I have made a beginner friendly (yet detailed) course on Quantitative Finance & Risk Modelling. For my certification in Quantitative Finance contact analyticsuniversity@gmail.com or WhatsApp me on +31 625521289 or +91 9811519397 (do not call, just drop me a message on WhatsApp). Modules Covered: - Financial maths - Asset pricing -Risk management -Financial Econometrics -ML in Finance - Quant trading - Credit risk modelling -Market risk modelling
Time series analysis is one of most complicated topics for me and your video has simplified it so much for me. Your handwritten notes also helped a lot to understand the concept. Thank a lot for explaining in such a brilliant way!!!
This is really very well explained in a practical and clear manner. Thank you so much, this really made the concepts hit home, and I can read supplemental material on this with much better context and understanding. Thank you for taking the time to make this video.
There are plenty of videos on youtube. If you don't like how he teaches, go find another one. That is the beauty of internet. For me, it served the purpose and now I understand time series. Thank you, very much.
Can't agree more. Some people just have a title of doctor and no brain. This is the first time I understood the concept after reading and watching so many stuff.
This lecture is by far the best. Thank you Sir. You broke the topic to its simplest form. I have found most of the processes difficult to grasp before now , even my lecturers were unable to give me what I needed. You have set me free from the shackles of this course. I am a research student and once again, THANK YOU SIR. Sigh!
This is a great video ...you people know how to explain time series ... simple but sure you have explained in few minutes what my lecturer struggled to explain in two weeks
Y = a + bX is univariate analysis. Multivariate always refers to the dependent variables. So if we are forecasting/estimating one dependent variable then it is always univariate. If we have more than one independent variables, then it is called a multiple regression to be precise
Y = a+bX is multivariate analysis. That equation tries to predict the variation in Y(var 1) using the variation in X(var 2) hence multivariate. Univariate refers to variation of a single variable(and not comparing it to anything else)
Thanks for taking so much pain and patience in explaining the concepts. I know it is not easy to explain these abstract concepts. Great work. Excellent video on time series and modeling.
Well-done! Very professional, informative, with a lot of contents, and answers almost every possible questions. In the future videos, please also explain specific letters. For example, if you say that "p". or t, or u, or whatever, please explain that those specific letters refer to. Thanks a lot. I took a lot of useful notes.
In the MA equation, while predicting y(t), why is e(t) also included in the equation? How can we get the error value at time t when we haven't predicted y at time t?
Indeed a very informative video on time series and forecasting. One video contained all information that I needed in order to start practising time series on datasets. Thanks a lot.
The best explanation of time series. It's totally worth the 53 mins. However I have a doubt, when he said about the error in the MA method. Equation what you meant was: xty = slope*xt + intercept. and the error = xty - xt. Kindly correct me if I am wrong.
While explaining the White Noise series you said if the series is white noise then we will not use any time series forecasting but in Moving Average model you said the error term is a white noise. Can you please explain this, I am but confused, regarding the use of Time series forecasting model when we have a white noise process .
Great conceptual explanation of time series. I particularly loved the questions you raised and responded to. They are vital to understanding the concept yet so rarely appear in other sources. Thank you.
Good video. Nice clear explanations. I am taking time series/forecasting class and have tests coming up soon and this was a good summary of concepts. We use SAS in this class, I wish we used R as it is much easier
I am new to time series, your video was helpful, it had all the concepts in one place and it was an hour well spent. However I don't think differencing and differentiating are the same thing. Differencing is the process of taking a difference of series from itself as various lags. I am not sure if its about taking a derivative (like you hinted) ...
At 32:04 you have mentioned that differencing is actually differentiating. Isn't it actually subtracting with the order of the backward shift operator? Say first order differencing is actually yt - yt-1.
Much appreciated efforts has been made to provide robust understanding of the subject matter. Just few questions: 1) If we just look into a variable in an isolation (i.e stock price) etc on the basis of historical trend, its quite possible that this trend will not gonna happen in the future time period. For this problem, I've seen many people working on the elimination of trend. So, if we are able to remove trend, then still can it be possible to forecast a variable (stock price) ?
Hello Sir, I have a question about forecasting. Should plan corrections be determined during forecasting? Or is it not necessary to determine them? Why is there an extrapolation? An extrapolation is absolutely necessary.
22:00 mins - If white noise is purely random, then how come it has a 0 mean and a constant variance? A specific mean and a constant variance makes a term determinable or predictable, right? Kindly help me on this. Thank you :)
Not at all. Mean is irrelevant in discussing if a phenomenon is random, what's important is variance and for a non-random phenomenom, that variance should be 0. If the phenomenom does not vary, has variance 0, then it is deterministic and vice versa. Take a fair coin, give tails the value 0 and heads the value one. Then the outcome of one toss has a variance of (0^2)*0.5+(1^2)*0.5=0.5 The variance of this phenomenon is 0.5 it iss constant and known, but the result of the toss is still random and nobody can predict it with certainty. Another example, suppose you go to a casino and you play roulette, you bet 10$ on a number between 1 and 36 and if you win you get 35*10$=350$. The variance of your earnings is (350^2)*(1/36)+((-10)^2)*(35/36) it's constant for every round of roulette, you know it beforehand but you will never be able to guess the outcome of a roulette roll with certainty EVER.
