sampling methods

Convenience Sampling

• not a random sampling technique

• The researcher selects those that are convenient respondents

• Weakness- No guarantee that all individuals from the population have an equal chance of being selected

• Weakness- Bias is easily introduced as a result of the researchers personal preferences

Quota Sampling

• not a random sampling technique

• used in opinion polling and market research

• for example an interviewer might be told to select 20 men, 20 women and 10 children

• Weakness- Bias can still be introduced depending on how intimidating the interviewees are to the researcher

Systematic Sampling

• A random sampling technique

• every nth element is chosen after starting at a random point

• all members of the population must be organised, e.g. alphabetically, If a sample size of n is required from a population of size p, then the amount of groups there will be, x will be calculated as x = p / n. Once x, the number of groups is established a random number generator will be used to generate a random number between 1 and x ( r ). we then need to select item r, r+x, r+2x, r+3x etc

• Weakness- impossible for 2 consecutive items in a list of the population to be included in the sample

• Weakness- if p / n does not return an integer it means remaining members of the population cannot be in the sample

• if someone is unavailable the next item in the population list may be selected

Simple Random Sampling

• Random sampling technique

• all members of a population of size N are identified and assigned a numerical value. If a sample size n is required, a random number generator is sued to generate n random values between 1 and N

• Ensures that each member of the population has an equal chance of being selected

• Weakness- it is possible for one group to be under represented

• Weakness- each member of a population will need to be identified and then numbered, this is time consuming and expensive

Stratified Random Sampling

• a stratified sample is obtained by taking samples from each subgroup of a population in proportion to their relative size within the population.

Cluster Sampling

• entire population is divided into groups, e.g. neighbourhood, and a random sample of these groups are selected

• This is more practical and/ or economical than simple random sampling or stratified sampling