I was just as confused as you stated you were when I was first introduced to this topic. You gave me a eureka moment and suddenly it is clear. Thank you.
I have worked with logit models a lot (binomial, multinomial, ordered). This video is so useful and simply expressing the transition from linear regression to logistic one. Thanks.
Will u please help me ..em Ms economics studnts and i have issues in my thesis .i don't knw what method to apply for estimation ..if u r willing to help me i'll tell u in detail about my thesis.
Nice graphics, but if I was seeing it without prior knowledge, I would be deeply confused by what appears to be a plot of ln (p/(1-p)) on the Y axis. While p is forced to follow the sigmoid shape, the ln (odds) range from negative to positive infinity, and the prediction will be a straight line, not a curve. So I cannot recommend this video without a clear explanation of that step.
Thank you for making it easy to understand this concept. How do we fit this sigmoid curve for best fit, do we have to change its shape, or give it offset ? Some sort of that example would have made it more interesting. Thanks alot again. It was quite helpful.
A link to the next video in the description would be a nice touch, since you're referring to it by the end of the video ;) Thanks for the video. And good job on the voice, it's not easy to do, and you're very easy to follow.
Hi ondskabenselv, this is lecture form the Data Science A-Z course which is hosted on superdatascience.com or on Udemy. But we are not putting the whole course here.
It was a very good tutorial. Thanks a lot Kirill for that. Been always a follower of your classes. Have a small query. Being a beginner into data science field, do I need to know how does the mathematical functions like sigmoid function or the MLE works mathematically in Logistic regression? Or will the information imparted in this video related to Log. Reg. is sufficient enough to sustain in this field? Please suggest. P.S. The mathematical derivations seems to be a bit complicated
Our attempt is to find a function which can best fit the points in the space. Sigmoid function expressed in logarithm terms is one of the best fit for this. That is the reason we call it Logistic regression . As stated in the video note It is the appropriate regression analysis to conduct when the dependent variable is dichotomous (binary).
Hi darek4488! Sad you didn't like it. We are trying our best to provide interesting free materials here on RUclips so tune in for other videos. Have a great day! SDS team
You are a Good Tutor but content is very Basic .. No Solved Examples ,,, Purpose not solved. Please also add Learning Outcomes at the beginning so that we can save our time.
by far the best explanation I found on youtube
I was just as confused as you stated you were when I was first introduced to this topic. You gave me a eureka moment and suddenly it is clear. Thank you.
Learn more about logistic regression with R
drive.google.com/file/d/1qcq_186AMe2XK9aNiSLxLbvXlAmryWXX/view?usp=sharing
Very much simplified good explanation . Thanks. I would love to see more machine learning algorithms.
Thanks for tuning in!
I have worked with logit models a lot (binomial, multinomial, ordered). This video is so useful and simply expressing the transition from linear regression to logistic one. Thanks.
Will u please help me ..em Ms economics studnts and i have issues in my thesis .i don't knw what method to apply for estimation ..if u r willing to help me i'll tell u in detail about my thesis.
So smart way to explain this question in my mind for a long time. Thank you!
Loved it. Thanks. 👏
You are most welcome!
Nice graphics, but if I was seeing it without prior knowledge, I would be deeply confused by what appears to be a plot of ln (p/(1-p)) on the Y axis. While p is forced to follow the sigmoid shape, the ln (odds) range from negative to positive infinity, and the prediction will be a straight line, not a curve. So I cannot recommend this video without a clear explanation of that step.
That was wonderful, informative and interesting demonstration. Thank you so much!
Thank you for making it easy to understand this concept. How do we fit this sigmoid curve for best fit, do we have to change its shape, or give it offset ? Some sort of that example would have made it more interesting. Thanks alot again. It was quite helpful.
A link to the next video in the description would be a nice touch, since you're referring to it by the end of the video ;)
Thanks for the video. And good job on the voice, it's not easy to do, and you're very easy to follow.
Hi ondskabenselv, this is lecture form the Data Science A-Z course which is hosted on superdatascience.com or on Udemy.
But we are not putting the whole course here.
That was a very good explanation! Thanks
So well explained thanks. I liked the part that you said "So this is a model if front of you right there" :)))
Thanks for your comment Sepide!
Learn more about logistic regression with R
drive.google.com/file/d/1qcq_186AMe2XK9aNiSLxLbvXlAmryWXX/view?usp=sharing
Very very nice explanation
Very good and clear explanation. Thanks.
You are most welcome Atanu!
I get it now. Thank you so much for this excellent tutorial!
You are most welcome Tim!
Very good but i wished that you work more with math and ln(p/1-p) etc
Awesome explanations. Thanks for creating such a excellent presenation with clear explanation.
You are most welcome Uttam!
Great Explanation
Best video thank you so much! I hope some other concepts of Machine Learning in the upcoming days
It was a very good tutorial. Thanks a lot Kirill for that. Been always a follower of your classes. Have a small query. Being a beginner into data science field, do I need to know how does the mathematical functions like sigmoid function or the MLE works mathematically in Logistic regression? Or will the information imparted in this video related to Log. Reg. is sufficient enough to sustain in this field? Please suggest. P.S. The mathematical derivations seems to be a bit complicated
Depends on what is your goal Santanu.
Sustain in the field quite a vague goal
Hi, Thanks so much. It's nice, clear and easy to follow. Waiting for your next video..
You are most welcome Helio!
Great video! It was very helpful and gave me some intuition on logistic regression. Thank you.
You are most welcome Maroon, thanks for tuning in!
where's the application video?
thanks man
Excellent, thank you.
You are almost welcome Jamie!
Speaking about linear regression, presented here: how can experience be negative? Please, check the plot again.
Could you please let us know what moment exactly you are talking about. Thanks!
This was a great explanation
Learn more about logistic regression with R
drive.google.com/file/d/1qcq_186AMe2XK9aNiSLxLbvXlAmryWXX/view?usp=sharing
BEST explanation. Thank you
Learn more about logistic regression with R
drive.google.com/file/d/1qcq_186AMe2XK9aNiSLxLbvXlAmryWXX/view?usp=sharing
Good simplified explanation
Thank you, Arshad!
Thanks for the nutshell video. Great way to refresh my knowledge :)
You are most welcome KoenigNord!
Why do we need to use sigmoid function only?
Hi Sudhiir,
This is how Logistic Regression works
Our attempt is to find a function which can best fit the points in the space. Sigmoid function expressed in logarithm terms is one of the best fit for this. That is the reason we call it Logistic regression .
As stated in the video note It is the appropriate regression analysis to conduct when the dependent variable is dichotomous (binary).
great explanation...
so satisfied
This is nice and simple explanation of a complicated problem...
You are most welcome Arun!
You completely failed to explain the mathematics behind it and how to obtain a function of probability from some example data points.
Hi darek4488!
Sad you didn't like it. We are trying our best to provide interesting free materials here on RUclips so tune in for other videos. Have a great day!
SDS team
Learn more about logistic regression with R
drive.google.com/file/d/1qcq_186AMe2XK9aNiSLxLbvXlAmryWXX/view?usp=sharing
You are a Good Tutor but content is very Basic ..
No Solved Examples ,,, Purpose not solved.
Please also add Learning Outcomes at the beginning so that we can save our time.