How is it a measure of dispersion or variability? Suppose, I have 2(upwards) as a difference(Yactual - Ymean = 2) and 3(downwards) as a difference(Yactual - Ymean = 3) . Then 2 power of 2 i.e 4 + 3 power of 3 i.e 9. That is, 4+9 is 13?! So, how does this imply variability or dispersion. Yeah. A lot of books talk about converting negative to positive. But that is not the correct logic. Errors are magnified, in fact, and may imply distortion.
![เปิดบ้าน โคตรสวย ป๋องกพล รู้จักตั้งนาน เพิ่งรู้ว่ารวย!!! l [Nickynachat]](http://i.ytimg.com/vi/tmgCF_2HfYI/mqdefault.jpg)
👉🏻 Sign up for Our Complete Data Science Training with 57% OFF: bit.ly/2TR8Keb
Probably the best visual explanation on the Internet for a non statistical person. Wish many person find this channel.
This is the most underrated video ever!!
you made it very very clear. thank you...
You are welcome!
Short and precise 🫡
Great video man.
Do you have any idea where does Sum of square due to curve fits in here?
Loved this video! Do we have pre set parameters for these terms? Ex: what would be a good sum of squares error?
Is it ok to speculate on what explains the residuals?
What is orthogonal sum of squares
How is it a measure of dispersion or variability? Suppose, I have 2(upwards) as a difference(Yactual - Ymean = 2) and 3(downwards) as a difference(Yactual - Ymean = 3) . Then 2 power of 2 i.e 4 + 3 power of 3 i.e 9. That is, 4+9 is 13?! So, how does this imply variability or dispersion. Yeah. A lot of books talk about converting negative to positive. But that is not the correct logic. Errors are magnified, in fact, and may imply distortion.
my head is still scrambled lol
Thanks for nothing. I got nothing
You sound like this: 🤓
This is plainly wrong! Regression does not imply causation