SOAN 2120 Lecture Notes - Lecture 19: Random Number Generation, Simple Random Sample, Stratified Sampling

• School: University of Guelph
• Department: Sociology and Anthropology
• Course: SOAN 2120
• Professor: David Walters

Document Summary

Nonprobability sampling: sample size in advance, random, mathematical theory, knowledge of population, types: page 219. Haphazard (convenience/accident) worst in terms of you"re ability to get a proper sample of the population. Quota: ensures certain quotas are met, but then relies on haphazard. Purposive: researcher uses judgement to select cases with specific purposes in mind. The purpose is less to generalize to the large population, and more to gain a deeper understanding to specific types. Go to places where they can be found. Researcher continues sampling until all resources (time financial, and energy) are exhausted. Similar to purposive sampling, but the researcher stops when the amount additional information is small of negligible. Snowball: uses referrals or networks to draw sample. Used in studies of people who deviate from the dominant pattern (or people have less predominant characteristics). The goal is to collect information (i. e. , learn more about) on special (or peculiar cases that are non representative of the whole group.