Actuarial Outpost > CAS CAS Exam 7 Spring 2020 Progress Thread - Now in October!
 User Name Remember Me? Password
 Register Blogs Wiki FAQ Calendar Search Today's Posts Mark Forums Read
 FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions

 Enter your email to subscribe to DW Simpson weekly actuarial job updates. li.signup { display: block; text-align: center; text-size: .8; padding: 0px; margin: 8px; float: left; } Entry Level Casualty Health Life Pension All Jobs

 Thread Tools Search this Thread Display Modes
#201
12-05-2019, 08:26 AM
 lostatsea Member CAS Join Date: Oct 2015 Posts: 64

There were no major changes to the syllabus, right? Planning to start studying in the new year.
__________________
ACAS | 7 | 8 | 9
#202
12-05-2019, 09:01 AM
 Unrealistic Ace Member CAS Join Date: Nov 2017 Posts: 234

Quote:
 Originally Posted by lostatsea There were no major changes to the syllabus, right? Planning to start studying in the new year.
The only change I have seen is an errata for Taylor being added. Everything else seems to be identical.
#203
12-06-2019, 08:12 PM
 trueblade Member CAS Join Date: Jul 2012 Location: Castlevania Studying for Freedom Posts: 1,234

Clark, page 53, the information matrix

The notations are misleading, shouldn't "?" be theta, and "y" be i? I have no idea why they use a different set of notations here.
__________________

ACAS 7 8 9
#204
12-11-2019, 07:44 AM
 Unrealistic Ace Member CAS Join Date: Nov 2017 Posts: 234

Quote:
 Originally Posted by trueblade Clark, page 53, the information matrix The notations are misleading, shouldn't "?" be theta, and "y" be i? I have no idea why they use a different set of notations here.
Yes.
#205
12-11-2019, 10:33 AM
 AbedNadir Member CAS SOA Join Date: Mar 2014 Studying for FCAS Posts: 2,848

Page 11 of Brosius, I'm looking at the linear approximation formula and the 1.2.3 listed for Hugh White's questions. If Cov(X,Y) < Var(X), isn't L(x) still bigger than E[Y]? How is this a decrease in the reserve? Isn't this true for all conditions?

Like, let's say x = 5 and E(X) = 4, then under all conditions E[Y|X] = (something bigger than 0 ) + E[Y]
__________________

Last edited by AbedNadir; 12-11-2019 at 10:36 AM..
#206
12-11-2019, 01:49 PM
 trueblade Member CAS Join Date: Jul 2012 Location: Castlevania Studying for Freedom Posts: 1,234

Quote:
 Originally Posted by Unrealistic Ace Yes.
Ty!
__________________

ACAS 7 8 9
#207
12-11-2019, 02:21 PM
 trueblade Member CAS Join Date: Jul 2012 Location: Castlevania Studying for Freedom Posts: 1,234

Mack 1994 is bothering me.

on pg.112, Mack states

The fact that the chain ladder estimator uses weights which are proportional to ��jk therefore means that ��jk is assumed to be inversely proportional to ������(Cj,k+1/Cjk|Cj1,...,Cjk)

I don't get how he came up with this conclusion. Why does the weight in the CL estimator imply Cjk is inversely proportional to the variance of the future development factor?
Attached Images

__________________

ACAS 7 8 9
#208
12-11-2019, 02:36 PM
 CuriousGeorge Member CAS SOA Join Date: Dec 2005 Posts: 1,632

Quote:
 Originally Posted by trueblade Mack 1994 is bothering me. Why does the weight in the CL estimator imply Cjk is inversely proportional to the variance of the future development factor?
Each variance assumption yields a different minimum variance unbiased estimator of f. For the basic variance assumptions, (constant, proportional, proportional to the square) the MVUE for each can be written with a similar formula, just by changing the weights.

So if you use a formula with a certain set of weights, you are implicitly making a statement about what you believe the variance relationship is (because if you believed it was something else, you are stupid for not using the MVUE for what you thought it was).
#209
12-11-2019, 02:48 PM
 trueblade Member CAS Join Date: Jul 2012 Location: Castlevania Studying for Freedom Posts: 1,234

Quote:
 Originally Posted by AbedNadir Page 11 of Brosius, I'm looking at the linear approximation formula and the 1.2.3 listed for Hugh White's questions. If Cov(X,Y) < Var(X), isn't L(x) still bigger than E[Y]? How is this a decrease in the reserve? Isn't this true for all conditions? Like, let's say x = 5 and E(X) = 4, then under all conditions E[Y|X] = (something bigger than 0 ) + E[Y]
Correct me if I'm wrong. I think the main point here is L(X) will increase less than the increase in x and they are comparing the following two reserves

Assume Cov(X,Y)/Var(X)=0.9, E[Y]=10

Expected reserve = E[Y] - E[X] = 10 - 4 = 6

Estimated Ultimate L(x) = (5-4)*0.9+10 =10.9
Reserve: L(x) - x = 10.9-5=5.9 < 6, hence the decrease
__________________

ACAS 7 8 9
#210
12-11-2019, 08:25 PM
 AbedNadir Member CAS SOA Join Date: Mar 2014 Studying for FCAS Posts: 2,848

Quote:
 Originally Posted by trueblade Mack 1994 is bothering me. on pg.112, Mack states The fact that the chain ladder estimator uses weights which are proportional to ��jk therefore means that ��jk is assumed to be inversely proportional to ������(Cj,k+1/Cjk|Cj1,...,Cjk) I don't get how he came up with this conclusion. Why does the weight in the CL estimator imply Cjk is inversely proportional to the variance of the future development factor?
It's derived in appendix B
__________________

 Thread Tools Search this Thread Search this Thread: Advanced Search Display Modes Linear Mode

 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 09:13 PM.

 -- Default Style - Fluid Width ---- Default Style - Fixed Width ---- Old Default Style ---- Easy on the eyes ---- Smooth Darkness ---- Chestnut ---- Apple-ish Style ---- If Apples were blue ---- If Apples were green ---- If Apples were purple ---- Halloween 2007 ---- B&W ---- Halloween ---- AO Christmas Theme ---- Turkey Day Theme ---- AO 2007 beta ---- 4th Of July Contact Us - Actuarial Outpost - Archive - Privacy Statement - Top