| 
  • 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
 

lec4

Page history last edited by PBworks 12 years, 5 months ago

 

 

Survey responses:

 

1.  What questions do you have?

Text Response

How much effort should be spend in making sure we understand the intuition behind the derivations vs.

how much effort should we put into memorizing the formulas?  Are they equally important?

 

A(Ted): Some formulas, I would argue, are worth memorizing, becuase they solidify grasp of the concepts.

Example: the formula for b, and the s.e. of b.  I also think you should understand the proofs we cover in

class-->I will not ask you to reproduce the proofs on an exam, but I think the proofs are a basis for understanding.

 

 

 

2.  Do you have any suggestions on how this lecture/lab (or the course in general) could be improved?

Text Response

The only thing I would change is the textbook, lol.  I would be willing to pay for both a text and the software, so that is not a consideration for me.  However, I have not found this to be a "friendly" text and have ended up using other regression texts in addition.

 

A(Ted):  Thanks for letting me know.  I think no single textbook would be the top choice of every student.  I will provide references for several other texts I have found usefull.

 

 

 

3.  Do you have any specific questions regarding this lecture/lab or the class in general?

#

Answer

 

 

 

Response

%

1

No questions, I'm cool.

 

 

 

 

 

 

 

 

 

 

 

8

89%

2

Yes (see below).

 

 

 

 

 

 

 

 

 

 

 

1

11%

 

 

 

Total

 

 

 

9

100%

 

 

 

4.  Did the class move at the right speed for you today?

#

Answer

 

 

 

Response

%

1

Too fast

 

 

 

 

 

 

 

 

 

 

 

1

10%

2

OK

 

 

 

 

 

 

 

 

 

 

 

9

90%

3

Too slow

 

 

 

 

 

 

 

 

 

 

 

0

0%

 

 

 

Total

 

 

 

10

100%

 

 

 

5.  If you said either "too fast" or "too slow" please explain (it can be brief, just enough so I get the idea)

Text Response

I wasn't familiar with the calculations that involved calculus, so those parts seemed fast - the pace of the rest of the lecture was fine.

 

 

 

6.  If, in the previous question, you said you didn't understand the lecture/lab "well" or "very well", please comment on what the principal source of difficulty was.

Text Response

in a matrix notation, why do you add a constant term in x(x=constant term, gender, occupation)? is a constant term an intercept of the equation?

 

A(Ted): Yes, the constant term is the intercept.  It is the variable that every case has a value of 1 for.

I don't have a background in calculus - so while I understood the main concepts, the differentiation calculations part was not easy for me to follow.

 

A(Ted): That's ok...the class, as a whole, does not require calculus...just that one proof.

 

 

 

7.  If you were absent from this class, please explain why. 

Text Response

I have been quite sick this week. I expect to be back in class on Thursday, however.

 

 

 

8.  Again, I apologize for taking your time to answer these questions.  However, this is extremely helpful for me to improve the course.  Thanks.    These questions refer to:  Lecture 4    How well do you feel that you under...

#

Answer

 

 

 

Response

%

1

very well

 

 

 

 

 

 

 

 

 

 

 

0

0%

2

well

 

 

 

 

 

 

 

 

 

 

 

8

73%

3

so-so, OK

 

 

 

 

 

 

 

 

 

 

 

3

27%

4

not well

 

 

 

 

 

 

 

 

 

 

 

0

0%

5

I was lost

 

 

 

 

 

 

 

 

 

 

 

0

0%

6

I was absent from class (see next question)

 

 

 

 

 

 

 

 

 

 

 

0

0%

 

 

 

Total

 

 

 

11

100%

 

 

%qND In OLS, why does the variance of beta, σ2differ from s2?

 

A:(Ted) σ2is the true variance, and s2 is the estimated variance, based on the sum of squared errors.  It will be different from σ2due random variation in the (randomly drawn) error terms.

 

A:(Mike)  Ted is completely correct.  It might be useful to also think of σ2as theoretical variance and s2 as applied variance.     Philosophically, its a bit a like the 'ideal' is never reached by human effort.    In chemistry, a similar issue arises because a 100% pure sample can never be truly attained in the lab.

 

 

Comments (0)

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