Actuarial Outpost
 
Go Back   Actuarial Outpost > Search Forums
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions



Showing results 1 to 25 of 300
Search took 0.17 seconds.
Search: Posts Made By: Abraham Weishaus
Forum: Long-Term Actuarial Math 11-15-2019, 12:04 PM
Replies: 309
Views: 72,047
Posted By Abraham Weishaus
I am now getting D for #8 (instead of C).

I am now getting D for #8 (instead of C).
Forum: Long-Term Actuarial Math 11-14-2019, 11:28 AM
Replies: 309
Views: 72,047
Posted By Abraham Weishaus
I haven't seen a PAK. I'm getting ADBCC ABCED...

I haven't seen a PAK. I'm getting ADBCC ABCED DAABE DCCEE


If any of these are wrong, please inform me.
Forum: MAS-I 11-08-2019, 02:03 PM
Replies: 9
Views: 1,146
Posted By Abraham Weishaus
The sample variance S^2, by definition, uses the...

The sample variance S^2, by definition, uses the sample mean in its calculation, not the true mean. Even if the true mean is known. I am not aware of any symbol for \frac{\sum (X_i-\mu)^2}{n} -...
Forum: Investment / Financial Markets 11-07-2019, 11:06 AM
Replies: 4
Views: 358
Posted By Abraham Weishaus
max(0,50-S) is equal to one of two things: either...

max(0,50-S) is equal to one of two things: either it is equal to 0 or it is equal to 50-S. If it is equal to 50-S, there is no way that 50-S>55-S. Having eliminated the 50-S alternative, we're left...
Forum: Investment / Financial Markets 11-06-2019, 08:18 PM
Replies: 4
Views: 358
Posted By Abraham Weishaus
Where do you see that statement? Yes,...

Where do you see that statement?


Yes, they both lose money if S>59.16, but the short forward loses more in that range. When S is lower than 50, they both are profitable but the forward's...
Forum: MAS-I 11-03-2019, 05:03 PM
Replies: 9
Views: 1,146
Posted By Abraham Weishaus
No. You have to divide by 19 (to get the...

No. You have to divide by 19 (to get the unbiased sample variance of the distribution) and by 20 (to get the variance of the sample mean). I divided by 19 on line 2. Then I divided by 20 on line 4....
Forum: MAS-II 10-28-2019, 06:26 PM
Replies: 159
Views: 21,630
Posted By Abraham Weishaus
The situation in the question is impossible. ...

The situation in the question is impossible. Gamma is the conjugate prior for Poisson, and the mode starts at 0 for an exponential and converges monotonically to 2 as number of claims go to...
Forum: MAS-I 10-09-2019, 10:06 PM
Replies: 4
Views: 487
Posted By Abraham Weishaus
Check the errata.

Check the errata.
Forum: MAS-I 10-04-2019, 06:33 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Depends. If m=10, then the mean is 6. If m=1,...

Depends. If m=10, then the mean is 6. If m=1, then the mean is 0.6.
Forum: MAS-I 10-04-2019, 08:47 AM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
The 2 losses are for amounts above 25000. If...

The 2 losses are for amounts above 25000. If there were no deductible, their likelihoodx would be S(25000). However, due to the deductible, you receive no information about losses below 1000, so...
Forum: Short-Term Actuarial Math 10-02-2019, 09:30 PM
Replies: 7
Views: 826
Posted By Abraham Weishaus
There is no such thing as premium by AY. AY is...

There is no such thing as premium by AY. AY is only for accidents. Loss payments are categorized based on the year of the underlying accident. They may also be categorized by calendar year, but...
Forum: MAS-I 09-17-2019, 06:09 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Yes. I'm going to remove the smoothing part from...

Yes. I'm going to remove the smoothing part from the question. The original exam question based on the textbook used then used a simpler smoothing method - they had 10 observations, with the first...
Forum: MAS-I 09-17-2019, 06:05 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Yes, .6 quantile = 60 percentile. Divide your...

Yes, .6 quantile = 60 percentile. Divide your percentile number by 100 to get the corresponding quantile.


I should divide, not multiply: k/(n+1) quantile. I'll post an erratum.
Forum: MAS-I 09-05-2019, 01:46 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Don't thank me - thank Klugman and the other...

Don't thank me - thank Klugman and the other authors of Loss Models for their method. I understand Tse's logic, but a method that sets the median of {1,1,3,3,5,5) equal to 2.5 rather than 3 strikes...
Forum: MAS-I 09-04-2019, 05:47 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
This smoothing method, from Tse's textbook, is...

This smoothing method, from Tse's textbook, is slightly different from the one in Loss Models (and described in the ASM manual). Since MAS-I is purely based on Tse and not Loss Models, I will post...
Forum: MAS-I 09-03-2019, 09:58 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
The question asks for the smoothed empirical...

The question asks for the smoothed empirical percentile, and that is 11.625 - read the textbook to see how smoothed empirical percentile is defined. 12 is the 75th percentile of the empirical...
Forum: MAS-I 09-03-2019, 09:52 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Read the "Tables" section in the introduction of...

Read the "Tables" section in the introduction of the ASM manual. Or if you wish, download an old MAS-I exam and read the second bullet of item #4 of the exam instructions. A little weird that they...
Forum: MAS-I 08-05-2019, 06:58 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Where is the solution assuming that?

Where is the solution assuming that?
Forum: Short-Term Actuarial Math 08-04-2019, 08:34 PM
Replies: 3
Views: 783
Posted By Abraham Weishaus
OK, that's not a good way to prove it. Here's a...

OK, that's not a good way to prove it. Here's a better way.
e_Z(d(1+r))= E[Z-d(1+r)|Z>d(1+r)]
Now Z>d(1+r) if and only if X>d, so this is
e_Z(d(1+r))=E[Z-d(1+r)|X>d]
But...
Forum: MAS-I 07-27-2019, 11:29 PM
Replies: 2
Views: 1,118
Posted By Abraham Weishaus
The links in the ASM manual to all the old exams...

The links in the ASM manual to all the old exams still work, so they're all stored on the CAS site. Most of the links are of the form www.casact.org/ admissions/ studytools/ exam3/ spyy-3.pdf...
Forum: MAS-I 07-24-2019, 10:30 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Well, since the first paragraph of The...

Well, since the first paragraph of The Disreputable Dog's post is taken from Ross page 651 which is on the MAS-I syllabus, I would say that the method is on the MAS-I syllabus.


But I agree that...
Forum: Short-Term Actuarial Math 07-20-2019, 11:49 PM
Replies: 2
Views: 800
Posted By Abraham Weishaus
Effective date of the rate change, not effective...

Effective date of the rate change, not effective date of the policy. Usually the date the policy is issued isn't called the effective date, it's called something else, like "issue date". But I can...
Forum: MAS-I 07-14-2019, 02:39 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Yes, #1 and #3 are errors on my part. And you...

Yes, #1 and #3 are errors on my part. And you have gone through Ross's derivation in #2 so you should get the same result.
Forum: MAS-I 07-09-2019, 07:07 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
Yes. With modern computers using lots of...

Yes. With modern computers using lots of precision, the probability of 0 is infinitesimal, so it hardly makes a difference, but that is the reason Ross prefers the second method.
Forum: MAS-I 07-09-2019, 01:53 PM
Replies: 574
Views: 87,484
Posted By Abraham Weishaus
In practice most computer random number...

In practice most computer random number generators can generate 0 but will never generate 1. That's why Ross is the preferred option.
Showing results 1 to 25 of 300

 

All times are GMT -4. The time now is 12:43 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 0.47908 seconds with 7 queries