Intuitively you are adding more variables to the model so the model would have a better explanation of the data. At the least, R^2 won't decrease because you can set coefficient of new-added variables to 0 if it "harms" the model. But in general though useless, those variable would still have minor explanation of the data so R^2 would increase. But that often leads to overfitting, consider extreme case where you have as many independent variables as data points and the model is able to fit every single one of data point, and R^2 is 1 in that case, nevertheless it would be a useless model.
A good video but what most of you guys are not clarifying is , how do i know the model is good using the adjusted r2 . Like what is good adjusted r2? I have run the multiple regression on excel already with so many independent variables. so am stuck now, i cant comment whether its a good model or not using the adjusted r2. From which value to which value ? Thank you for responding
good day sir, I just wanted to ask if an independent variable is not significant or does not have an explanatory power to the model but when removing it lowers the adjusted r-square what does this imply? so far the reason that i know the reason is because the t-statistic is greater than one. With this information, what can we infer?
How do you know if the new variables added are not correlated to the target feature? If adding a variable to the equation increases the R2 value, isn't that evidence that there is potential correlation?
Which of the following tells us how strong the relationship is between two variables? IS THE ANSWER E?! a) the slope of a line b) the intercept of a line c) the coefficient of determination d) the coefficient of correlation e) both C and D are correct
![“อ.เบียร์ คนตื่นธรรม” มาตามคำเรียกร้อง แหกศาสตร์ฮวงจุ้ย เตือนสติอย่างมงาย | แฉ 7 พ.ย. 67 [1/3]](http://i.ytimg.com/vi/5fc4S3xBNfc/mqdefault.jpg)
amazing video, I was so confused by this
Thank you for posting this! It help me quite a bit.
Very fine and understanding vdo
Simply outstanding!
It is a helpful video. Many thanks, Prof.
thankyou for such a nice explanation.
Marvellous Video,got all the concepts cleared.
The best on yt
what a great video Thank You Sir
Very very well explained. Thankyou ❤️ from 🇮🇳
Thank you so much
Great video! However, why does the R^2 value increase with the number of independent variables?
Intuitively you are adding more variables to the model so the model would have a better explanation of the data. At the least, R^2 won't decrease because you can set coefficient of new-added variables to 0 if it "harms" the model. But in general though useless, those variable would still have minor explanation of the data so R^2 would increase. But that often leads to overfitting, consider extreme case where you have as many independent variables as data points and the model is able to fit every single one of data point, and R^2 is 1 in that case, nevertheless it would be a useless model.
amazing
It would have been great if the links to the related video were on the description.
Very good explanation, understand upon your explanation. !
awesome explanation. thanks a million.
A good video but what most of you guys are not clarifying is , how do i know the model is good using the adjusted r2 . Like what is good adjusted r2? I have run the multiple regression on excel already with so many independent variables. so am stuck now, i cant comment whether its a good model or not using the adjusted r2. From which value to which value ? Thank you for responding
Great video! Very helpful for my data analysis project
Thank You So Much Sir it's very clear and understandable
Thank you sir.
👍👍
great! thanks Prof.
good video, really helpful, thanks
good day sir, I just wanted to ask if an independent variable is not significant or does not have an explanatory power to the model but when removing it lowers the adjusted r-square what does this imply? so far the reason that i know the reason is because the t-statistic is greater than one. With this information, what can we infer?
How do you know if the new variables added are not correlated to the target feature? If adding a variable to the equation increases the R2 value, isn't that evidence that there is potential correlation?
Thank you!
but how does it identifies as a useful or useless predictor ?
Hi Dr Ryan,
If my R2 is 0.30 and my RMSE is relatively very low, consider the RMSE below the average, so should I consider this model to be good.
Which of the following tells us how strong the relationship is between two variables?
IS THE ANSWER E?!
a) the slope of a line
b) the intercept of a line
c) the coefficient of determination
d) the coefficient of correlation
e) both C and D are correct
there may be a mistake, I think R2 can be less than zero, right? Model is worse than average guess?
so R2_adj is always lower than the R2
Thank you for the beautiful video :-)
What is your name by the way :-)
what is predicted r2
I have heared from my professors adjusted r2 value is always less than r2 value.why is it so?
Since it overcomes the dependency i.e. misleading accuracy by inc in independent variables that is why this might happens.
I generally write R-squared lol
Sathi baneko xu waps garnus la
capo
Thank you so much