a constant mean and variance, I thought it also means that there is no autocorrelation. Here you check that the timeseries has a constant mean and variance and say that it is "stationary". So does stationarity mean only constant mean and variance?
We had before our transformed AR into MA process as = epsilon(t) + coef*epsilon(t-1)+coef^2*epsilon(t-2)+..., but i kinda cannot get it why are we adding coef^t*a(0) here. Is it just because of how AR specified, so we 100% need to have a first data point? and even if so, why are there superscript t in coeficient, not 0? Thanks in advance for answer
You are the best at time series but I think u need to prepare new play list about that bcz while u talking about AR model in the 2nd video I didn't know what is it
but if we have to take the first difference to get to stationarity, then are we not limited to only making predictions of differences? instead of making prediction of the absolute level of the variable itself, such as sales?
@ritvikmath Hi, i've watched both the invertibility videos, but i'm struggling to understand how we get the first part of line 2: a_t = phi^t a_0 + ... Please can you help me understand this?
Although it seems too late, it is just the regression model describing a value of a variable at time ”t” that is dependent to a previous value at time ”t-1”, including the white noise variable. As an example, take the GDP.
Even in |phi|infinity. So, doesn't this violate the constant variance conditiion as a_1, a_2 and so on all will have different variances (meaning it is actually changing over time)?
I read and watched many many many sources. This one is far the best explanation. It explains both intuitively and mathematically well
thank you!
I am angry at two people who disliked this very helpful video!
probably my statistics professor lol
WHO THE HECK disliked this masterpiece???
If I had to guess, it's the kind of person who is probably some math postdoc with 20 PhDs who slightly disagrees with some tiny assumption somewhere that would take an hour to explain with analysis the "rigorous" way. You're right though, and it annoys me too. This is a super helpful video and is perfect for someone trying to get their head around unit roots.
@ BAM
CCP
@@redcat7467 double BAM
lol
really u the only youtuber whos digging this deep, i hope you continue and panel data plz its the trend nowdays
Thank you for breaking this down man. You really have a special knack for this. We need more content! 😉
This is awesome, have my time series exam in a week and was not too optimistic... you're a lifesaver!
You explain this topic so good and understandable. The world needs more teachers like you 👍🏻 thank you!
Wow, thank you!
please provide a direct link to the video you mention at 3:26 AR as MA inf as it is not in the earlier videos in this playlist.
best teacher ever, firmly believe that the ability of teaching is a talent! Thanks
Thank you for saving me and breaking all of this down in a way that is not only comprehensible but highly efficient too. I appreciate you, too
I think what you have explained is the essence of unit roots. Thank you for sharing! It's a gift for the world.
Don't know why I am only discovering your excellent content now. Great work. Clear pronunciation, properly zoomed visuals, in-focus text, well paced delivery, well thought out organization of material.
I look forward to watching the Dickey-Fuller or the Augmented DF.
Thank you for your time and for being so clear! 😊
ritvikmath...hands down you have the best stat formulas and models explanation videos on youtube....clear, concise and exemplary..bravo!
Wow, thanks!
I am just getting into machine learning and this series of videos gives me all the math and stats background knowledge I need for understanding the time series, thank you!
Excited for your journey!
OMG man you explain everything sooooo well
and that's not easy to do because you talk about very complicated stuff !!!
looking so forward to watch all your videos
Going through all your videos about Time Series... great videos, thanks a lot!
Glad you like them!
firstly at first hearing I was panicked about these concepts, but this sir has nailed it and explained it in a way which made very easy to relate the situations graphically and mathematically. Kudos!!
I'm having my first time series course. Neither the lecture nor the notes and textbook give a clear introduction to key concepts in TS. Excellent video and should've watched earlier.
Best videos on time series I have seen. I love this!
Just want to say that these videos are great (have only watched the VAR and the unit Root ones). Nothing new under the sun, but you are explaining them in clear ways with good/simple examples.
This is something I saw the need for with Econometrics, but you are a good job, and I don't think I could add anything to what you have done so far.
Looking forward to reviewing the rest of your collection, and seeing more of this content.
Glad you like them!
Your videos have been really helpful for my study this semester. Thank you so much. Keep up the great work :)
Your teaching ir perfect! And is helping me a lot with my thesis. Thank you so so much! Regards from Brazil.
