Sampling Flashcards
Population
Entire Group of Interest
Sample
The subset of the population that is chosen for the study
Census
When every member of a population is included in the study
Sampling
The process by which the researcher chooses a sample from a population
Goals of Sampling?
External validity, economic sample, representation of the population
Representative Sample (Unbiased Sample)
All members of the population have an equal chance of being included in the sample
Sampling Error
The extent to which the sample is not representative
Unrepresentative Sample (Biased Sample)
(also known as nonprobability + nonrandom)Sample in which some members of the population are left out (some members may be over/underrepresented).
What are the 2 sampling techniques?
Probability + Nonprobability
What are the 4 types of probability sampling?
Simple random sampling, systematic sampling, cluster sampling, stratified random sampling
What are the 4 types of nonprobability sampling?
Convience sampling, quota sampling, purposive sampling, snowball sampling
Probablity Sampling
(also known as random) Results in an unbiased or representative sample - Each member of the pop. has an equal chance of being included
Simple random sampling
Choose random set of people from entire pop. to be in your sample (EX: use a random number table or random # generator)
Systematic Sampling
Choosing “ever so many” individuals for the sample (do not need a sampling frame) (EX: choose every 4th person that comes into the ER)
Do you need a sampling for simple random sampling?
Yes - The name and contact info for everyone in your population
Cluster Sampling
Clusters of participants w/n the population are selected at random. Collect data from every ind. in each cluster
Multistage Sampling
Clusters of participants w/n a population are selected at random, then you collect data from a random sample w/n each cluster
Stratified random sampling
Researcher identifies a particular sociodemographic category (strata). Choose randomly w/n each category
Proportionate sampling method
Sampling is chosen in proportion to its representation in the population
*Additional Information about Cluster/Multistage
Cluster are not selected w/proportions in mind. They often use naturally divided groups (school districts, etc.)
*Additional Information about Stratified
Final sample sizes of each strata are proportional to those in the population. Divide the population based on shared characteristics (occupation, age, race, etc.)
Convenience Sampling
Sample consisting of people who are easy to contact and readily available
Quota Sampling
Researcher ensures a certain number of percentage of people from a particular group(s) are included in the sample
Purposive Sampling
Only recruiting certain kinds of people in your sample
(EX: study on barriers to cancer screening)
Snowball Sampling
Participants are asked to recommend a few acquaintances for the study
(EX: recruiting parents w/toddlers)
Self-Selection
When a sample contains only people who volunteered to participate. Automatic in nonprobability samples, but can happen w/ probability samples. A sample containing too many of the most unusual people
Misgeneralization
Attempting to generalize results based on unrepresentative people
Nonprobability - “WEIRD Samples”
Western, Educated, Industrialized, Rich, Democratic
*Notes on sample size
Having a larger sample does not always make our sample more representative. For external validity of a sample, it is HOW and NOT HOW MANY. Sample size is a statistical validity issue, not an external validity issue