2:23 Statistical Models: Notation 8:10 Equivalent Linear Regression Notation 12:22 Understanding Alternative Regression Notation 17:25 Generalized Alternative Notation for Most Models 23:33 Forms of Uncertainty 29:26 Systematic Components: Examples 40:08 Overview of Stochastic Components 44:30 Choosing Systematic and stochastic components
Hello Professor King, and greetings from Germany! For a seminar, I had to read your chapter on "a language of inference", from your 1998 book without much knowledge about statistical methodology. Let's say it was rather... hard to follow being new to the field (because, as you know, it is a quite densely packed chapter) - but this video already helped me immensely in unraveling the meaning of this new language. Thank you for that!
Such an excellent & wonderful course Professor! Thank you for doing this - it truly is helping me. Just had a question - What is the difference between error and bias? I understand we measure the error in terms of how 'away' it is from the actual data, but that seems to me the same as 'bias'. If it is not the same, then how do we measure bias?
Error consists of the combination of all unknown contributions to the outcome. Bias consists of estimable contributions to the outcome. The bias is systematic and you can try to account for it in your discussion/interpretation. The error is something you can warn of in the discussion/interpretation but you cant make an attempt to account for. That is how I have explained it. But I'm also here and viewing to try to improve my teaching of Quant Methods because I feel sure Dr. King knows more than me. So if I am wrong I hope he corrects.
You are wrong. A histogram is a good judge of a distribution being normal, by definition. You are a poor speaker. You have deceived yourself. I suppose what you meant to ask was, is a histogram a good judge of whether the source distribution is normal, as a producer distribution that produced the final curve. You have done nothing in the question to verbally distinguish the generating distribution from the final distribution as a collection of points. You were so anxious to create a trick question that you didn't outline the question correctly. -5 points for you
2:23 Statistical Models: Notation
8:10 Equivalent Linear Regression Notation
12:22 Understanding Alternative Regression Notation
17:25 Generalized Alternative Notation for Most Models
23:33 Forms of Uncertainty
29:26 Systematic Components: Examples
40:08 Overview of Stochastic Components
44:30 Choosing Systematic and stochastic components
I love this. I'm studying Political Science in Peru. I hope you continue with this.
Thank you very much Prof. King.
Your video is a blessing
Hello Professor King, and greetings from Germany! For a seminar, I had to read your chapter on "a language of inference", from your 1998 book without much knowledge about statistical methodology. Let's say it was rather... hard to follow being new to the field (because, as you know, it is a quite densely packed chapter) - but this video already helped me immensely in unraveling the meaning of this new language. Thank you for that!
Excellent!! Thanks!
Sería hermoso que alguien subtitulara esto
Such an excellent & wonderful course Professor! Thank you for doing this - it truly is helping me.
Just had a question - What is the difference between error and bias? I understand we measure the error in terms of how 'away' it is from the actual data, but that seems to me the same as 'bias'. If it is not the same, then how do we measure bias?
Error consists of the combination of all unknown contributions to the outcome. Bias consists of estimable contributions to the outcome. The bias is systematic and you can try to account for it in your discussion/interpretation. The error is something you can warn of in the discussion/interpretation but you cant make an attempt to account for.
That is how I have explained it. But I'm also here and viewing to try to improve my teaching of Quant Methods because I feel sure Dr. King knows more than me. So if I am wrong I hope he corrects.
You are wrong. A histogram is a good judge of a distribution being normal, by definition. You are a poor speaker. You have deceived yourself. I suppose what you meant to ask was, is a histogram a good judge of whether the source distribution is normal, as a producer distribution that produced the final curve. You have done nothing in the question to verbally distinguish the generating distribution from the final distribution as a collection of points. You were so anxious to create a trick question that you didn't outline the question correctly. -5 points for you