SERVING THE QUANTITATIVE FINANCE COMMUNITY

Search found 9 matches

by drmwc1
December 14th, 2017, 11:07 am
Forum: Careers Forum
Topic: Quick help for a future Quant
Replies: 13
Views: 2663

Re: Quick help for a future Quant

OP is young. When I was young, I thought life would be a stroll through the forest admiring waterfalls. At some point, I was kidnapped by poo flinging feral monkeys. They kept me captive in a cave. After many years, I learned that there is beauty in caves as well. ISayMoo presumably hasn't yet found...
by drmwc1
November 28th, 2017, 10:09 am
Forum: Programming and Software Forum
Topic: Looking for hardware recommendations
Replies: 252
Views: 27629

Re: Looking for hardware recommendations

Am i spamming already? :-D My simulations run like freaking 5 x faster, not to mention the 10 cores. And I thought nothing can move me anymore (the last invention that gave me butterflies was electronic paper), but Oculus Rift experience is amazing. The immersion is so deep that when my husband app...
by drmwc1
October 11th, 2017, 10:58 am
Forum: Student Forum
Topic: What could go possibly wrong ...
Replies: 24
Views: 2259

Re: What could go possibly wrong ...

Here's a paper on getting the nearest correlation matrix in n-dimensions: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.230.4541&rep=rep1&type=pdf   I think the alternating projection method is in the NAG library. (Project to closest symmetric matrix with 1s on main diagonlal; project to ...
by drmwc1
May 15th, 2017, 8:16 am
Forum: Brainteaser Forum
Topic: Prisoners and hats
Replies: 17
Views: 52176

Re: Prisoners and hats

you changed the problem from N prisoners and M colors to an infinite number of prisoners and 2 colors, 0 and 1.
See post number 8.

I was still working on it!
Sorry, I am becoming impatient in my dotage.
by drmwc1
May 12th, 2017, 1:55 pm
Forum: Brainteaser Forum
Topic: Prisoners and hats
Replies: 17
Views: 52176

Re: Prisoners and hats

It's been over 10 years, so I feel enough time has passed to post the solution. It follows the Batman dying introduction bit of this video:
by drmwc1
April 5th, 2017, 5:04 pm
Forum: Brainteaser Forum
Topic: exp(5) = [$]e^5[$]
Replies: 544
Views: 111735

Re: exp(5) = [$]e^5[$]

How about: 150-(87^3+12^5)/(83^3).

Good to 8 d.p.
by drmwc1
November 16th, 2016, 6:42 pm
Forum: General Forum
Topic: Is Hedgable a word?
Replies: 24
Views: 1820

Re: Is Hedgable a word?

The insurance CFO Forum spelled it as hedgeable. (http://www.cfoforum.nl/downloads/MCEV_P ... r_2009.pdf)

So it has been used before. 
by drmwc1
January 6th, 2016, 2:27 pm
Forum: Technical Forum
Topic: Best method for finding nearest positive semidefinite correlation matrix for large matrices with judgment embedded
Replies: 12
Views: 3488

Best method for finding nearest positive semidefinite correlation matrix for large matrices with judgment embedded

<r>You could just re-order tor get the correlations you want fixed to be in the top left corner; then if necessary reorder again back to the original order.NAG algorithm G02an seems to do the trick in this case: <URL url="http://www.nag.co.uk/IndustryArticles/nearest_correlation_matrix_mk25.pdfIf"><...
by drmwc1
November 24th, 2015, 3:02 pm
Forum: Technical Forum
Topic: Best method for finding nearest positive semidefinite correlation matrix for large matrices with judgment embedded
Replies: 12
Views: 3488

Best method for finding nearest positive semidefinite correlation matrix for large matrices with judgment embedded

<r>There is an algorithm that lets you choose a weighting, and gets the nearest correlation matrix allowing for the weighting. The weighting matrix needs to be PSD. Here is the paper: <URL url="http://eprints.ma.man.ac.uk/232/01/covered/MIMS_ep2006_70.pdf"><LINK_TEXT text="http://eprints.ma.man.ac.u...
GZIP: On