Hello sir I want to thank you so much for this video the effort you put into this video incredible. it is so easy to follow and understand Thank you for my bottom of my heart
What if both ACF and PACF have spikes cut off to zero? Is that possible? Because I am running time series on R and my graphs are showing cut off to zero for both ACF & PACF.
because the data there is a trend in the diff process, it turns out that in the second diff the new data does not show a trend ... but when forecasting try diff 1 is obviously smaller 'MSE' ... how about that? please explain
Hi , For Strictly stationary you told mean , variance and covariance are time invariant, that is constant. For weakly stationary also you have mentioned mean, variance should be constant. Can you please help me on this ?
Please please please declare your values. Is beta a constant? integer? real? is Phi a constant? It would be helpful to use proper mathematical notation to make it clear!
By definition I time series has regular time intervals but how do I work on time series with irregular time intervals like sensor data coming at irregular time? Can I still use ARIMA, ARMA, MA models ?
Regarding white noise series,You have mentioned that mean of the series will be 0 for white noise series and then later told that time series shouldn't be applied and take the average of the series..If mean is 0 how does it matter of calculating average
I have made a beginner friendly (yet detailed) course on Quantitative Finance & Risk Modelling. For my certification in Quantitative Finance contact analyticsuniversity@gmail.com or WhatsApp me on +31 625521289 or +91 9811519397 (do not call, just drop me a message on WhatsApp).
Modules Covered:
- Financial maths
- Asset pricing
-Risk management
-Financial Econometrics
-ML in Finance
- Quant trading
- Credit risk modelling
-Market risk modelling
This is probably the most complete video on UA-cam on this subject! Thank you!!
thanks
It was difficult for me to have a big picture about time series. Now, i have the big picture with your video..thank you alot!...from Ecuador!!!
One of the most productive 53.14 minutes of my life🤗
thanks
@@AnalyticsUniversity Thank you
Time series analysis is one of most complicated topics for me and your video has simplified it so much for me. Your handwritten notes also helped a lot to understand the concept. Thank a lot for explaining in such a brilliant way!!!
thanks. learn Panel data analysis now : ua-cam.com/video/f01WjeCdgEA/v-deo.html
Super video! I applauded for $2.00 👏
Appreciate!
This is really very well explained in a practical and clear manner. Thank you so much, this really made the concepts hit home, and I can read supplemental material on this with much better context and understanding. Thank you for taking the time to make this video.
There are plenty of videos on youtube. If you don't like how he teaches, go find another one. That is the beauty of internet. For me, it served the purpose and now I understand time series. Thank you, very much.
This is the best explanation of time series model on you tube!
Thanks! Please support us on Patreon for more quality free content
www.patreon.com/user?u=2969403
Can't agree more. Some people just have a title of doctor and no brain. This is the first time I understood the concept after reading and watching so many stuff.
Just coz it worked for you doesn't mean its gonna work for everyome
Nicely done! Throughout this session, you have articulated clearly why we need to perform certain steps. That was quite helpful for me.
This lecture is by far the best. Thank you Sir. You broke the topic to its simplest form. I have found most of the processes difficult to grasp before now , even my lecturers were unable to give me what I needed. You have set me free from the shackles of this course. I am a research student and once again, THANK YOU SIR. Sigh!
thanks
This truly is the best video on the subject. I have regression and time series exam this Saturday! This was a huge help!
I just want to say thank you for this video. Very well explained . Very thorough and understandable .
thanks
This is a great video ...you people know how to explain time series ... simple but sure you have explained in few minutes what my lecturer struggled to explain in two weeks
Y = a + bX is univariate analysis. Multivariate always refers to the dependent variables. So if we are forecasting/estimating one dependent variable then it is always univariate. If we have more than one independent variables, then it is called a multiple regression to be precise
Y = a+bX is multivariate analysis. That equation tries to predict the variation in Y(var 1) using the variation in X(var 2) hence multivariate. Univariate refers to variation of a single variable(and not comparing it to anything else)
Very good lecture; not waste of time and not seen the lecturer but the content.
Thank you
Very Well explained. Found this video too useful after searching through different websites. Thanks....
Top' s my professor's lectures by a mile and a 1/2!!!
Thanks
i loved your presentation sir!
You took your time, explained in a clear and practical manner.
thank you for this video
It is very nice presentation style. It help students to understand what main points should be understood.
