Actuarial Outpost
 
Go Back   Actuarial Outpost > Exams - Please Limit Discussion to Exam-Related Topics > SoA/CAS Preliminary Exams > Exam PA: Predictive Analytics
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 our jobs meet your skills and objectives.


Reply
 
Thread Tools Search this Thread Display Modes
  #131  
Old 10-30-2019, 09:24 PM
windows7forever windows7forever is offline
Member
SOA
 
Join Date: Apr 2016
Posts: 398
Default

Quote:
Originally Posted by DyalDragon View Post
Key point is that the most important sections have not been released yet, and have a release estimate of "end of November". The last week of November is U.S. Thanksgiving week so unless it's done before Monday it will be December before it actually gets delivered. If time from delivery to actual access is about the same as the last released section (about 1 week), you will be lucky to have a full week with the material.
Chapter 3 took a few days later to arrive at actuarial bookstore since the author announced the update was done. There might be some technical conversion done between the author's version and the version available on actuarial bookstore that needed some days to complete. Hope it's faster for Thanksgiving release. People eat Turkey on Thanksgiving, but PA exam takers eat manual and case studies in that weekend.
Reply With Quote
  #132  
Old 11-01-2019, 03:50 PM
ryangold96 ryangold96 is offline
SOA AAA
 
Join Date: Oct 2019
Studying for Predictive Analytics
College: UT Austin Alumni
Favorite beer: Weihenstephaner Original
Posts: 2
Default How to handle data only available for certain observations?

In the sample project, SAGE (spouse age) and SEDUCATION (spouse education) have zeros listed for individuals who do not have a spouse. How should I treat these types of variables in a model? I feel as if including the variables without doing some sort of transformation is misleading or could misrepresent the importance of spousal information for individuals who have spouses.

Would an interaction term suffice in a GLM?

Would a transformation suffice?

Would two different models be needed (one on married individuals and one of single individuals)?
Reply With Quote
  #133  
Old 11-04-2019, 11:31 PM
PerpetualMotion's Avatar
PerpetualMotion PerpetualMotion is offline
Member
SOA
 
Join Date: Jan 2013
Location: Kentucky(Louisville)
Studying for Exam MLC
College: University of Louisville Alumni
Favorite beer: Zombie Dust
Posts: 412
Default

Quote:
Originally Posted by ryangold96 View Post
In the sample project, SAGE (spouse age) and SEDUCATION (spouse education) have zeros listed for individuals who do not have a spouse. How should I treat these types of variables in a model? I feel as if including the variables without doing some sort of transformation is misleading or could misrepresent the importance of spousal information for individuals who have spouses.

Would an interaction term suffice in a GLM?



Would a transformation suffice?

Would two different models be needed (one on married individuals and one of single individuals)?
I don't remember the dataset nor the solution but I would think you could create a new married indicator variable for sage or maybe add them together. For education, if it's not clear what it means then test if it's significant and if not throw it out. If it is just mention that it's not clear and would need a SME to provide clarity. Just justify what you do. Just my 2 cents, I'm approaching this exam as if it were a project I had at work.
__________________
P,FM MFE , C, MLC,
Modules 1-8 IA
FA


And NUH is the letter I use to spell Nutches
Who live in small caves, known as Nitches, for hutches,
These Nutches have troubles, the biggest of which is
the fact there are many more Nutches than Nitches.
Reply With Quote
  #134  
Old 11-04-2019, 11:45 PM
PerpetualMotion's Avatar
PerpetualMotion PerpetualMotion is offline
Member
SOA
 
Join Date: Jan 2013
Location: Kentucky(Louisville)
Studying for Exam MLC
College: University of Louisville Alumni
Favorite beer: Zombie Dust
Posts: 412
Default

Some things I'm focusing on/ thinking about: if continuous graph the target and see what kind a distribution it follows. Think of correlated variables logically given the problem and see if you can't combine them. Know how to read residual plots. Know what likelihood and deviance are. Make sure to be able to interpret coefficients in logistic regression where categorical variables give a percentage value in relation to the base. Aic/bic, forward/backward selection, ridge/lasso (all penalty stuff). Be comfortable with trees, forests and how gradient boosting works. If poisson and grouped data you probably want to log the exposures as an offset, on that same note look for over dispersion. Cross validation techniques and why you choose certain parameters. This is jumbled and quick but feel free to add/critique.
__________________
P,FM MFE , C, MLC,
Modules 1-8 IA
FA


