Statistics Flashcards

1
Q

Assumptions for binomial model to be valid

A
  1. Probability remains constant
  2. Events occur independently of one another
  3. There are only two possibilities for each outcome
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Describe how to collect a random sample of k out of N items

A
  1. Give each item a number from 1, 2, … , N
  2. Generate a random number between 1 and N using a calculator
  3. Continue until k different items have been selected
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

3 disadvantages of census

A
  1. Takes a lot of time, effort and money to carry out
  2. Can be difficult to make sure all members are surveyed
  3. Impractical if tested items are used up or damaged
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Advantage of census

A

Gives an unbiased, accurate representation of the whole population

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

Advantage of simple random sampling

A

Completely unbiased - each member has an equal chance of being selected

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Advantage/disadvantage of systematic sample

A
  • Should give an unbiased sample
  • But if interval coincides with a pattern, the sample could be biased
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Number needed for each category in stratified sampling

A

(size of category in pop. ÷ total pop. size) x (total sample size)

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

2 advantages of stratified sampling

A
  • If categories are disjoint, should give a representative sample
  • Useful when results vary depending on categories
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Disadvantage of stratified sampling

A

The extra detail needed can make it more time consuming and expensive

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Describe method for quota sampling

A
  1. Divide population into categories
  2. Give each category a quota (the number of members to sample)
  3. Collect data until quotas are met in all categories (without random sampling)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

2 advantages of quota sampling

A
  1. Easy for interviewer as they don’t need a list of the whole population
  2. Non-response is less of a problem
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Disadvantage of quota

A

Can be biased by the interviewer as selection isn’t random

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

Advantage of opportunity sampling

A

Data can be gathered quickly and easily

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Disadvantage of opportunity sampling

A

It isn’t random and can be very biased - no attempt to make the sample representative

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Describe method for cluster sampling

A
  1. Divide the population into clusters covering the whole population
  2. Randomly select clusters to use in the sample, based on the required sample size
  3. Either use all members of the selected clusters (one-stage cluster sample) or randomly sample within each sample (two-stage cluster sample)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

2 drawbacks of cluster sampling

A
  • Results can be less representative
  • Not always possible to separate the population into cluster in a natural way
17
Q

Describe method for sampling using self-selection/volunteer sampling

A
  1. Advertise or appeal to the whole population
  2. Either use everyone who responds as the sample, or take a sample of them that best represents the population
18
Q

3 advantages of self-selection/volunteer sampling

A
  1. Requires little time or effort in finding sample members
  2. Non-response is less of an issue
  3. Sometimes is the only way to find member of a population
19
Q

Disadvantage of self-selection/volunteer sampling

A

There can easily be trends within the respondents, such as people having strong opinions, which would lead to bias