| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Stop wasting time looking for files and revisions. Connect your Gmail, DriveDropbox, and Slack accounts and in less than 2 minutes, Dokkio will automatically organize all your file attachments. Learn more and claim your free account.

View
 

lec2

Page history last edited by PBworks 12 years, 6 months ago

survey questions from lecture 2

 

Q: I am not familiar with the {} notation - could provide a brief explanation? Thanks!

A:(Ted) { } could mean different things.  Here I am using it to denote the variance function.  I.e., var{x}=sum of (x-mean x) quantity squared.  (ask

me in class if this isn't clear)

 

Q: I am unsure how to approach the proofs. Should I feel comforted by their existence, as I

now know for sure that what we are working on has a basis in logic, or should I try to learn/do them?

 

A(Ted): I would say yes...see if you can follow the steps of the proofs.  Some are more important than others.  For example, if you understand the proof for

the variance of b1, then you are likely to retain the concept of where the standard error of regression coefficients comes from.

Q: using this command in stata (from lab assignment 1 sheet) -collapse (mean) occ_fem=sex occ_ave=wage (count) occ_n=sex, by (occ)- occ_fem

is supposed to be the proportion of women in the occupation, right? If so, how does STATA know only to pull the female values from the sex var?

 

A(Ted): it is just calculating the mean of sex by occ.  I.e., just as someone might calculate the percent hispanic by state etc.  So it is just taking averages.

Q: What is the NWK book that the slides often refer to? Is this something we need to read in addition to the online text?

A:(Ted) Netter, Wasserman , and Kutner, Applied Regression Analysis.  A standard book  for a course like this.  You do not need to read it, but I have referenced it when I have used it to write the lectures.

 

comments:

I found the class very helpful in clarifying certain concepts I was having trouble with. However, I still need to go back and compare the textbook reading with my class notes before I will feel completely comfortable. Some of the reason for this, I believe, is that the current textbook uses different symbols for the statistical concepts than last semester's used, so I am often "translating" the symbol into English and then back into the symbol from the previous class. I'm not sure this is necessarily a bad thing, though, although it slows me down a bit. What it does do is make me restate everything verbally, which probably helps me understand it better.

 

Ted: There is nothing wrong with translating the symbols into English...

It seemed like you were speaking too fast. At some points, by the time I processed and understood what you said, you were onto something else and I had missed a something in the middle. I did eventually figure it out after class when I looked back over my notes and the lecture slides, but it was difficult to follow during class. Also, I have difficulty when you are reading off formulas from the slides or board. For example, "xi sub y quantity squared". It took me a few times to understand what you were saying, but it is very helpful when you physically pointed to what you were talking about. Given all that, I do understand that you can't go too slow because other students in the class already know some of this material really well.

 

Ted:  Thanks...I will try to point to the part of the formula as I say it.  In some sense, it is redundant to say the formula when it is in the slide, but it slows me down, which is good.  Does it help to look over the lecture slides before class?

 

I understood it in between so-so and well. I think the main ideas were all clear. But I couldn't follow all the proofs that fast. I need to go back and look at it more slowly.

I can methodically work through the various sums of squares to get to the end point, but this is not intuitive. If you asked what was the difference between the total sum of squares and the sum of squares due to the regression, for instance, I'd draw a blank. I can look at the formulas to figure it out, but it isn't committed to memory.

 

Ted:  Keep in mind that the total sum of squares is just N  times the variances of Y.  SSR is variation in the predicted value.

 

 

I was glad you didn't cold call on me. I am not normally shy in class to volunteer but if cold called in a math class, my brain tends to freeze (unless I've had time to think about it sufficiently first).

 

Ted: I want to stress that it is fine to say "pass".  I just want to get a sense of general  comprehension in the class as a whole, not specific individuals.  I have the feeling that when the average student doesn't understand something in a stats course he/she remains silent.  Asking questions is a way to get a sense of the level of understanding.  If many of the students in the class are scared of me calling on them, let's discuss this in class (feel free to bring it up).

Comments (0)

You don't have permission to comment on this page.