Statistics 101: Nonlinear Regression, The Quadratic Model

In this Statistics 101 video, we learn about the nonlinear quadratic model. To support the channel and signup for your FREE trial to The Great Courses Plus visit here: ow.ly/xVD030fiZ8S
My playlist table of contents, Video Companion Guide PDF documents, and file downloads can be found on my website: www.bcfoltz.com
Happy learning!
The Great Courses Plus is currently available to watch through a web browser to almost anyone in the world and optimized for the US, UK, and Australian markets. The Great Courses Plus is currently working to both optimize the product globally and accept credit card payments globally.
#statistics #regression #machinelearning

[@pavittarsingh5870]

I am happy the channel is still active, and videos are being uploaded. I hope you keep it up... The tutorials are great, really love them. Tbh, I have tried a few out there but these were the awesomest from all I can see. :) In further, I would request you to, please upload the slides (pdf would be fine), if possible. Its hard to make notes at the same time and enjoy the video at the same time, I feel like I am going to miss on something.. Thanks.

[@mohammedalsubaie3512]

I was that quite student in the class without any participation, but now! Oh man I even stand up in front of the class and explain what everything comes together. Thank you from the bottom of my heart

[@coscinaippogrifo]

Bless you for these amazing videos! You're making my quarantine enjoyable and useful :)

[@theos.6229]

amazing like always...your videos are really made to facilitate understanding...Great Job Sir!

[@fredygonzalocarvajalserran1654]

Nice video, thanks...Excellent explanation.

[@swghavoc]

Wow! Thank you for making it understandable!

[@bensmith6987]

This is much better quality both in delivery the content and lay out. Thank you so much. Should have a course on udemy. Then i would have taken it 100%.

[@sintiacarolina1122]

really easy to understand. thank you, it helps me alot. :)

[@tantruongkhanh1312]

Thank you PROF

[@nawilliam2754]

Great video. Indebted to you Brandon.

[@karnam7444]

Hi Brandon, do you know how I can manually calculate sum of square of quadratic factors such as A^2, B^2 etc?

[@JuanCarloshgo]

hey, I love your videos, do you plan to do something on bayesian statistics??

[@pierre-louispaugam5773]

Hello Brandon I have one question. Do you plan on making an "ANCOVA - Understanding the calculations" video one day ? :) Thank you in advance !

[@bobjohnson4318]

Hi Brandon, a request. I am interested in understanding the relationship of Design of Experiments, like a Central Composite Design, with Regression. Are they different subjects, or is Regression a component of DOE? Also, I think I understand interaction effects, but quadratics --- I cannot grasp them yet. I really like how you slow down and explain what is going on, answering all the questions that a novice would ask themselves as they went through the process. We like understanding what the calculations are, even though we will ultimately let the software do it. Any thoughts on this are appreciated, or if you want to ask me for any clarification, I hope I am explaining it right.

[@tnl6349]

Hi Brandon Thanks for this great video. I was wondering if it was possible and if yes how would look the regression equation for a quadratic model with polynomial x with multiple independant variable? Thanks

[@subratasutradhar3599]

Which software did you use to do the calculation?

[@charlesschwer1792]

Great video! In reality, due to job turn over, there would not be as many salesmen still working after five years compared to the number of salesmen who have worked less than three years. So the density of observations should show more than half who had 3.5 years or less experience. Unless, there is almost no job turn over.

[@edgarbahilorodriguez3066]

Hi! I am sorry but using a predictor^2 does not change your OLS problem to a non-linear one. The vector of least-squares estimators a1,b1,c1, ... depends in a linear way on the vector of response variables y1,y2,y3,…,yn. You can not say that a quadratic model is not linear because it can be expressed as a linear combination of the predictors. I think that you need to clarify that even that you are fitting a non-linear relationship between the inputs and the outputs from the statistical point of view the problem is still being linear. BR

[@raymondgeorge1545]

Thank you Brandon it was really helpful in my professional transformation. But When I checked the maximum point is 380.49..... so is it fine to take only few 4 number after decimal for accuracy 🤔?

[@KhaLed-pb4pu]

how did you decide that b1 is the x term and b2 is the xsquared term?

[@user-mt2pm1yx7i]

Super

[@ccuuttww]

sometimes u may find multi min if your curve have more argument Its can a same thing in gradient descent

[@BrandonFoltz]

Absolutely! This was a simple example. I will get to gradient descent here soon. Thanks Jill!

[@muratcanakdogan26]

Hello y=1/(Ax+B)^2 and y=A/(x+B) least square table fitting How to solve?

[@ashrukhtf3183]

Can you please share one example with python for non linear regression example

[@lauAlv]

"now, don't freak out, this is not that bad". HOW DO YOU KNOW US SO WELL? lol.