Study and Sampling Types

Study and Sampling Types

Census: Information collected about an entire population. (i.e. the sample is identical to the population)

Longitudinal Study: A study that follows individuals over a long period of time.

Example: Track the grades of high school math students from grades 9-12. Your OSR.

Cross-sectional Study: A study that considers individuals from different groups at the same time.

Example: News media surveying people across Canada before an election campaign to determine public support for the various candidates and parties.

Time Series Data: Data that have been accumulated over an extended period of time; often collected for a longitudinal study.

Examples: Consumer Price Index (CPI) calculated at regular intervals, your dental records are updated periodically by your dentist.

Sampling Interval = (if you are choosing a sample by asking every 5th person in the population to respond, then the sampling interval is 5)

Random: Occurring completely by chance. Random sampling helps reduce bias.

Random Sampling Types:

Simple Random: Sample selection is completely random using instruments of chance.

Systematic Random: Has a random starting point but follows a pattern using the sampling interval. (Example, I randomly select a student in the class, but then I sample every 3rd std starting from them.)

Stratified Random: The population is divided into strata (or groups), and within each stratum a simple random sample is taken. The strata may be chosen according to some criteria. (Example, PHS students are stratified by grade level and a random sample of students is selected from each grade.

Cluster Random: The population is divided into clusters (or groups) and then entire clusters are randomly selected. (Example, the classes at PHS are clusters of students, and our class is one of the clusters that can be randomly selected by the principal.)

Multi-stage Random: Groups are selected using simple random method, and then within each selected group, simple random method is used again to select the sample. (Example: 10 postal codes are randomly selected from within the City of Cambridge, and then within each of the 10 selected postal codes, 5 houses are randomly selected to survey)

Destructive Sampling: The samples are destroyed in the process of testing. This is a common practice in quality control at manufacturing facilities. (Example: 5 cookies from each batch of 10,000 are tasted by quality control inspectors. The sampled cookies cannot be sold and are disposed of after tasting, but are a sample of the entire batch)