Welcome Guest [Log In] [Register]
This forum is used with the NationStates web-game designed and run by Max Barry. While not officially affiliated, this serves as the regional forum for the regions: Middle East, African Continent, American Continent, Asian Continent, and European Continent.

You're currently viewing our forum as a guest. This means you are limited to certain areas of the board and can "read only".

In order to get the most out of these forums, please become a member and read this guide - http://z3.invisionfree.com/nationstates/index.php?showtopic=3060


If you're already a member please log in to your account to access all of our features:

Username:   Password:
Add Reply
Strange econometric result
Topic Started: Nov 16 2007, 06:09 PM (426 Views)
Paradise
Member Avatar
Resident bureaucrat

What was your thesis about?

I work on financial market long-run risk-return tradeoffs. It is (almost) exclusively statistical analysis, but the theoretical framework I use for this is quite unusual.

If I exclude all my graphs, statistical tables, annexes, table of contents, summary and presentation page, I must have around 30 pages of text, which is pretty much the norm for all published econometric researches.
Offline Profile Quote Post Goto Top
 
New Harumf
Member Avatar
Bloodthirsty Unicorn
Paradise
Dec 3 2007, 07:46 PM
What was your thesis about?

I work on financial market long-run risk-return tradeoffs. It is (almost) exclusively statistical analysis, but the theoretical framework I use for this is quite unusual.

If I exclude all my graphs, statistical tables, annexes, table of contents, summary and presentation page, I must have around 30 pages of text, which is pretty much the norm for all published econometric researches.

"The Use of Classical Poetic Techniques in non-Traditional Contemporary Poetry"

Realise, of course, that "contempory" at the time meant through 1976!! :lol:
Offline Profile Quote Post Goto Top
 
Paradise
Member Avatar
Resident bureaucrat

Damn. This looks so boring (no offence) :lol:

And you wrote 110 pages on that? That's crazy :wacko:
Offline Profile Quote Post Goto Top
 
Allesandra
Member Avatar
Only Girl Actively Participating in Threads
 *  *  *  *  *
See, I look at all that and think of some of the tests I learned for experimentation in a computational research class I took last year. However, none of them seems to be the same sort of tests that I learned, like the T-Test, Chi Squared Good of Fitness or ANOVA.

I am afraid that I cannot be of assistance. Sorry. >.<
Offline Profile Quote Post Goto Top
 
Paradise
Member Avatar
Resident bureaucrat

The T-test is there. It's the "t" column. The corresponding p-value is also available in the P>|t| column.

I can also use a chi-square statistic for global signification instead of a Fischer one, both are asymptotically equivalent. The default in my statistical program is the Fischer test, however.
Offline Profile Quote Post Goto Top
 
Rhadamanthus
Member Avatar
Legitimist

I barely remember a thing I learned in Statistics. All these tests go right over my head.
Offline Profile Quote Post Goto Top
 
Allesandra
Member Avatar
Only Girl Actively Participating in Threads
 *  *  *  *  *
Paradise
Dec 4 2007, 07:25 PM
The T-test is there. It's the "t" column. The corresponding p-value is also available in the P>|t| column.

I can also use a chi-square statistic for global signification instead of a Fischer one, both are asymptotically equivalent. The default in my statistical program is the Fischer test, however.

I was never taught the Fischer test.....can you compare it to other tests I may actually know?
Offline Profile Quote Post Goto Top
 
Paradise
Member Avatar
Resident bureaucrat

W = n/(n-k)*r*F

The "=" should be replaced by an "approximately equal".

W is the value of the Wald statistic which follows a chi-square distribution
n is the number of observations
n-k is the degree of freedom
r is the number of restrictions to test
F is the value of the Fischer statistic which follow a Fischer distribution

If n --> infinity, then n/(n-k) --> 1. We then have the direct equality:
W= r*F
Offline Profile Quote Post Goto Top
 
Draxis
Member Avatar
Captain
Paradise
Dec 4 2007, 07:09 PM
W = n/(n-k)*r*F

The "=" should be replaced by an "approximately equal".

