Sampling Flashcards

1
Q

point sampling

A

e.g. names on a list or coordinates on a map

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

linear sampling

A

e.g. sampling along a line such as transect along dunes or a road

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

areal sampling

A

e.g. usually in investigation surveys where a quadrat is used to measure the contents of a 1 metre square area or it could be a grid square on a map

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

random sampling description

A

random number tables to select points e.g. sampling stone size in a river

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

advantages of random sampling

A
  • more statistically useful for subsequent tests, so allows follow up analysis
  • no bias
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

disadvantages of random sampling

A
  • items can be duplicated
  • easy to miss important subdivisions
  • hard to ensure its truly random
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

stratified sampling description

A

-when the parent population or sampling frame is made up of sub sets known as strata of known size. these sub sets make up different proportions of the total , and therefore sampling should be stratified to ensure that results are proportional and representative of the whole

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

advantages of stratified sampling

A
  • ensures no significant aspect of the sub sets is missed

- very flexible and applicable to most investigations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

disadvantages of stratified sampling

A
  • biased
  • proportions of sub sets must be known
  • can’t make valid statistical inferences
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

sampling definition

A

the strategy of collecting data that is representative of the whole population

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

problems if the sample size is too small

A
  • less reliable averages can be taken
  • more affected by anomalies
  • biased
  • anything less than 30 doesn’t provide valid conclusions
  • statistical tests can’t be done
  • might miss something
  • patterns/trends are disorted
How well did you know this?
1
Not at all
2
3
4
5
Perfectly