You're a master, thank you for sharing your knowledge with those of us with lower cognitive abilities. By the way, thank you - I understand the concept now.
mate, you just become part of my suscriptions, this termp poped up in an econometric analysis and I didn't knew what an unit root is until you, very clear and nice. thanks mate
Welcome aboard!
You summarize the important facts so easy and understandable. Thank you so much.
Excellent video!! Fine balance between theory and practice
I've just found your channel. You're giving out there quality man. Congrats!!!
This is so helpful! GREAT video!! Saver of my Econometrics module!! Thank you so much!!!
Great to hear!
It is not easy to breakdown a difficult mathematical concept in such a simple to understand way! Subscribed!
Excellent, the best explain about the AR(1) model of stationary!
Really good video!! Didn't understand these AR and Unit Roots definitions but you managed to explain this in a simple talk
Glad it was helpful!
I am greatly inspired watching this video to dig deeper about time series. Actually Imma lil' bit confused yet at this moment I got to understand unit root well. thank youuu!
Thanks so much for it, really great explanation and easy to understand. Watching from Brazil, congrats! You are great.
You're very welcome!
Man you should have been my econometrics professor. Thank you for the hard work.
Happy to help!
You sir have a gift in conveying complex idea into very easily understandable concept! Keep up the good work!!
Thanks a lot!
You're awesome This is a really well-spoken and intriguing video. Thanks for sharing!
You are unbelievable amazing sir, I appreciate it and really really hope you have a great great life
I appreciate that!
Greatest explanation ever! you just saved my whole thesis
really good introduction to unit test for time-series data. loved it and finding your video on characteristic eqn for more complicated time series!!
You're so good at this. Your videos rock man.
I appreciate that!
Good introduction, this helped a lot. Thank you!
Glad it was helpful!
Best explanation. Would have been best if the playlist was arranged
You are a genius man. I salute you.
Nice explanation. One question - Why did the variance term has powers of two, should it not include odd powers as well : phi, phi^3, phi^5 ...
Very good explanation of unit root. Thank you.
Great Stuff Ritvik! Looking forward to the characteristic equation video
Superb awesome and splendid
@1:19 God you're such a good teacher. I wish you were my professor back in college.
@4:15 See how well he explained the expectancy. See how easy that was to understand.
1. At 3:38, where did first term a0 come from?
2, 10:20 you mentioned phi = 1 so E(at) = a0, but the whiteboard shows MOD(phi) = 1, so i'm thinking can't E(at) = - a0? (There seems to be an assumption t in power is even so (-1)(-1) = 1.)
3. 11:45 variance is getting bigger as we go rightwards. What if we limited the analysis to the 1st 1/4 of the x-axis? That looks stationary. This prompts the question do people conveniently choose the range of x to model to artificially make their results look great? Related question is how far back in history to go when building time series models?
Man, that is awesome! Thank you so much.
Extremely well presented and clear, thank you
Amazing explanation! Good job!
Glad you liked it!
Fantastic Ritvik. I benefitted. Normally I use the family tree to explain and understand Time Series. The grandpa grandson genealogy examples that work equally good. But this one is more direct
Glad it was helpful!
I can just to thank you and ask for more awesome videos
THANK YOUUU SO MUCH!! Great and very clear explanation.
man, what a life saver! thanks for the video
Hi Ritvik, can we have the play list in a sequence ?
Great explanation, thanks. Keep it up
Magically clear. Thank you so much.
Can you also add some references to publications which you consider easy to follow?
thank you so much for dumb this down for me. Cant wait for your next content
Thank you for informative content
Amazing explanation man! THANK YOU!!!!!
My pleasure!
Man your videos are amazing and super intuitive so please keep making the thanks!!!
I've got just one question. In the last example for dt = at - a_t-1,
did you get dt = et using the assumption that phi=1 so the at_1 terms cancel out?
If you did then would you need to first test that phi is a unit root so you can then use that as an assumption to make dt = et?
It's not "assumed" that phi = 1 coz we already know it is. Our time series isn't stationary when phi = 1. So to make it stationary, we take the first difference.
For the first case, we have checked mean and variance but we did not check seasonality. Don't we also need to check that to be sure it is stationary?
Thank You very much ! Your videos are amazing
Thank you for such great videos
Glad you like them!
Clear explanation. Could you please explain which video you are referring to when talking about the MA infinity model? May I ask how you got the first term in the AR(1) model that you have specified? Thank you very much for your time.
