What are Autoregressive (AR) Models

Поділитися
Вставка
  • Опубліковано 31 гру 2024
  • Time to start talking about some of the most popular models in time series - ARIMA models. First things first, let's look at the AR piece - autoregressive models!

КОМЕНТАРІ • 82

  • @pettirto
    @pettirto Рік тому +1

    Thanks Mr. LaBarr, I'm studying for my exam in time series and your videos are very helpful. Greetings from Italy!!!

    • @AricLaBarr
      @AricLaBarr  Рік тому

      Grazie! Glad to hear it was helpful!
      Ciao!

  • @enock_elk
    @enock_elk 4 роки тому +5

    Came here after being confused by my Lecturer,
    Thank you very much for simplifying this!

  • @oq88
    @oq88 3 роки тому +1

    One of the best teachers i’ve ever seen!
    Thank you

  • @hugoagudo4282
    @hugoagudo4282 3 роки тому +5

    Great video. I’ve had a text book about time series that’s been gathering dust because I was afraid of all the symbols. This helps a lot

  • @clickbaitpolice9792
    @clickbaitpolice9792 2 роки тому +1

    just become my lecturer lol. i love the enthusiasm you put in. makes learning more fun lol

  • @oren2234
    @oren2234 3 роки тому +1

    my statistics is very basic and i just needed a forecasting algorithm, this video explained it sooo well

  • @arnonym5995
    @arnonym5995 10 місяців тому

    I like the way you convey the intuition behind AR and MA models. One thing that might be confusing is however the terminology, in particular with regard to short and long memory, which is different in common literature. Therein, AR, MA and ARMA models are considered to be short-memory models, because their autocovariances are summable. Also AR models, whose autocovariance function (ACVF) decays quite quickly towards zero for increasing lags, even though the ACVF values in fact never fully reach zero, has summable autocovariances. In contrast long-memory behavior is indicated by a hyperbolically decaying ACVF, which results in an ACVF whose elements are not summable anymore. A popular example is the fractionally integrated ARMA model, often denoted by either FARIMA or ARFIMA, that can still have ACVF values of notable magnitude for large lags.

  • @economicsfriendly7425
    @economicsfriendly7425 3 роки тому +1

    wow your teaching style is really amazing !! please make more videos on time series analysis. we really need your help!!

  • @williamgomez6226
    @williamgomez6226 2 роки тому

    Thank you, j had seen this equation when a was studying reinforcement learning, it's like the Value function weighted by a discount factor.... Great explanation!!!

  • @ahsanshabbir16
    @ahsanshabbir16 3 роки тому

    Hi Dr Aric LaBarr you work is Amazing please continue this again
    Under 5 minute concept is great

  • @felipedaraujo_
    @felipedaraujo_ 3 роки тому +1

    Excellent teaching! Thanks for your good work Aric!

  • @eengpriyasingh706
    @eengpriyasingh706 2 роки тому

    For 3:51, what is the manipulation done should be explained a little. Since I am not from this background it will be difficult for me to go through what and how it is happening?

    • @ArunKumar-yb2jn
      @ArunKumar-yb2jn 2 роки тому

      May be you should make some effort by gathering a little background before asking that question?

    • @eengpriyasingh706
      @eengpriyasingh706 2 роки тому

      @@ArunKumar-yb2jn u r so smart that's why I am asking...if he has told some references or a bit of manipulation done......if I have already some background then definitely I will not be here

    • @ArunKumar-yb2jn
      @ArunKumar-yb2jn 2 роки тому

      @@eengpriyasingh706 May be you should not act so entitled.

  • @vadimkorontsevich1066
    @vadimkorontsevich1066 2 роки тому

    God bless you for your efforts to explain!

  • @rossijuan9548
    @rossijuan9548 3 роки тому

    Excellent contribution, thank you very much

  • @bend0596
    @bend0596 Рік тому

    super clearly explained, thanks!

  • @josealeman5008
    @josealeman5008 2 роки тому

    simple and beautifully explained! thanks!

  • @pol-aurelienhay5050
    @pol-aurelienhay5050 20 днів тому

    merci beaucoup monsieur Labarr!

  • @magtazeum4071
    @magtazeum4071 Рік тому

    at 3:31, 2nd term on the right hand side of the last equation, shouldn't the power of PI be (t-1) instead of t (and so on) ?

    • @AricLaBarr
      @AricLaBarr  11 місяців тому

      Completely correct! In all honesty, I should have had the left hand side be Y_(t+1) to make the math work better.

