My Math Forum  

Go Back   My Math Forum > College Math Forum > Advanced Statistics

Advanced Statistics Advanced Probability and Statistics Math Forum


Thanks Tree1Thanks
  • 1 Post By Maschke
Reply
 
LinkBack Thread Tools Display Modes
August 21st, 2019, 01:45 PM   #1
Newbie
 
Joined: Aug 2019
From: France

Posts: 1
Thanks: 0

Model for maximizing chance of success based on opinion poll

Hi,

I have to make a medical diagnosis for a patient: is he A or B?

I can not make inspection of the patient, and my only help is a poll of N medical experts that observed him.

Out of N experts, the track records for their past diagnoses are as below:
  • 12% of experts had a success rate of 32%
  • 43% of experts had a success rate of 38%
  • 45% of experts had a success rate of 43%

Questions:

1 / How can I maximize my chance of giving the right medical diagnosis, based only on the source of medical experts?

2/ What if the diagnosis asked is not only A or B, but A or B or C?

3/ What if my experts are the best Y experts out of 100, but I don't know the distribution of their success rate?

Thanks very much for your suggestions!

Last edited by skipjack; August 21st, 2019 at 05:21 PM.
alexkn is offline  
 
August 21st, 2019, 06:59 PM   #2
Senior Member
 
Joined: Aug 2008
From: Blacksburg VA USA

Posts: 354
Thanks: 7

Math Focus: primes of course
If future diagnosis success can be related to the past diagnosis history, maximal success would be to get the expert consensus and conclude the opposite, since they are correct less than 50% of the time. I have no comment on the next 2 parts.
billymac00 is offline  
August 21st, 2019, 07:58 PM   #3
Senior Member
 
romsek's Avatar
 
Joined: Sep 2015
From: USA

Posts: 2,644
Thanks: 1476

A and B (and C) are mutually exclusive or not?
romsek is offline  
August 21st, 2019, 10:19 PM   #4
Senior Member
 
Joined: Aug 2012

Posts: 2,426
Thanks: 760

Quote:
Originally Posted by alexkn View Post
I have to make a medical diagnosis for a patient: is he A or B?

I can not make inspection of the patient, and my only help is a poll of N medical experts that observed him.
In the US at least, doctors are not allowed to diagnose patients whom they have not personally examined. When you see a doctor making, say, a mental health diagnosis of some public figure; you can be sure that doctor is breaking the ethical rules of his profession.

You should refuse to render a judgment; and you should demand that one of the N doctors who actually observed the patient should make the diagnosis.

I don't mean to be too literal here; but if the OP is possibly a pre-med trying to figure out their stats homework, let me take the opportunity to suggest that ethics ALWAYS come first. The relationship between the patient always comes first. Statistics could NEVER tell you anything about the human being in front of you.

I would refuse to answer such a question. It would NEVER be possible to render a statistics-based diagnosis on a patient you haven't personally seen.
Maschke is offline  
Reply

  My Math Forum > College Math Forum > Advanced Statistics

Tags
based, chance, maximizing, model, opinion, opinion poll, poll, success



Thread Tools
Display Modes


Similar Threads
Thread Thread Starter Forum Replies Last Post
x% get a binary answer right - how many of them by chance (chance=0.5)? LionessLover Probability and Statistics 2 July 10th, 2015 01:54 PM
Model Associated with Maximizing Profit Alcapwns Calculus 0 February 19th, 2015 01:42 PM
figuring out the average in a poll jaycuts Advanced Statistics 1 April 15th, 2013 12:41 PM
Poll: Have you ever seen a UFO, alien or cosmic object? Trigeometry 93 New Users 1 April 16th, 2009 08:18 AM
Interesting Poll johnny New Users 7 December 1st, 2007 08:34 PM





Copyright © 2019 My Math Forum. All rights reserved.