Great video, could you explain where comes from the name "root" in this topic?
huge video very well done
Big thanks!
Dude, this was amazing.
thank you sir, for your impact.
Impulse Response Function Please! I want to apply it in my Bachelor Thesis in Finance but struggle to get the hang of it :(
Dear Anton, greetings and all the best with your use of impulse response functions. Do you still need help? I could help... A brief discussion may get you off the ground.
@@TheTijuT Cheers Tiju, I figured it out on my own by now through textbooks.
Took me a while but according to my supervisor I did a good job... Thank you anyways :)
I am studying IRF too. Interesting stuff.
5:40 when counting variance why do we only take even steps of fi ? 10:15 is fi 1 or -1? and in that case expected value should be 0 ?
One of those tutorials that transcend time
Excellent video. What’s the relation between unit root and eigenvalues?
Hello Ritvik ! Thanks for the fantastic video 😄
At the end, when you compute the Lag 1 of the time series, you're left with the epsilon_t time series. While it is stationary, do you have anything left to model and predict since it's pure white noise ?
Also it would be great to know how L1 applies to higher orders of AR series, but maybe it's covered in future videos, I'm still checking them out one by one !
Thanks again for the great series, wishing you the best.
very fluid and Breez to watch!! is it possible to connect and seek your guidance further. Cheers!! Vivek
Is it just me or the order of videos in this playlist is off for others too? Like in this one he refers to a previous video on how to represent an AR model as a MA model but I haven't seen that video yet...I assume it comes later?
Honestly this is brilliant, thanks you
thank you so much for making this video such simple.
thanks for the videos with clear explanation. I look forward to watching the dickey fuller test, is it gonna be uploaded yet?
this is some solid and simple explanation.
did he ever release the video about roots for ar(2) models?
Excellent sir,Thankyou
At 5m21s you say that phi^t * a_0 is a constant, so has variance zero. But...seems to be a function of t to me?
These videos have been incredibly helpful, thanks so much :)
Hi @ritvikmath could we also use tests like the ADF and Hurst Exp to determine exactly which parts of a trending timeseries could be considered stationary?
is the playlist in the correct order? where are the AR MA videos you are talking about
Awesome explanation
Very nice explanation and video, I subscribed! However, I think the explanation 2 is slightly incorrect - in case of phi < -1, plot of time series should jump from positive to negative values, I think, not monotonically decrease. Then in this case expected value should not even exist (+ or - Inf?).
And in case 3 why you didn't go to the limit with calculating variance like in case 1 and 2? As answer t*sigma^2 is only partially correct.
Happy to be corrected on everything :) Greeting from Poland!
I had a question. I'm confused on the meaning of "stationary". Besides having a constant mean and variance, I thought it also means that there is no autocorrelation. Here you check that the timeseries has a constant mean and variance and say that it is "stationary". So does stationarity mean only constant mean and variance?
We had before our transformed AR into MA process as = epsilon(t) + coef*epsilon(t-1)+coef^2*epsilon(t-2)+..., but i kinda cannot get it why are we adding coef^t*a(0) here. Is it just because of how AR specified, so we 100% need to have a first data point? and even if so, why are there superscript t in coeficient, not 0? Thanks in advance for answer
Thank u so much for making such a great tutorial!! But may i knw why the variance of dt is sigma squared??
Could someone please provide sequence for this playlist? It’s hard to get the correct flow
You are the best at time series but I think u need to prepare new play list about that bcz while u talking about AR model in the 2nd video I didn't know what is it
but if we have to take the first difference to get to stationarity, then are we not limited to only making predictions of differences? instead of making prediction of the absolute level of the variable itself, such as sales?
Why does the error term e sub (t-k), have the same coefficient phi? Don't error terms have no coefficients with mean zero?
beautiful video, just the right amount of math for a quick revision
@ritvikmath Hi, i've watched both the invertibility videos, but i'm struggling to understand how we get the first part of line 2: a_t = phi^t a_0 + ...
Please can you help me understand this?
Although it seems too late, it is just the regression model describing a value of a variable at time ”t” that is dependent to a previous value at time ”t-1”, including the white noise variable. As an example, take the GDP.
Even in |phi|infinity. So, doesn't this violate the constant variance conditiion as a_1, a_2 and so on all will have different variances (meaning it is actually changing over time)?