LinuxQuestions.org
Welcome to the most active Linux Forum on the web.
Go Back   LinuxQuestions.org > Forums > Non-*NIX Forums > General
User Name
Password
General This forum is for non-technical general discussion which can include both Linux and non-Linux topics. Have fun!

Notices


Reply
  Search this Thread
Old 02-13-2020, 12:03 PM   #1
business_kid
LQ Guru
 
Registered: Jan 2006
Location: Ireland
Distribution: Slackware & Android
Posts: 11,028

Rep: Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251
[SOLVED] Statistics - revisited


I got a statistics formula here before (Thanks guys), but now I believe what I have is/was wrong, so I have to ask again.

I'm trying to calculate an estimate of the statistical probability of a particular gene being inherited for the number of generations necessary for evolution. Let's say 2500 generations for the purposes of establishing a formula.

Now genetic inheritance has a probability of [P=1 in 2] or {P=0.5} per mutation, per generation. So the probability of holding 1 mutation in the first generation for 2500 generations is [P=1 in 2^2499] or {P=0.5^-2499}. OK.

Here's where it gets messy: The probability of holding 2 mutations per generation is 1 in 4; of 3 mutations, 1 in 8, etc. So if we write the progression, allowing 1 mutation per 10 years, we get

[P = 1 in (2)^2499+(2)^2489+(2)^2479+≈(2^250)^9]
=1.88e752 + 3.37e1498 + 5.76e2338 + ≈2.08e677

We can simplify a little; These are brought to Scientific notation, which has only 2 decimal places, so all the minor terms are lost unless they affect the first 2 decimal places.

So I would like to know how to sum that expression, short of doing it longhand. It has a geometrically progressive element to the power of an negative arithmetically progressive element . As no evolutionist I have asked can give me any numbers, estimates, or guesses as to how many relevant mutations over how many generations/years a change of species takes, I calculate several possibilities. In the same article, I have a scenario of 1,000 mutations over 20,000 generations, and I certainly don't want to do that out longhand!

Presuming that can't be done I would like to find the largest term. With additive probabilties, anything whose exponent is 2 or more smaller gets corrected out in Scientific notation, so only the near maximum terms matter.

EDIT: I don't need the sum at all - I need the maximum evaluated term. Because term 2, etc includes the term 1 probability. A more correct form would be

P= 1 in (2^10)+(4^10)+(8^10)+(2^250)^9. Summing that would get it. The 1st formula is right for getting the maximum term

Last edited by business_kid; 02-14-2020 at 06:43 AM. Reason: solved
 
Old 02-14-2020, 06:42 AM   #2
business_kid
LQ Guru
 
Registered: Jan 2006
Location: Ireland
Distribution: Slackware & Android
Posts: 11,028

Original Poster
Rep: Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251Reputation: 1251
[SOLVED] Statistics - revisited

I have this worked out. Term n of my first equation serves as an (slightly low) approximation. The thing I asked for the sum of is actually hopelessly low.
Geometric Progressions: Term n=a*(r^n-1). a=2; r=2. The Geometric bit is 2,4,8,16 etc.
Arithmetic Progressions: Term n=a+((n-1)d). a=2499; d=-10. The arithmetic bit is 2499, 2489, 2479, etc.

The maximum evaluated term (By trial and many, many errors) is term 126: (2^125)^(2499+(1250*-10)) = 2.04e46,998 or {4.92e-46999}
 
  


Reply


Thread Tools Search this Thread
Search this Thread:

Advanced Search

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 Off
HTML code is Off



Similar Threads
Thread Thread Starter Forum Replies Last Post
Partition Removal Revisited ca0695 Linux - Software 3 08-19-2001 01:09 AM

LinuxQuestions.org > Forums > Non-*NIX Forums > General

All times are GMT -5. The time now is 05:21 PM.

Main Menu
Advertisement
My LQ
Write for LQ
LinuxQuestions.org is looking for people interested in writing Editorials, Articles, Reviews, and more. If you'd like to contribute content, let us know.
Main Menu
Syndicate
RSS1  Latest Threads
RSS1  LQ News
Twitter: @linuxquestions
Facebook: linuxquestions Google+: linuxquestions
Open Source Consulting | Domain Registration