1.2 Random Sampling Flashcards

1
Q

What would we want from random sampling

A

Each thing in our sampling frame to have an equal chance of being chosen, in order to avoid bias

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

3 types of random sampling

A
  • Simple random sampling
  • Systematic sampling
  • Stratified sampling
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Method of simple random sampling

A
  • To carry out a simple sample, size n, from a population size N, firstly, we need a sampling frame
  • Each item is assigned a different number from 1 to N. Use a random number generator to select ā€˜nā€™ unique numbers
  • Choose the items corresponding to these numbers to form the sample
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Advantages of simple random sampling

A
  • Avoids bias as each sampling unit has a known equal chance of being selected
  • Easy and cheap to implement for a small population and samples
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Disadvantages of simple random sampling

A
  • Not suitable when population size is large
  • A sampling frame is needed
  • Sample may not accurately reflect the population (could by chance be all girls, eg in bluebook)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Full marks layout of simple random sampling question

A
  • Using the [list, eg register] as a sample frame, assign the [items] a number from [1 to (total number of items)]
  • Use a random number generator to get [whatever sample asked for in Q] unique numbers
  • Choose the [items] corresponding to those numbers to form the sample
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is systematic sampling

A

In systematic sampling, the required elements are chosen at regular intervals from an ordered list

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

Method of systematic sampling

A

To carry out systematic sampling (size n, from population size N) again you need a sampling frame.

  • Each item is assigned a different number from 1 to N. Starting at a random item (number chosen by random number generator) between 1 and k (k=pop size, N/samp size, n). Take every kth element to from the sample

eg Q in bluebooks

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

Advantages of systematic sampling

A
  • Simple & quick to use
  • Suitable for large samples & populations
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Disadvantages of systematic sampling

A
  • Can introduce bias if sampling frame is small & not random as patterns can be picked up in the data
  • A sampling frame is needed
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Full marks layout of systematic sampling questions

A
  • Using the [list] as a sample frame, assign each name a number from 1 to [total pop]
  • total pop size/sample size asked for = k
  • Use a random number generator to obtain a number between 1 and k. Starting with that number , select every kth name to form the sample
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is stratified sampling

A

Population is divided into groups (strata) & a simple random sample is carried out in each group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Method of stratified sampling

A
  • To carry out a stratified sample (size n from population size N) we need a sampling frame and distinct strata. The same proportion n/N is to be sampled from each strata
  • Within each strata, each item is assigned a different number & a random number generator is used to select the number of unique numbers required
  • Choose the items corresponding to these numbers to form the sample
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Advantages of stratified sampling

A
  • Sample reflects population structure
  • Guarentees proportional representation of groups within population
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Disadvantages of stratified sampling

A
  • Sampling frame is needed & population must be clearly classified into distinct strata
  • Selection within each stratum suffers from same disadvantages as simple random sampling
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Full mark layout of stratified sampling questions

A
  • [1st group, male size]/[total pop] = k males
    [2nd group, female size]/[total pop] = b females
  • Assign each [1st group, males] a number from 1 to [male size] & [2nd group, females] a number from 1 to [female size]
  • Use a random number generator to get k unique numbers of [males] and b unique numbers of [females]
  • Select the [people] corresponding to those numbers to form the sample