Chapter 7: Sampling

convenience and volunteer

2 ways a sample can be biased

probability sampling

every member of the population has the same chance of being selected

simple, systematic, cluster, stratified, oversampling

5 techniques for random sampling

cluster sampling

cluster the population, randomly select clusters, collect data from all people in that cluster

stratified random sampling

selecting every 3rd person from a population

cluster sampling

A researcher wants to study the study habits of Tulane students. They randomly select 5 classes and survey every student in those classes.

stratified random sampling

A researcher wants to study the study habits of Tulane students. They divide students into 4 groups based on class year(freshmen, sophomores, juniors, and seniors) and randomly select students from each group.

oversampling

A researcher wants to study the experiences of Tulane students. Since international students make up a smaller percentage of the population, the researcher intentionally selects more international students than their proportion of the student population.

oversampling

Intentionally sample more people from a smaller or underrepresented group to ensure they are adequately represented in the study.

oversampling

Researcher wants to sample 1,000 people and make sure South Asians are a part of the sample. But maybe the location where the data is collected only has 4% South Asians. 40 people may not be enough for statistical reasons so the researcher decides to sample 100. South Asian category of people will count for 10% instead of 4

random assignment

enhances internal validity by ensuring comparison and treatment group have same kinds of people

convenience, purposive, snowball, quota

non probability sampling

quota sampling

Ex. surveying students until you have 50 freshmen, 50 sophomores, etc

quota sampling

Recruiting participants until predetermined numbers for different groups are reached, without random selection

frequency claims

external validity is crucial for _____

sampling method

external validity comes from the _______