Actuarial Outpost
 
Go Back   Actuarial Outpost > Exams - Please Limit Discussion to Exam-Related Topics > SoA > Modules 6-8
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions


Reply
 
Thread Tools Search this Thread Display Modes
  #11  
Old 12-21-2010, 02:05 PM
Passacaglia's Avatar
Passacaglia Passacaglia is offline
Member
 
Join Date: Jan 2006
Location: Chicago
Posts: 933
Default

Quote:
Originally Posted by RetActuary84 View Post
I hate to throw a curveball in here, but I can't figure out what kind of method we should be using to determine the number of assays to use or min. to mine.
It looks like, from the question, the CFO suggests using VaR. So it's probably VaR or something else.
Quote:
I did notice in G12 that the formula they're using to determine the decay from assays is N(.945,.01). It says it should be N(.945, .02). Am I missing something in the reading that this is right? After running a few scenarios, the results seem a bit more intuitive using the N(.945, .02)
I dunno about all that. But for Task 2, I really don't think you even need to look at the model.
Reply With Quote
  #12  
Old 12-21-2010, 02:38 PM
jadedteacher jadedteacher is offline
Member
 
Join Date: Feb 2006
Posts: 101
Default

RetActuary84, I just sent you a PM.
Reply With Quote
  #13  
Old 01-22-2011, 12:52 AM
Actuarial007 Actuarial007 is offline
 
Join Date: Dec 2010
Posts: 15
Default

Quote:
Originally Posted by Passacaglia View Post
Yeah, you just have to do the minimum to mine and the number of assays together -- you can't do one, then the other. If you keep the minimum to mine as 0, you'll always mine, and the number of assays you conduct is just throwing money away -- the assays help you determine whether you should mine, and if your minimum to mine is 0, you're going to mine no matter what.

HOWEVER, you're answering Task 3 here. Read the assignment for Task 2 again, and don't do what it tells you to do in subsequent tasks -- just do what it says to do before that.
I try to vary the number of assays and minimum to mine together, but the result is still counter intuitive. All the VaR get worse (more negative). How should I vary the minimum to mine? Like increase it from 0.9 to 0.91 while change number of essay from 8 to 9?

Thanks for your help !
Reply With Quote
  #14  
Old 01-24-2011, 02:43 PM
Passacaglia's Avatar
Passacaglia Passacaglia is offline
Member
 
Join Date: Jan 2006
Location: Chicago
Posts: 933
Default

Quote:
Originally Posted by Actuarial007 View Post
I try to vary the number of assays and minimum to mine together, but the result is still counter intuitive. All the VaR get worse (more negative). How should I vary the minimum to mine? Like increase it from 0.9 to 0.91 while change number of essay from 8 to 9?

Thanks for your help !
I tried a bunch of different combinations -- for example, to use your numbers, I tried a simulation with everything else the same, but one with 0.9 and 8 assays, another with 0.9 and 9 assays, another with 0.91 and 8 assays, and another with 0.91 and 9 assays. I ran the macro several times, probably testing hundreds of combinations, 20 at a time.
Reply With Quote
  #15  
Old 02-02-2011, 11:40 AM
SooMe SooMe is offline
Member
SOA
 
Join Date: Dec 2006
Favorite beer: Bellevue
Posts: 93
Default

This is great so far. I'm not sure how we're supposed to interpret the row
% ends<0
and
% where mine opens

Is this talking specifically about the scenarios? i.e. The % of scenarios of 1000 that leave the mine open?

I'm confused about %ends<0. That doens't make sense to me.
Any suggestions?
Reply With Quote
  #16  
Old 02-02-2011, 03:05 PM
Hawkeye16 Hawkeye16 is offline
Member
SOA AAA
 
Join Date: Jul 2007
Favorite beer: Anything Dark
Posts: 1,188
Default

%ends<0 means the percentage of scenarios that end with negative cash. 1 - %ends<0 is the percent of scenarios that result in a profit after 20 years.
__________________
Despite the high cost of living, it remains very popular.
Reply With Quote
  #17  
Old 02-07-2011, 03:19 PM
olfb12345 olfb12345 is offline
 
Join Date: Feb 2011
Posts: 3
Default

Quote:
Originally Posted by Actuarial007 View Post
I try to vary the number of assays and minimum to mine together, but the result is still counter intuitive. All the VaR get worse (more negative). How should I vary the minimum to mine? Like increase it from 0.9 to 0.91 while change number of essay from 8 to 9?

