Week 4 10/2/2013 11:57:00 AM
Sampling: selection of individuals & other units of analysis for research.
Representative sample – sample that is similar to the population in
all important areas.
o Can’t ask people in your class – would exclude a majority of
individuals. i.e. people from different faculties.
o Chance of bias – possible participants dependent on non-
universal criteria. Would not represent the population from
which it was selected.
o Steps to minimize bias:
Use random method to pick the sample.
Each element has the same chance of being
selected – number from a lottery cage.
Have adequate sampling frame/list of potential
Do not exclude certain cases as it will not
represent the population.
Have everyone respond.
When people do not respond, it does not
represent the population as those who did
respond might differ from those who did not.
Structured interviews: all respondents are asked exactly the same
questions in the same order with the aid of a formal interview schedule.
Questionnaire: written questions that the respondent completes w/o the
aid of an interviewer.
Sampling error cannot be eliminated entirely.
Probability sample: sample selected at random in which each unit in
the population has a known probability of being selected.
Minimizes sample error