0
   

Extrapolation

 
 
vicbay
 
Reply Wed 30 Sep, 2015 12:26 am
Hi,

I have a question regarding extrapolation.
Its hard to formulate the question, so I asked a couple...

I know what extrapolation means, but I have the below scenario which I need some clarity on:

We have to do 6000 surveys in a month.
I only manage to do 5000.
Based on the 5000, do we extrapolate the data to "look" like 6000?
In other words the 5000 in fat becomes 6000?
OR
Based on the 5000, we extrapolate the data to make future decisions (trends) based on the data. Almost linear...something going forward.

So does extrapolation of the 5000 means it makes it 6000 or can we only predict future trends based on the 5000.

If we can use the 5000 to make it look like 6000....then surely you can use 1000 instead of 5000.
What is the statistical minimum of the sample based on the size of the universe? (Ratio)

Thanks!!
John
  • Topic Stats
  • Top Replies
  • Link to this Topic
Type: Question • Score: 0 • Views: 371 • Replies: 1
No top replies

 
engineer
 
  1  
Reply Wed 30 Sep, 2015 05:24 am
@vicbay,
5000 samples vs 6000 samples is not extrapolation. Extrapolation is looking at a trend and assuming that trend will continue on into a region where you don't have any data. An example would be looking at the stock market performance over the last twenty years and using that to predict the performance ten years from now. You can't extrapolate to make 5000 samples look like 6000.
0 Replies
 
 

Related Topics

 
  1. Forums
  2. » Extrapolation
Copyright © 2024 MadLab, LLC :: Terms of Service :: Privacy Policy :: Page generated in 0.08 seconds on 11/16/2024 at 05:48:31