Data Collection Flashcards
What is a population?
The whole set of items that are of interest
What is a sample?
Some subsets of the population intended
What is a sampling unit?
Each individual thing that can be sampled in the population
What is a sampling frame?
The list formed when sampling units are named/numbered
What is a census?
Data collected from the entire population
Pros and cons of a census
Pros
- gives a completely accurate result
Cons
- time consuming
- expensive
- cannot be used when testing involves destruction
- large vol. of data to process
Pros and cons of a sample
Pros
- cheaper
- quicker
- less data to process
Cons
- data=x accurate
- data=x large enough to represent small subgroups
What is random sampling?
When each sampling units name in the sampling frame has an equal chance of being chosen=avoids bias
Simple random sampling
What is it:
Every sample has an equal chance of being selected.
Method:
Assign each item a number from 1 to n (n=no. Items)
Use random number generator, or lottery sampling’ (names in a hat) to generate the required sample size. Ignore repeats.
Select items that correspond to the number.
Pros and cons of simple random sampling
Pros
- bias free.
- easy and cheap to implement.
- each number has a known equal chance of being selected.
Cons
• Not suitable when population size is large.
• Sampling frame needed.
Systematic random sampling
What is it :
Required elements are chosen at regular intervals in ordered list.
Method:
Assign each item a number from 1 to
n (where n items)
Calc k:
k =pop size (N)/samp size (n)
Generate a random number between 1 and k as your starting number
Then select every kth element
Pros and cons of systematic random sampling
Pros
- Simple and quick to use.
• Suitable for large samples/ populations.
Cons
- Sampling frame needed.
• Can introduce bias if sampling frame not random.
Stratified random sampling
What is it :
Population divided into groups (strata) and a simple random sample carried out in each group.
sample size (n)
Same proportion/population size (N)
sampled from each strata.
Used when sample is large and population naturally divides into groups.
Pros and cons of stratified random sampling
Pros
• Reflects population structure.
• Guarantees proportional representation of groups within population.
Cons
• Population must be clearly classified into distinct strata.
- Selection within each stratum
suffers from same disadvantages as simple random sampling.
Quota sampling (non-random)
What is it :
Population divided into groups.
A quota of items/people in each group reflects the group’s proportion in the whole population.
Interviewer selects the actual sampling units. (eg advertise) until the quota is full. Ignore items from a group once sample is full.