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


Long-Term Actuarial Math Old Exam MLC Forum

Reply
 
Thread Tools Search this Thread Display Modes
  #1  
Old 11-05-2003, 03:10 PM
Msta Msta is offline
Member
 
Join Date: Nov 2002
Posts: 53
Default #4 Nov 2003

Can someone please work this problem out. I had a mental block on it, and still do.

Thanks.
Reply With Quote
  #2  
Old 11-05-2003, 03:31 PM
Woody Woody is offline
Member
SOA
 
Join Date: Feb 2002
Location: Andy's room
Favorite beer: Tusker
Posts: 393
Default

I got 99.3 so I chose 100, which was correct. However, I've heard that others got 99.6. I probably did it wrong, but here's how I did it.

Want Pr(Agg Maint Costs >1.2E[S]) >=0.1

E[N]=Var[N]=3
E[X]=80; Var[X]=40000

So, E[S]=240 for one computer, 240t for t computers. We are trying to find t.
Var[S]=139,200 for one computer, 139,200t for t computers.

So, Pr(Agg Costs > 1.2(240t)=288t)>=0.1

So, when normalizing, (288t - 240t)/(139,200t)^(0.5) = 1.282

You end up getting 48t = 478.31(t^(0.5))

When you solve for t, you get 99.3.

Worked for me. Maybe I got lucky.
Reply With Quote
  #3  
Old 11-05-2003, 03:37 PM
Msta Msta is offline
Member
 
Join Date: Nov 2002
Posts: 53
Default

Grrrr. Forgot the t in the frickin Variance.


$#%#$%#$%!#
Reply With Quote
  #4  
Old 11-05-2003, 03:39 PM
Tommy Vercetti Tommy Vercetti is offline
Member
CAS
 
Join Date: Jan 2003
Posts: 988
Default

I work it the same way as woody.
#31 is a simular question, but i can't work it out
Reply With Quote
  #5  
Old 11-05-2003, 03:42 PM
dumples dumples is offline
Member
CAS
 
Join Date: Sep 2003
Posts: 1,249
Default

lambda=3*n
muS=80
VarS=200^2
first moment of severity = 80^2+200^2

muA = lambda*muS
VarA= lambda * fmos = 3*n*(80^2+200^2)
sigmaA=VarA^.5


Find n so that PHI((1.2*muA-muA)/sigmaA)=(1-.1)=.9

.2*muA/sigmaA)=1.282
48*n^.5/(3*(80^2+200^2))^.5=1.282
n^.5=1.282/48*(3*(80^2+200^2))^.5
n=(1.282/48 )^2*(3*(80^2+200^2))=99.29624167
Reply With Quote
  #6  
Old 11-05-2003, 03:51 PM
Tommy Vercetti Tommy Vercetti is offline
Member
CAS
 
Join Date: Jan 2003
Posts: 988
Default

#31?
Reply With Quote
  #7  
Old 11-05-2003, 04:08 PM
Woody Woody is offline
Member
SOA
 
Join Date: Feb 2002
Location: Andy's room
Favorite beer: Tusker
Posts: 393
Default

Quote:
Originally Posted by Tommy Vercetti
I work it the same way as woody.
#31 is a simular question, but i can't work it out
Tommy, you want Pr (L>0)<=0.05. So you need to calc E[L] and Var[L].

E[L] is Ax-pi(a-duex) = 0.24905-(0.025)[(1-0.24905)(1.06)/.06] = -0.082619 for one policy, -0.082619t for t policies.

Var[L] = (1+P/d)^2[2Ax-Ax^2] = [1+(0.025)(1.06)/.06]^2[0.09476-0.24905^2] = 0.0680346 for one policy, 0.0680346t for t policies.

So, when normalizing, 0-(-0.082619t)/(0.0680346t)^(0.5) = 1.645. You then get 0.42907(t^(0.5))=0.082619t. Solving for t you get 26.97. So answer is B, 27.
Reply With Quote
  #8  
Old 11-05-2003, 04:17 PM
Tommy Vercetti Tommy Vercetti is offline
Member
CAS
 
Join Date: Jan 2003
Posts: 988
Default

Quote:
Originally Posted by Woody
Quote:
Originally Posted by Tommy Vercetti
I work it the same way as woody.
#31 is a simular question, but i can't work it out
Tommy, you want Pr (L>0)<=0.05. So you need to calc E[L] and Var[L].

E[L] is Ax-pi(a-duex) = 0.24905-(0.025)[(1-0.24905)(1.06)/.06] = -0.082619 for one policy, -0.082619t for t policies.

Var[L] = (1+P/d)^2[2Ax-Ax^2] = [1+(0.025)(1.06)/.06]^2[0.09476-0.24905^2] = 0.0680346 for one policy, 0.0680346t for t policies.

So, when normalizing, 0-(-0.082619t)/(0.0680346t)^(0.5) = 1.645. You then get 0.42907(t^(0.5))=0.082619t. Solving for t you get 26.97. So answer is B, 27.
Sh!t.
For some reason, I work the same as you but keep getting the wrong ans from calculator
Now the calculator works.
sux.
Reply With Quote
  #9  
Old 11-05-2003, 04:26 PM
dumples dumples is offline
Member
CAS
 
Join Date: Sep 2003
Posts: 1,249
Default

Quote:
Originally Posted by Tommy Vercetti
#31?
ok, i got this wrong but here we go.

for each case sold
Var[L]=(1+p/d)^2* 2Ax-Ax^2 (the first little 2 should be floating but i can't make that happen)
=0.068034639
Sigma(L)=0.260834505

find the annuity due = (1-Ax)/d=13.26

So E[L] for one case is 13.26*.025-.24905 = .08262 (without intermediate rounding)


E[nL]=n*E[L]=.08262N
sigma(nL)=n^.5*Sigma(l)=0.260834505

PHI((E[nL]-0)/sigma(nL))=.95
E[nL]/sigma(nL)=1.645
n^.5=1.645*sigma(L)/E[L]=5.193354214
n=26.97092799=27
Reply With Quote
  #10  
Old 11-05-2003, 04:27 PM
dumples dumples is offline
Member
CAS
 
Join Date: Sep 2003
Posts: 1,249
Default

it takes too long to type this stuff
Reply With Quote
Reply

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 06:31 AM.


Powered by vBulletin®
Copyright ©2000 - 2018, 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 0.44394 seconds with 9 queries