gs--xa
Badges: 10
Rep:
?
#1
Report Thread starter 10 months ago
#1
For iv) How do I select a random sample??
0
reply
Teenie2
Badges: 11
Rep:
?
#2
Report 10 months ago
#2
It could be something as simple as assigning a number to each consultant (from 1 to 600) and then selecting the 1st, 31st, 61st, etc up to 571.
1
reply
Gregorius
Badges: 14
Rep:
?
#3
Report 9 months ago
#3
(Original post by Teenie2)
It could be something as simple as assigning a number to each consultant (from 1 to 600) and then selecting the 1st, 31st, 61st, etc up to 571.
You could indeed, but why use systematic sampling when it would be so easy to do simple random sampling? You've numbered them from 1 to 600, use a random number generator to pick 20 integers from that range.
1
reply
dextrous63
Badges: 14
Rep:
?
#4
Report 9 months ago
#4
(Original post by Gregorius)
You could indeed, but why use systematic sampling when it would be so easy to do simple random sampling? You've numbered them from 1 to 600, use a random number generator to pick 20 integers from that range.
Would this be affected if the list had been arranged in rank order? A simple yes or no will suffice. Thanks
0
reply
Gregorius
Badges: 14
Rep:
?
#5
Report 9 months ago
#5
(Original post by dextrous63)
Would this be affected if the list had been arranged in rank order? A simple yes or no will suffice. Thanks
No.



However, your question alludes to structure in the data that might be relevant to how the research question is approached and analysed in real life (this is going way beyond the question asked). If there's a big disparity between the sizes of the firms, for example, you may wish to weight the sampling towards or away from big firms. This can still be done using a simple random number generator, but would involved allocated a block of numbers to each firm, the size of each block in proportion to the size of each firm.
0
reply
dextrous63
Badges: 14
Rep:
?
#6
Report 9 months ago
#6
(Original post by Gregorius)
No.



However, your question alludes to structure in the data that might be relevant to how the research question is approached and analysed in real life (this is going way beyond the question asked). If there's a big disparity between the sizes of the firms, for example, you may wish to weight the sampling towards or away from big firms. This can still be done using a simple random number generator, but would involved allocated a block of numbers to each firm, the size of each block in proportion to the size of each firm.
So, kinda stratifying things?
0
reply
Gregorius
Badges: 14
Rep:
?
#7
Report 9 months ago
#7
(Original post by dextrous63)
So, kinda stratifying things?
A little bit like stratifying, yes.
0
reply
X

Quick Reply

Attached files
Write a reply...
Reply
new posts
Back
to top
Latest
My Feed

See more of what you like on
The Student Room

You can personalise what you see on TSR. Tell us a little about yourself to get started.

Personalise

With HE fairs postponed, would a virtual HE fair be useful?

Yes (68)
61.82%
No (42)
38.18%

Watched Threads

View All