W is the value of the Wald statistic which follows a chi-square distribution
n is the number of observations
n-k is the degree of freedom
r is the number of restrictions to test
F is the value of the Fischer statistic which follow a Fischer distribution

If n --> infinity, then n/(n-k) --> 1. We then have the direct equality:
W= r*F

*Wimpers in a corner*

Make the bad math go away paradise, make it go away!
Offline Profile Quote Post Goto Top
 
Eleytheria-Duo
Member Avatar
Resident Bystander
I was never fond of math, but I see (I think) where Paradise was going with his statements now. Regardless, I am not even going to touch this so I don't end up making a fool of myself forevermore. :lol:
Offline Profile Quote Post Goto Top
 
New Harumf
Member Avatar
Bloodthirsty Unicorn
Eleytheria-Duo
Dec 4 2007, 09:57 PM
I was never fond of math, but I see (I think) where Paradise was going with his statements now. Regardless, I am not even going to touch this so I don't end up making a fool of myself forevermore. :lol:

Posted Image
Offline Profile Quote Post Goto Top
 
Rhadamanthus
Member Avatar
Legitimist

New Harumf
Dec 5 2007, 06:12 PM
Eleytheria-Duo
Dec 4 2007, 09:57 PM
I was never fond of math, but I see (I think) where Paradise was going with his statements now. Regardless, I am not even going to touch this so I don't end up making a fool of myself forevermore.  :lol:

Posted Image

Damn... I know I've seen that before, but I don't remember for the life of me what it was...
Offline Profile Quote Post Goto Top
 
New Harumf
Member Avatar
Bloodthirsty Unicorn
Romanus Diogenes
Dec 5 2007, 06:14 PM
New Harumf
Dec 5 2007, 06:12 PM
Eleytheria-Duo
Dec 4 2007, 09:57 PM
I was never fond of math, but I see (I think) where Paradise was going with his statements now. Regardless, I am not even going to touch this so I don't end up making a fool of myself forevermore.  :lol:

Posted Image

Damn... I know I've seen that before, but I don't remember for the life of me what it was...

LOL, 100 points to anyone who can guess (it is part of a formula).
Offline Profile Quote Post Goto Top
 
Paradise
Member Avatar
Resident bureaucrat

I'm submitting my Master's research report Thursday B)
Offline Profile Quote Post Goto Top
 
Draxis
Member Avatar
Captain
Paradise
Dec 18 2007, 04:20 PM
I'm submitting my Master's research report Thursday B)

I have my hell day of three finals in a row starting at 7am and ending at 2pm on thursday.

Good luck with your masters report Paradise.
Offline Profile Quote Post Goto Top
 
Nag Ehgoeg
Member Avatar
The Devil's Advocate

New Harumf
Dec 5 2007, 07:15 PM
Romanus Diogenes
Dec 5 2007, 06:14 PM
New Harumf
Dec 5 2007, 06:12 PM
Eleytheria-Duo
Dec 4 2007, 09:57 PM
I was never fond of math, but I see (I think) where Paradise was going with his statements now. Regardless, I am not even going to touch this so I don't end up making a fool of myself forevermore.  :lol:

Posted Image

Damn... I know I've seen that before, but I don't remember for the life of me what it was...

LOL, 100 points to anyone who can guess (it is part of a formula).

At limit (any variable upto infinity) the hyperbolic logarithm of the product of all positive integers less than or equal to variable n negative n times hyperbolic log n plus n negative h. log n over two is equal to one plus the the sum of SOMETHING plus limit R (any variable approaching infinity).

Anyone who cares (as this is a wiki image) could just hop on over to the wiki, and do a search to find the page that the image is hosted on and pretend to be smart. I don't, really, care that much.

...

Ok you've got until tomorrow before I do it.
Offline Profile Quote Post Goto Top
 
New Harumf
Member Avatar
Bloodthirsty Unicorn
Draxis
Dec 18 2007, 06:25 PM
Paradise
Dec 18 2007, 04:20 PM
I'm submitting my Master's research report Thursday B)

I have my hell day of three finals in a row starting at 7am and ending at 2pm on thursday.

Good luck with your masters report Paradise.

Well, Hell should be over for you! Hope all went well and you gave the Devil his due. :lol:
Offline Profile Quote Post Goto Top
 
Paradise
Member Avatar
Resident bureaucrat

Finally, I submitted Wednesday B)
Offline Profile Quote Post Goto Top
 
« Previous Topic · Off-Topic · Next Topic »
Add Reply