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

Probability Old Exam P Forum

Thread Tools Search this Thread Display Modes
Old 02-15-2019, 08:53 AM
tfish2718 tfish2718 is offline
Join Date: Feb 2019
Posts: 2
Default Exam P Practice Question 238

Question: In a large population of patients, 20% have early stage cancer, 10% have advanced stage cancer, and the other 70% do not have cancer. Six patients from this population are randomly selected. Calculate the expected number of selected patients with advanced stage cancer, given that at least one of the selected patients has early stage cancer.
(A) 0.403
(B) 0.500
(C) 0.547
(D) 0.600
(E) 0.625


Here's my confusion. I understand the solution mathematically. I understand how they calculate it and the formulas they're using. However, my intuitive understanding of the situation would lead me to answer B.

The way I see it, if we pick 6 patients, and at least one has early stage cancer, then since this is a large population, we can consider this the same as randomly picking 5 patients, since the 6th patient is set. Then of course we would expect 5*0.1 = 0.5 patients with advanced stage cancer. This is obviously wrong. So what is it that shifts the expected value? Why isn't it effectively the same as picking 5 random patients? Thank you.
Reply With Quote
Old 02-15-2019, 10:20 AM
Gandalf's Avatar
Gandalf Gandalf is offline
Site Supporter
Site Supporter
Join Date: Nov 2001
Location: Middle Earth
Posts: 31,286

That is a more complicated version of a fairly common puzzler.
i have two children. At least one is a boy. What is the probability I have 2 boys?
Answer is 1/3, not the 1/2 your method gives. Children in birth order, could be d d, d s, s d, s s. First case is out.
Reply With Quote
Old 02-15-2019, 10:36 AM
Michael Mastroianni's Avatar
Michael Mastroianni Michael Mastroianni is offline
Join Date: Jan 2018
Posts: 38

Imagine the probability for early stage cancer was 0.9 so that there are only two cases: early with 0.9 and advanced with 0.1. Then the probability of having at least 1 early stage of the 6 selected is nearly 1. This means the expected value of # of advanced stage given at least 1 early has to be nearly equal to the unconditional expected value of the # of advanced stage people and we know that’s 6*0.1=0.6. It really depends on how likely early stage is. If early stage was nearly impossible, the answer would be close to 0.5.

You could answer this question without doing any work just by observing that the answer must be between 0.5 and 0.6.
Michael Mastroianni, ASA
Video Course for Exam 1/P:
Reply With Quote
Old 02-15-2019, 10:44 AM
tfish2718 tfish2718 is offline
Join Date: Feb 2019
Posts: 2

Ah, thank you Gandalf. Funnily enough, the Monty Hall problem was a passing thought for me but I didn't think about it too deeply. That makes more sense.
Reply With Quote

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 08:52 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 0.14210 seconds with 11 queries