  • @Atrix256
    @Atrix256 3 місяці тому

    A lot of overlap here with an infinite impulse response filter from DSP. Im about to watch the moving average model video, but am wondering if that is the finite impulse response equivalent :)

    • @AricLaBarr
      @AricLaBarr  Місяць тому

      Not familiar with the infinite impulse response filter! Let me know what you think after watching the MA model video!

  • @valdompinga
    @valdompinga 2 роки тому

    man, you are incredible!
    Im learning ARIMA like im building legos!

  • @ΜιχαήλΣκιαδάς-γ8β
    @ΜιχαήλΣκιαδάς-γ8β 2 роки тому

    I could not undrestand how do you calculate the φ because I 've seen a lot of correlation types and I do not know which one to use. Thank you for your time.

    • @AricLaBarr
      @AricLaBarr  2 роки тому +1

      It actually isn't a correlation directly (unless it is an AR(1) model and then it is the Pearson correlation if the variables are standardized). The best way to think about it is that it is a weight in a regression model. The model chooses the weight that maximizes the likelihood (MLE) of the model and predictions. Hope this helps!

    • @ΜιχαήλΣκιαδάς-γ8β
      @ΜιχαήλΣκιαδάς-γ8β 2 роки тому

      @@AricLaBarr It helped a lot, thank you

  • @elisesauvary8174
    @elisesauvary8174 3 роки тому +1

    You are a god send!!

  • @roym1444
    @roym1444 4 роки тому +1

    Is there any online resource you know of that would demonstrate how to code some of the concepts you've spoke about ?

  • @dipenmodi1807
    @dipenmodi1807 4 роки тому +1

    Can you explain the difference between Static, Dynamic and Autoregressive Probit models?

  • @kumaratuliitd
    @kumaratuliitd 3 роки тому +1

    Hi Aric, thanks for the explanatory video. Can it be said that AR(1) is equivalent to Single Exponential Smoothing algorithm because it too depends on the Previous forecast and error.

    • @AricLaBarr
      @AricLaBarr  3 роки тому +1

      Actually, a single exponential smoothing model is equivalent to a moving average of order 1 after taking a single time difference (more formally called an ARIMA (0,1,1) model or sometimes an IMA(1,1))! This is because of the structure of the single exponential smoothing model. It is a combination of past and prediction, but the prediction is more past, etc. Hope this helps!

  • @robin5453
    @robin5453 Рік тому

    Best ever, thank you!!

  • @NishaSingh-qf2it
    @NishaSingh-qf2it 2 роки тому +1

    Hi Aric!
    This was such a splendidly explained video. I have a doubt though about NARX. Do they function the same way as this one (explained in the video) because NARX is also autoregressive model? If not, could you please explain about NARX as well?

  • @michalkiwanuka938
    @michalkiwanuka938 6 місяців тому

    the underlying assumption is that we know the data up to time t-1, and we use the observed data to estimate the parameters (ϕ1,ϕ2,…,ϕpϕ1​,ϕ2​,…,ϕp​ and e_t) , right?

  • @razzlfraz
    @razzlfraz 5 років тому +1

    Does anyone know where the line is between autoregression and regression is, because, eg lowess and loess functions are called local regression, yet it looks like "local regression" is a form of autogression from a 10,000 ft view. My guess atm is that local regression does not add stochastic noise making it just barely miss the definition, but I am only guessing here. It could also be local regression is a form of autoregression but everyone is too lazy to write it all out. Whatever it is, I would like to know!

    • @PhilosophySoldier
      @PhilosophySoldier 4 роки тому

      Good question - I'm also wondering the answer. @Aric LaBarr can you help?

  • @pjy1006
    @pjy1006 2 роки тому

    Love your videos! I am on a quest to find out why we need stationarity for ARIMA model (many explanations online but I cannot say I have a very clear understanding). Is stationarity necessary for Simple Exponential Smoothing?

    • @AricLaBarr
      @AricLaBarr  2 роки тому

      We need stationarity because the structure of ARIMA models are that they revert to the average of the series if you predict out far enough. That wouldn't work very well at all if we have trending or seasonal data!
      Simple ESM's don't need stationarity, but do require no trend or seasonality to make them work best. Stationarity is more mathematically rigorous than just no trend or seasonality.
      Hope this helps!

  • @MrSk8L8
    @MrSk8L8 4 роки тому +1

    Great explanation

    • @AricLaBarr
      @AricLaBarr  4 роки тому

      Thank you! Glad you liked it!

