Data Collection Flashcards
Population
Whole set of items that are of interest.
Sample
Subset of the population intended to represent the population.
Sampling frame
Set of individuals or items from which a sample has been drawn.
Sampling unit
People or items that have been sampled.
Census
Data from the entire population.
Advantages/Disadvantages of Census
Advantages: should give a completely accurate result
Disadvantages: time consuming, expensive, can’t be used when testing involves destruction(people dying, moving away in 4 years) and it is a very large volume of data to process
Sampling
Set of items or events possible to measure
Advantages/Disadvantages of Sampling
Advantages: cheap, quick and is a low amount of data to process
Disadvantages: data may not be accurate and data may not be large enough to represent small sub-groups
Parameter
A calculation of a sample or population such as mean. Also a variable that does not change within a specific instance but can be adjusted to define different instances.
Sampling error
Difference between the actual value of a parameter and the value derived from a sample.
Bias
Systematic error in the collection of a sample(examples: asking a leading question, small sample size, wrong person asking questions, sample not representative of whole population)
Random Sampling
When every item or person has an equal chance of being selected for the sample.
Non-Random Sampling
Sample selection process where not all individuals in the population have an equal probability of being chosen.
Simple Random Sampling
When every sample has an equal chance of being selected. You can do it by giving each sampling unit an identifying number and using a random number generator to select one.
Advantages/Disadvantages of Simple Random Sampling
Advantages: cheap, easy, unbiased as every number has an equal chance of being selected
Disadvantages: not suitable for a large population, sampling frame(list of names/items) needed
Systematic Sampling
Required elements that are chosen at regular intervals in an ordered list. (example: taking every 12th element where k=population size/sample size starting a random item between 1 and k)
Advantages/Disadvantages of Systematic Sampling
Advantages: simple, quick and suitable for large populations
Disadvantages: sampling frame needed, bias if sampling frame isn’t random(example: you need to pick every 5th item)
Stratified Sampling
When a population is divided into strata(groups) and a simple random sample is carried out on each group.(example: same proportion of sample size/population size sampled from each group(strata))
Advantages/Disadvantages of Stratified Sampling
Advantages: reflects population structure, guarantees proportional representation of groups within population, distinct groups with no overlap
Disadvantages: population must be clearly classified into distinct strata and selection from each stratum suffers the same as simple random sampling
Random Sampling issue
Random sampling may be problematic at times as there is no sampling frame for something such as everyone in the Uk that is left handed. This is why quota sampling may be used instead.
Quota Sampling
Population divided into groups according to characteristics. It is a quota of items/people in each group that is set to reflect the group’s proportion in the whole population.
Advantages/Disadvantages of Quota Sampling
Advantages: quick, cheap, allows small sample to still be representative of population, no sampling frame required and allows for easy comparison between groups in the population
Disadvantages: non-random sampling introduces bias, dividing a population into groups can be inaccurate, non responses aren’t recorded and increasing number of groups increases time taken/cost.
Opportunity/Convenience Sampling
Sampling taken from people who are available at time of study who meet the criteria.
Advantages/Disadvantages of Opportunity/Convenience Sampling
Advantages: easy to carry out, inexpensive
Disadvantages: unlikely to produce a representative sample, highly dependent on individual researcher
Cluster Sampling
Non-random stratified sampling which define each cluster and you collect random samples from each cluster. Non random as you choose the cluster, but data is random.
Advantages/Disadvantages of Cluster Sampling
Advantages: no sampling frame needed and not expensive to identity clusters
Disadvantages: unlikely to provide a representative sample because clusters have similar characteristics resulting in an over representation within a cluster