Best explanation of ARMA I've seen. Thank you.
Thanks
Thanks for taking so much pain and patience in explaining the concepts. I know it is not easy to explain these abstract concepts. Great work. Excellent video on time series and modeling.
Thanks
Please look into what seems a mistake to me at 30:10 it is differencing not differentiating. The difference between values for a lag.
Yes, you are right! I have mispronounced 'differencing' and 'differentiating' in many place.
You are such a helpful professor. Your videos have helped me much. Thank you
what an incredible tutorial! Please keep posting many more. Thanks and God bless you.
thanks
You save my ass for my Bachelor Thesis. Thank you very much !
Amazing clarity of concept with good explanation!!
Well-done! Very professional, informative, with a lot of contents, and answers almost every possible questions. In the future videos, please also explain specific letters. For example, if you say that "p". or t, or u, or whatever, please explain that those specific letters refer to. Thanks a lot. I took a lot of useful notes.
millions thanks sir, this lecture is worthy for ones who don't have access to formal class
Thanks! Please support us on Patreon for more quality free content
www.patreon.com/user?u=2969403
best tutorial on time series, so far.
Thanks! Please support us on Patreon for more quality free content
www.patreon.com/user?u=2969403
Thanks for making this video tutorial. Many of my doubts are now clear.
Ads every 2-2,5 minutes, that would be too many even for a tv channel! Useful video, but get your ads setting in order!
don't watch it! simple
@@indianarchangel irresponsible respond
Yes it's hard to learn when being interrupted every 5 min. So I downloaded it, and watched offline
Try adblock. will blow your mind
Skip to the end and replay.. no more ads
very good and clear explanations! Out of all tutorials, this was the best to understand the time series models! Can you share the data set?
The best help i have ever got on youtube. Thanks a lot.
this is beautiful..sir, this is amongst one of the best explanation which i have seen till now..thank you too much!!
Thanks
Very good sir
In the MA equation, while predicting y(t), why is e(t) also included in the equation? How can we get the error value at time t when we haven't predicted y at time t?
Univariate time series prediction: Box jenkins methodology 34:48
nicely explained... cleared few of my concepts... Thanks for making this video.
Thanks a lot ur explanation is crisp and clear.
thanks
Thanks
this was the best video on you tube of time series!! I from Perú, thanks!!
Thanks
Very good and helpful video for understanding Time series 👌
Indeed a very informative video on time series and forecasting. One video contained all information that I needed in order to start practising time series on datasets. Thanks a lot.
Thank you so much sir. Your explanation has taught me enough about the time series model. Thank so much from Bhutan.
thanks
fundamentally clear timeseries concept🙌
The best explanation of time series. It's totally worth the 53 mins. However I have a doubt, when he said about the error in the MA method. Equation what you meant was: xty = slope*xt + intercept. and the error = xty - xt. Kindly correct me if I am wrong.
Thanks
@@AnalyticsUniversity ? correct or no
While explaining the White Noise series you said if the series is white noise then we will not use any time series forecasting but in Moving Average model you said the error term is a white noise.
Can you please explain this, I am but confused, regarding the use of Time series forecasting model when we have a white noise process .
Great conceptual explanation of time series. I particularly loved the questions you raised and responded to. They are vital to understanding the concept yet so rarely appear in other sources. Thank you.
thanks
Good video. Nice clear explanations. I am taking time series/forecasting class and have tests coming up soon and this was a good summary of concepts. We use SAS in this class, I wish we used R as it is much easier
Best time series video ever.
Thanks! Please support us on Patreon for more quality free content
www.patreon.com/user?u=2969403
this is really a good explanation of time series analysis for beginners .i learn a lot from this video..thank u very much sir
Excellent tutorial. The instructor did a great great job. Kudos!
Thanks! Please support us on Patreon for more quality free content
www.patreon.com/user?u=2969403
This tutorial is so good! Many thanks and gratulations for this perfect work! Time series can now handled easy ;)
Thanks
I am new to time series, your video was helpful, it had all the concepts in one place and it was an hour well spent. However I don't think differencing and differentiating are the same thing. Differencing is the process of taking a difference of series from itself as various lags. I am not sure if its about taking a derivative (like you hinted) ...
One of the best video for learning econometrics basics... Thankyou soomuch.
At 32:04 you have mentioned that differencing is actually differentiating. Isn't it actually subtracting with the order of the backward shift operator? Say first order differencing is actually yt - yt-1.
the best explanation of time series but too many ads in one video.
are ads random or do content providers get to choose the frequency? For some reason, this video felt like it had a ridiculous number of ads.
Much appreciated efforts has been made to provide robust understanding of the subject matter. Just few questions: 1) If we just look into a variable in an isolation (i.e stock price) etc on the basis of historical trend, its quite possible that this trend will not gonna happen in the future time period. For this problem, I've seen many people working on the elimination of trend. So, if we are able to remove trend, then still can it be possible to forecast a variable (stock price) ?