Thanks for your help !
I agree with you -- increasing the number of assays actually increases variance within the model, which is counter-intuitive. The formula in cell G12 is causing this. I am including this issue as part of Task 1 -- thoughts?
Reply With Quote
  #18  
Old 02-07-2011, 04:51 PM
mhsmith mhsmith is offline
Member
SOA AAA
 
Join Date: Oct 2007
Location: Arizona
Studying for December FAC!
Posts: 438
Default

Quote:
Originally Posted by Actuarial007 View Post
I try to vary the number of assays and minimum to mine together, but the result is still counter intuitive. All the VaR get worse (more negative). How should I vary the minimum to mine? Like increase it from 0.9 to 0.91 while change number of essay from 8 to 9?

Thanks for your help !
Find some starting point, and then vary each separately. Or have a starting point and vary them in a square, such as:

low min, low # mid min, low # high min, low #
low min, mid # mid min, mid # high min, mid #
low min, high # mid min, high # high min, high #

That should give you a sense of how the two are supposed to move together. You could be at the optimal point for one and not the other, or too low on one and too high on the other. Moving them only in tandem (and in a fixed relationship) will obscure the true optimal point (unless you're REALLY lucky).
Reply With Quote
  #19  
Old 02-10-2011, 06:02 PM
mjg394 mjg394 is offline
Member
 
Join Date: Jun 2007
Posts: 70
Default

Quote:
Originally Posted by mhsmith View Post
Find some starting point, and then vary each separately. Or have a starting point and vary them in a square, such as:

low min, low # mid min, low # high min, low #
low min, mid # mid min, mid # high min, mid #
low min, high # mid min, high # high min, high #

That should give you a sense of how the two are supposed to move together. You could be at the optimal point for one and not the other, or too low on one and too high on the other. Moving them only in tandem (and in a fixed relationship) will obscure the true optimal point (unless you're REALLY lucky).
I used your advice and used 2, 4 and 6 assays and used .91, .92 and .93 as my minima to mine. Looking at the AO, I believe we are looking for the highest VaR. The table I pasted below shows that the ranks of the VaR vary between Var(80) through VaR(95) as well as the mean.

# assays 2 4 6 2 4 6 2 4 6
Min to mine 0.91 0.92 0.93
Mean $ 2 5 9 1 4 8 3 6 7
VaR(80) 1 2 5 4 3 6 8 7 9
VaR(90) 5 7 9 4 6 8 1 3 2
VaR(95) 5 7 9 4 6 8 2 3 1

Aside from VaR(80), 2 assays and .93 min to mine looks like the best. 2 assays and .91 min to mine overall might be the strongest.

Any thoughts form anyone on which this would lead me to pick? Worse, am I way off on the methodology? Thanks in advance.

Last edited by mjg394; 02-10-2011 at 06:05 PM.. Reason: table looked bad
Reply With Quote
  #20  
Old 02-14-2011, 06:57 PM
Nene88 Nene88 is offline
 
Join Date: Feb 2011
College: Alumni
Posts: 2
Default

mjg394, how did you get all those positive values in that table? I tried the same numbers for assays and min to mine and got some pretty big negative values for VaR(90) and Var(95)
Reply With Quote
Reply

Tags
can-do, final assessment, task 2

Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off


All times are GMT -4. The time now is 07:03 AM.


Powered by vBulletin®
Copyright ©2000 - 2019, Jelsoft Enterprises Ltd.
*PLEASE NOTE: Posts are not checked for accuracy, and do not
represent the views of the Actuarial Outpost or its sponsors.
Page generated in 0.42380 seconds with 9 queries