And NUH is the letter I use to spell Nutches
Who live in small caves, known as Nitches, for hutches,
These Nutches have troubles, the biggest of which is
the fact there are many more Nutches than Nitches.
Reply With Quote
  #135  
Old 11-05-2019, 10:57 AM
DyalDragon's Avatar
DyalDragon DyalDragon is offline
Member
SOA
 
Join Date: Apr 2009
Location: Here
Studying for the hell of it...
College: AASU
Favorite beer: This one...
Posts: 33,036
Default

Quote:
Originally Posted by magicjello View Post
I should probably know this by now, but I don't. I'm still working through the modules and wondering in the actual exam, do they give you an RMD file that has some code in it already that you will fix/adjust/add on? Like in the examples? Or are we expected to start from scratch?
The code is there, but you have know how to use it and/or modify it to do what you want.
__________________
P FM MFE MLC C Predictive Analytics
VEE FAP FAP FAP FAP FAP FAP FAP FAP APC
Reply With Quote
  #136  
Old 11-05-2019, 11:01 AM
magicjello magicjello is offline
Member
SOA
 
Join Date: Sep 2015
Posts: 138
Default

Quote:
Originally Posted by DyalDragon View Post
The code is there, but you have know how to use it and/or modify it to do what you want.
Thanks! I just deleted my post after finding this....I'm should have looked a bit harder before asking.

I got nervous after reading something in mod 6 that I misinterpreted.
Reply With Quote
  #137  
Old 11-05-2019, 04:48 PM
ryangold96 ryangold96 is offline
SOA AAA
 
Join Date: Oct 2019
Studying for Predictive Analytics
College: UT Austin Alumni
Favorite beer: Weihenstephaner Original
Posts: 2
Question Lasso Residual Plot

Does anyone know if there is a quick way within the available packages for the exam to produce residual, qq, leverage, and scale plots for lasso and ridge regression models similar to the plot() output for regular GLMs?
Reply With Quote
  #138  
Old 11-05-2019, 06:00 PM
HammocksEnrage HammocksEnrage is offline
SOA
 
Join Date: May 2019
College: University of Notre Dame
Posts: 5
Default

Here's my main question...how many hours are you guys all thinking is a reasonable number to study for this exam? I've only studied 30 hours but feel like I've covered a decent amount of the material so far. So maybe I'll study about 100 or 150 total?
Reply With Quote
  #139  
Old 11-05-2019, 10:03 PM
mac1245 mac1245 is offline
Member
SOA
 
Join Date: Apr 2013
Studying for Exam LTAM
Posts: 126
Default

Quote:
Originally Posted by HammocksEnrage View Post
Here's my main question...how many hours are you guys all thinking is a reasonable number to study for this exam? I've only studied 30 hours but feel like I've covered a decent amount of the material so far. So maybe I'll study about 100 or 150 total?
Thanks!!! This gives me some hope. I am just getting started but then again I have no prior knowledge in predictive modelling
__________________
P/1 | FM/2 | MFE /3F | C/4 | LTAM | SRM | PA
VEE: Economics | Corporate Finance | Statistics
FAP Modules
Reply With Quote
  #140  
Old 11-06-2019, 05:31 PM
StrongGuy StrongGuy is offline
SOA
 
Join Date: Oct 2019
Location: New Jersey
Studying for FAP
Posts: 21
Default

Quote:
Originally Posted by HammocksEnrage View Post
Here's my main question...how many hours are you guys all thinking is a reasonable number to study for this exam? I've only studied 30 hours but feel like I've covered a decent amount of the material so far. So maybe I'll study about 100 or 150 total?
30 hours should be fine.

Get familiar with modules 6-8, as they will he the bulk of your exam.
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 11:01 PM.


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 0.22206 seconds with 10 queries