Actuarial Outpost
 
Go Back   Actuarial Outpost > Exams - Please Limit Discussion to Exam-Related Topics > SoA/CAS Preliminary Exams > Exam 4/C - Construction and Evaluation of Actuarial Models
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions


Upload your resume securely at https://www.dwsimpson.com
to be contacted when new jobs meet your skills and objectives.


Reply
 
Thread Tools Display Modes
  #381  
Old Yesterday, 02:31 PM
daaaave daaaave is online now
David Revelle
 
Join Date: Feb 2006
Posts: 2,909
Default

Quote:
Originally Posted by GMONEYBALLIN View Post
https://puu.sh/xHQyh/db9f7d3971.png

can someone tell me how the parameters for this distribution is an inverse gamma with theta = 2 and alpha = 4?

I understand the theta =2 but why is alpha = 4?
In the tables, they list the inverse Gamma density as


If you collect the factors of x outside the exponential, you have (1/x)^alpha in the numerator, and another x in the denominator, for a total of 1/x^{alpha+1}. In your expression, you have 1/beta^5, with beta as your variable, so 5 = alpha + 1 and alpha = 4.
__________________

Follow us on Twitter, Facebook, and LinkedIn
Reply With Quote
  #382  
Old Yesterday, 02:34 PM
MemorizingFormulas MemorizingFormulas is offline
SOA
 
Join Date: Nov 2016
Studying for C, SRM, VEE Stat
Posts: 16
Default

Quote:
Originally Posted by GMONEYBALLIN View Post
https://puu.sh/xHQyh/db9f7d3971.png

can someone tell me how the parameters for this distribution is an inverse gamma with theta = 2 and alpha = 4?

I understand the theta =2 but why is alpha = 4?
16/6 = 8/3
Did you forget this ?
Or else you can plug alpha=4 and theta=2 into the density of inverse gamma to verify it.
__________________
Econ Finance Stat(Fall 2017)
P C(Oct 2017) SRM(Fall 2017) LTAM(2018) MFE(Late 2018) FM(2019) PA
Reply With Quote
  #383  
Old Yesterday, 03:00 PM
LilSam88 LilSam88 is offline
Member
CAS
 
Join Date: Jul 2016
Posts: 39
Default

Quote:
Originally Posted by MemorizingFormulas View Post
I have a question about VHM.
If a portfolio contains risks of 2 classes, class A and class B, what is the VHM?
VHM = E(Var(mean | class)) + Var(E(mean | class))
The above formula is correct, right?
And is E(Var(mean | class)) equal to EPV?
The formula you stated is wrong.

Var(X) = E(Var(X | class)) + Var(E(X | class))
= EPV + VHM

So EPV = E(Var(X | class))
and VHM = Var(E(X | class))
__________________
P FM MFE S C
Reply With Quote
  #384  
Old Yesterday, 10:06 PM
Outsanity Outsanity is offline
Member
CAS
 
Join Date: Jul 2012
College: 1st year
Posts: 213
Default

Quote:
Originally Posted by MemorizingFormulas View Post
I have a question about VHM.
If a portfolio contains risks of 2 classes, class A and class B, what is the VHM?
VHM = E(Var(mean | class)) + Var(E(mean | class))
The above formula is correct, right?
And is E(Var(mean | class)) equal to EPV?

VHM is literally the variance of the means - the variance of the expected values of class A and class B.

Do you mean:
Sample Variance = E(Var(mean/class))+Var(E(mean/class)) = EPV + VHM = v+a

Quote:
Originally Posted by Whoaminoneofyourbusiness View Post
I'm at a 5.7 but I'm pretty content with just moving onto the TIA practice exams for a while. For me most of the questions I'm getting wrong/not finishing in 3.5 hours are "can you do this big MLE or solve this system of equations in 6 minutes" instead of "do you know this material"? Granted, I'm taking these after work so I'd probably have better luck with doing problems fast if I did them while I was more fresh.
I felt the same!

I was stuck on level 5.6 for a frustrating week, then I scored 89% on my last ADAPT (had 3 hard questions that I recognized from SOA, had 3 lucky guesses..) and made it to level 7.1 I am not doing level 7.1 exams, though.

The trouble is, I still need to reference formula sheet for certain formulas.

Quote:
Originally Posted by Ren_St View Post
What rarely tested topics are you guys skipping? I skipped over Polar method, kernels, multivariable information matrix, TVaR of lognormal... is it safe to skip these and focus on mastering the main topics instead?
From those I would say learn Polar method, kernels and memorize the TVar formula? I ran into a good amount of questions on polar & kernels on ADAPT. x:
Reply With Quote
  #385  
Old Yesterday, 10:59 PM
ThereIsNoSpoon ThereIsNoSpoon is offline
Member
CAS SOA
 
Join Date: Sep 2014
Studying for C
College: When the smog clears, _ _ _ _
Favorite beer: PABST! BLUE RIBBON!
Posts: 309
Default

Quote:
Originally Posted by Outsanity View Post

From those I would say learn Polar method, kernels and memorize the TVar formula? I ran into a good amount of questions on polar & kernels on ADAPT. x:
memorize the TVaR formula for lognormal and normal,you mean?
__________________

------------------------------------------
P FM MFE C MLC VEE Economics VEE Applied Statistics VEE Corporate Finance

Want to connect on LinkedIn? PM me!
Reply With Quote
Reply

Thread Tools
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 09:27 AM.


Powered by vBulletin®
Copyright ©2000 - 2017, 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 0.14943 seconds with 10 queries