Chapter 7 Flashcards
Which sampling techniques allow generalizing from a sample to population of interest?
Random Sampling techniques (not just sample size) as they lead to unbiased estimates of a population. Probability sampling techniques can also result in a representative sample.
Which sampling techniques do NOT allow generalizing from a sample to population of interest?
Nonrandom and self-selected samples do not represent the population as they are biased. They can be obtained when a researcher samples only those easy to reach or those who are more willing to participate.
What does the quality of a frequency claim depend on?
The ability to generalise from the sample to the population of interest
What does it mean when a sample is externally valid?
When it is unbiased, generalizable or representative
What probability sampling techniques are there?
- Simple random sampling - Choosing a random selection of a population with randomised methods
- Cluster sampling - Clusters of participants within a population are randomly selected and then individuals in each cluster are used.
- Multistage sampling - A random sample of clusters and then a random sample of people in those clusters are selected
- Stratified random sampling - when the researcher selects particular strata and randomly selects individuals in those categories - proportionate to the population
- Combination of these sampling techniques -
- Systematic sampling - Choosing randomly in a systematic way (like picking every 4th person in a line)
What nonprobability sampling techniques are there?
- Convenience sampling - Using a sample of people who are easy to contact and readily available to participate
- Purposive sampling - when only wanting to study certain kinds of people, therefore recruiting only those participants.
- Snowball sampling - to find rare individuals, where participants are asked to recommend acquaintances for the study
- Quota sampling - where the researcher indentifies subsets of the population of interests and then sets a target number for each category in the sample
*they do now allow generalising from a sample to a population
What is oversampling?
When a researcher intentionally overrepresents one or more groups in a sample.
Whats the difference between random sampling and random assignment?
In random sampling, it is down when a researcher creates a sample using a random method. Random assignment is only in experimental designs where researchers place participants randomly in different treatment groups. One concerns, external validity, the other internal.