  • @josephgan1262
    @josephgan1262 2 роки тому

    If I am using a AR(1) model, and I have data of Yt-1, do I need to recursive back all the way to start point to predict Yt? or I can just use the formula shown at @1:17

    • @AricLaBarr
      @AricLaBarr  2 роки тому

      You just use the formula! The recursive piece is to just show what is happening in concept if you keep plugging in what each lag truly represents. All you need for an AR(1) is just the lagged values (for each time point) to build the model!

  • @dineafkir5184
    @dineafkir5184 4 роки тому

    Nice video. Will you be making something about the ARCH/GARCH model :-)

  • @Rundtj45
    @Rundtj45 3 роки тому

    Excelente explanation, thanks

  • @vaishnavikhiste7841
    @vaishnavikhiste7841 Рік тому

    WELL EXPLAINED

  • @Pewpewforyou0
    @Pewpewforyou0 3 роки тому

    this was very helpful

  • @Rundtj45
    @Rundtj45 3 роки тому

    How is different between long and short run,
    Do you have any class about that

  • @梁馨月-m7c
    @梁馨月-m7c 4 роки тому +1

    I hope there is a video about MA model!!!!!

  • @mirroring_2035
    @mirroring_2035 Рік тому

    Okay you're genius, thanks

  • @ValentinLeLay
    @ValentinLeLay Рік тому

    Hi ! At 3:33 you wrote Yt = w/(1-ø) + ø^tY_1 + ... but shouldn't it be Yt = w/(1-ø) + ø^tY_0 + ... since it's basically ø^tY_t-t = ø^tY_0

    • @AricLaBarr
      @AricLaBarr  11 місяців тому

      You are correct! That should be Y_0 or phi^(t-1). I should have had the left hand side equal Y_t+1 and then my math would work better :-)

  • @Tomahawk1999
    @Tomahawk1999 4 роки тому

    Dear Aric, can a AR model have other predictors? and if yes what class of models is that?

    • @AricLaBarr
      @AricLaBarr  4 роки тому +2

      Yes they can!
      AR models are long memory models, but there are also short memory models (think quick shocks that don't last long in time) called Moving Average (MA) models. That is the next video about to come out!
      If you are talking about normal predictors (think X's in linear regression) then this class of model is called an ARIMAX model. I'll have a video on these coming soon!

    • @Tomahawk1999
      @Tomahawk1999 4 роки тому

      @@AricLaBarr Thanks for the quick reply!. I had to review a paper last week which used predictors (like X's) to examine stock prices in a time series model. I really had no clue and if and when u make a video, please do include how to run these models, and evaluate these models. Thanks a lot. stay safe.

  • @kafuu1
    @kafuu1 6 місяців тому

    nice video!

  • @mengsupeng6541
    @mengsupeng6541 4 роки тому

    Thank you. Already subscribed.

  • @amirhoseinbodaghi9527
    @amirhoseinbodaghi9527 3 роки тому

    Thank You Dear

  • @statisticianclub
    @statisticianclub 4 роки тому

    Really beneficial

  • @sidharthmohanty6434
    @sidharthmohanty6434 3 роки тому

    Thanks

  • @zubairkhan-hz1vz
    @zubairkhan-hz1vz 5 років тому +1

    Plz Arima model

  • @makting009
    @makting009 4 роки тому

    Sir one video about moving average

    • @AricLaBarr
      @AricLaBarr  4 роки тому

      Definitely! Be on the look out this week!

  • @insideonionyt
    @insideonionyt 4 роки тому +1

    Its damn awesome!!!!!

  • @anupamagarwal3976
    @anupamagarwal3976 2 роки тому

    perfect 5mins to understand any topic

  • @waimyokhing
    @waimyokhing 5 років тому

    what is exponential autoregressive model???

    • @razzlfraz
      @razzlfraz 5 років тому +1

      Like this? en.wikipedia.org/wiki/Exponential_smoothing

  • @andreneves6064
    @andreneves6064 4 роки тому

    Slides please

  • @GameinTheSkin
    @GameinTheSkin 3 роки тому

    You are a more level headed StatQuest, won't mind singalongs tho

  • @andresgonzalez-nl8or
    @andresgonzalez-nl8or 4 місяці тому

    shouldn't it be, if Φ > 1 and not Φ < 1?

    • @AricLaBarr
      @AricLaBarr  Місяць тому

      Not if you want stationarity. To be stationary, we want the value of phi to be less than 1 so that when raised to higher powers we have lower and lower impact on that observation the further back in time we go.

  • @batolhashimi6863
    @batolhashimi6863 2 роки тому +2

    I wish you were my professor instead of him.

  • @HardKore5250
    @HardKore5250 4 роки тому

    GPT-3

  • @abderrahimba7390
    @abderrahimba7390 2 роки тому

    Wooow