I'm speechless how a video of 20 min explained to me everything I was struggling with for a half of year Thank you a lot for making it so simple and clear. I would love more teachers to explain the basics like this.
THanks for the amazing video Doug! My only question is under what circumstance do we exponentiate? You used this when explaining constants in Reg1 and again in Reg3 when explaining the male/dummy variable = 0. Looking at other Regression output tables, I am not sure I can identify when the best time to do that is. Is there a rule of thumb? Thanks in Advance!
Hello Doug, Very nice video. I learned a lot in this short 20 min. I was so looking for this. Thanks a ton :) But I have one doubt regarding column 3, interpretation of Beta4. You took the exp of .461 which is 1.59. And you said 59% higher wages for male. Isn't it should be 1590 pesos higher earning for male than female. Please let me know.
+Mustafa Bohari Thanks for the kind words! In this situation the dependent variable is logged and the independent variable isn't. The log wages for males are 0.461 higher than the log wages for females, holding education and experience constant. That means males are expected to have wages exp(0.461) times higher than females. And because exp(1.461 = 1.59, that means they will be on average 59% higher. It's definitely not an additive effect of 1590 pesos.
Hello Doug, First of all, thank you very much for your video, which is very clear and helpful, as many people have said. I just have one question, what is the point of having both experience and experience^2 ? Trying to understand the logic behind your regression. If you have time to reply, you would solve this mystery haha. Cheers
As far as I understood it, experience^2 signifies the marginal effect of more experience. Because it is negative, it means that there is a decreasing marginal effect of experience on wages; Another year of experience has a weaker effect on your wage, as the year of experience before.
The researcher decided that the relationship btwn experience and wage was non-linear, hence we needed the exp^2 to show the decreasing marginal benefit (slope increasing at a decreasing rate). Hope this helps
I'm speechless how a video of 20 min explained to me everything I was struggling with for a half of year
Thank you a lot for making it so simple and clear.
I would love more teachers to explain the basics like this.
This is one of the best videos for explaining regression that I have seen. Thanks, man! You are a lifesaver!
This video concisely delivers the very core part. Truly a great prep/best refresher!
Thank you so much, Doug!
What a great video. im prepairing for a exam on this meterial. so happy that someone sheds some light to it. I would love to see more
Very detailed and crystal clear explanation. Thanks so much!
THanks for the amazing video Doug! My only question is under what circumstance do we exponentiate? You used this when explaining constants in Reg1 and again in Reg3 when explaining the male/dummy variable = 0. Looking at other Regression output tables, I am not sure I can identify when the best time to do that is. Is there a rule of thumb? Thanks in Advance!
really good, thank you for your time and efforts to make this wonderful video happen.
Greatest regression table video ever !!
Hello Doug,
Very nice video. I learned a lot in this short 20 min. I was so looking for this. Thanks a ton :)
But I have one doubt regarding column 3, interpretation of Beta4. You took the exp of .461 which is 1.59. And you said 59% higher wages for male. Isn't it should be 1590 pesos higher earning for male than female. Please let me know.
+Mustafa Bohari Thanks for the kind words!
In this situation the dependent variable is logged and the independent variable isn't. The log wages for males are 0.461 higher than the log wages for females, holding education and experience constant. That means males are expected to have wages exp(0.461) times higher than females. And because exp(1.461 = 1.59, that means they will be on average 59% higher. It's definitely not an additive effect of 1590 pesos.
Thank you very much for this clear and well explained video ! Was very useful
Regards
Very informative. Thank you very much!
Thank you so much!
Thank you soooo much for this video! Literally a life saver! But what is th reason behind taking the log of the dependent variable?
Thanks , it is well explained
Thank you very much for the lesson!
can I ask that at 8:47, why it's 1.059? Thank you so much!
oh right Exp() Thank you! your explanation is really helpful!
6:30 This is what i want.
Hello Doug,
First of all, thank you very much for your video, which is very clear and helpful, as many people have said.
I just have one question, what is the point of having both experience and experience^2 ? Trying to understand the logic behind your regression. If you have time to reply, you would solve this mystery haha. Cheers
As far as I understood it, experience^2 signifies the marginal effect of more experience. Because it is negative, it means that there is a decreasing marginal effect of experience on wages; Another year of experience has a weaker effect on your wage, as the year of experience before.
The researcher decided that the relationship btwn experience and wage was non-linear, hence we needed the exp^2 to show the decreasing marginal benefit (slope increasing at a decreasing rate). Hope this helps
Great
Good lesson!
the best
Thanks
Just let us know what the numbers tell us, not calculating
eh
Sorry, hard to follow