(10 intermediate revisions by 3 users not shown)
Line 1: Line 1:
 
 
<center><font size= 4>
 
<center><font size= 4>
 
Comments for [[ Ness slecture 2014|Neyman-Pearson: How Bayes Decision Rule Controls Error ]]
 
Comments for [[ Ness slecture 2014|Neyman-Pearson: How Bayes Decision Rule Controls Error ]]
Line 5: Line 4:
 
</font size>
 
</font size>
  
A [https://www.projectrhea.org/learning/slectures.php slecture] by [[ECE]] student Dennis Lee
+
A [https://www.projectrhea.org/learning/slectures.php slecture] by [[ECE]] student Robert Ness
 
+
 
</center>
 
</center>
 
----
 
----
Line 12: Line 10:
 
Please leave comments or questions below.
 
Please leave comments or questions below.
 
----
 
----
==Review by ...==
+
==Shaobo Fang's Review==
...
+
 
 +
Possible a minor typo at first line:    魔钟-->某种? corrected.
 +
 
 +
What's Impressive:
 +
 
 +
This selecture is simply impressive. Author focused on Hypothesis testing, and introduced LRT, Bayesian Test and Neyman-Pearson (UMP: Uniformly Most Powerful).
 +
 
 +
Many concepts are accurately described in Chinese, which is amazing. Even if I have taken the STAT course, I did not know the corresponding Chinese name to e.g. LRT, so the author indeed helps me a lot when I read Chinese texts on this topic in the future.
 +
 
 +
At the very end of the text, author also introduced a very interesting example, which helps reader understand the concepts better.
 +
 
 +
What's Covered:
 +
 
 +
The author covered all important concepts in Hypothesis Testing in a great way. For the LRT test, I guess in order to be more accurate:
 +
 
 +
<math> \lambda(X) = \frac{sup L(x|w_0)}{supL(x|w)}</math> 
 +
   
 +
Although it is already great, it would be even better if author can also briefly explain Power Function and Size of LRT.
 +
 
 +
=Tian's reply=
 +
 
 +
Interesting  topic. It's very surprising that the author can compose so great Chinese tutorial. The tutorial contains both theory and an application, which can really lead the reader to understand and gain a intuition on how it works.
 +
 
 +
Might be more interesting if talking a little about a changing k, basically ROC curves and how that could be further developed from this topic.
  
 
=Author's reply=
 
=Author's reply=
...
+
Typo corrected, thanks.
 
----
 
----
  

Latest revision as of 16:37, 12 May 2014

Comments for Neyman-Pearson: How Bayes Decision Rule Controls Error

A slecture by ECE student Robert Ness



Please leave comments or questions below.


Shaobo Fang's Review

Possible a minor typo at first line: 魔钟-->某种? corrected.

What's Impressive:

This selecture is simply impressive. Author focused on Hypothesis testing, and introduced LRT, Bayesian Test and Neyman-Pearson (UMP: Uniformly Most Powerful).

Many concepts are accurately described in Chinese, which is amazing. Even if I have taken the STAT course, I did not know the corresponding Chinese name to e.g. LRT, so the author indeed helps me a lot when I read Chinese texts on this topic in the future.

At the very end of the text, author also introduced a very interesting example, which helps reader understand the concepts better.

What's Covered:

The author covered all important concepts in Hypothesis Testing in a great way. For the LRT test, I guess in order to be more accurate:

$ \lambda(X) = \frac{sup L(x|w_0)}{supL(x|w)} $

Although it is already great, it would be even better if author can also briefly explain Power Function and Size of LRT.

Tian's reply

Interesting topic. It's very surprising that the author can compose so great Chinese tutorial. The tutorial contains both theory and an application, which can really lead the reader to understand and gain a intuition on how it works.

Might be more interesting if talking a little about a changing k, basically ROC curves and how that could be further developed from this topic.

Author's reply

Typo corrected, thanks.




Back to Ness slecture 2014

Alumni Liaison

Basic linear algebra uncovers and clarifies very important geometry and algebra.

Dr. Paul Garrett