Does this problem make sense? (Probability and Survey Sampling)

  • Context: Undergrad 
  • Thread starter Thread starter gjones89
  • Start date Start date
  • Tags Tags
    Sampling Survey
Join the discussion
Ask a follow-up here, or get your own question answered by working scientists, mathematicians and engineers — people, not an autocomplete.
Real named experts · corrections over time · the nuance an AI answer skips
1 reply · 2K views
gjones89
Messages
4
Reaction score
0
Hi,

I am trying to answer a question for an assignment, but am convinced that it doesn't make sense. Please see here: http://img813.imageshack.us/img813/1585/qst.png

My problem is with Plan 2 in the question. The probability of selecting any of the 5 elements on the first selection is 1/5. So for example, I can select element 1 with probability 1/5 on the first pick. But then, how can I work out the probabilities of choosing the 2nd, 3rd, 4th and 5th elements on the 2nd pick? Obviously these probabilities can't just be the numbers in the last column in the table, because if I add together the probabilties for choosing elements 2, 3, 4, and 5 (ignoring row 1 because we are sampling without replacement), I get (1/4 + 1/2 + 1/5 + 7/40) = 9/8, i.e. a total greater than one!

What is going on here? I want to work out the probability of picking, for example, element 1 on the first pick and element 2 on the second pick. Can anyone help?

Thanks.
 
Last edited by a moderator:
Physics news on Phys.org
If I understand problem correctly then
P(S[2]=i)=P(S[2]=i|S[1][tex]\neq[/tex]i)*P(S[1][tex]\neq[/tex]i)

so for i=1 then

P(S[2]=1)=(1/8)*(4/5)


will be the same method for other elements