Quite thoroughly explained. Thank you!
thanks for watching. Wish you a happy new year in advance!
thank you so much for explaining this so clearly! It's much much appreciated!
THANKS
Ek number. Best & crystal clear explanations. Keep up the good work.
Thank you so much sir!! So far the best video on time series
This is very helpful. I have a question though. At 24:47 what is Phi 1 and Phi2 and so on. How is that calculated.
Hello Sir,
I have a question about forecasting. Should plan corrections be determined during forecasting? Or is it not necessary to determine them? Why is there an extrapolation? An extrapolation is absolutely necessary.
At 22:10, for white noise you told that the average is the best forecast. But isn't average = 0, for such white noise time series?
very excellent presentation
can you tell me how to run this code and how would i get the dataset
which you have used in example
A very easy and simple way of time series concepts explanation.. Great job
Enjoyed the first 30 minutes and got concepts of time-series clear. After 30 minutes it was not very clear for me to understand. Thanks
22:00 mins - If white noise is purely random, then how come it has a 0 mean and a constant variance? A specific mean and a constant variance makes a term determinable or predictable, right? Kindly help me on this. Thank you :)
Not at all. Mean is irrelevant in discussing if a phenomenon is random, what's important is variance and for a non-random phenomenom, that variance should be 0. If the phenomenom does not vary, has variance 0, then it is deterministic and vice versa.
Take a fair coin, give tails the value 0 and heads the value one. Then the outcome of one toss has a variance of (0^2)*0.5+(1^2)*0.5=0.5 The variance of this phenomenon is 0.5 it iss constant and known, but the result of the toss is still random and nobody can predict it with certainty.
Another example, suppose you go to a casino and you play roulette, you bet 10$ on a number between 1 and 36 and if you win you get 35*10$=350$. The variance of your earnings is (350^2)*(1/36)+((-10)^2)*(35/36) it's constant for every round of roulette, you know it beforehand but you will never be able to guess the outcome of a roulette roll with certainty EVER.
@@PolKsio thanks man! confusion is cleared now!
Great work mate! easy to understand
best ts video ever found on youtube
madhu kumar thanks
Ohhhh... hey, there's a video in these ads!
Just chilling, this is a great video kids.
Hello sir
I want to thank you so much for this video
the effort you put into this video incredible. it is so easy to follow and understand
Thank you for my bottom of my heart
thanks
What if both ACF and PACF have spikes cut off to zero? Is that possible? Because I am running time series on R and my graphs are showing cut off to zero for both ACF & PACF.
If the data is completely random still we can predict future values from it, right ? i am currently working on a project which involves this concepts.
best explanation for time series .. Thank you very much sir
because the data there is a trend in the diff process, it turns out that in the second diff the new data does not show a trend ... but when forecasting try diff 1 is obviously smaller 'MSE' ... how about that? please explain
Where can I learn algorithms that are applied in Time series forcasting?
21:15, why would variance be constant?
Amazingly explained sir
Hi , For Strictly stationary you told mean , variance and covariance are time invariant, that is constant. For weakly stationary also you have mentioned mean, variance should be constant. Can you please help me on this ?
Great Video :)
1) What should we do if the residual is not random and has pattern.
2) Can you please share the dataset and ppt.
Thanks! Please support us on Patreon for more quality free content
www.patreon.com/user?u=2969403
In moving average model how do you get E(t) when you are forecasting Y(t) ?
Very easy to grasp and very well explained. Thanks a lot for the video!!
Great explanation by Dr Ray...
can i do ARIMA for mortality data of interval 5 years and only have 5 data point.
Whar if the dependent variable is a binary variable, ie. it has a value of 0 or 1?
Very nice explanation. I appreciate your kind effort.
for arma model
ok p denotes to past value..fair enough
but what does q stand for, so do we just took random alphabet to refer to random error term
Really nicely explained... Thank you so much sir 😄
How can I download the dataset used in case study i.e. death_Age.csv
ACF 36:25
Please please please declare your values. Is beta a constant? integer? real? is Phi a constant? It would be helpful to use proper mathematical notation to make it clear!
This is very good wow! But what about statationary? Can u say something about that?
By definition I time series has regular time intervals but how do I work on time series with irregular time intervals like sensor data coming at irregular time? Can I still use ARIMA, ARMA, MA models ?
How will I plot the data, fit model and forecast on the same plot using R?
Regarding white noise series,You have mentioned that mean of the series will be 0 for white noise series and then later told that time series shouldn't be applied and take the average of the series..If mean is 0 how does it matter of calculating average
I have the same question
This video is very helpful. I learned a lot. Thank you for sharing!