Week 2: Sampling data collection Flashcards
Explain each of the 4 types of populations. Give an example:
1. Target population
2. Source population/sampling frame
3. Sample population
4. study population
- target pop=the broad population to which the results of a study should be applicable. People we want our results to apply to. Ex: everyone living in Canada
- Source pop/sampling frame = subset of individuals from the target pop from which potential study participants will be sampled from. People from whom the population is selected. Ex: everyone registered to vote in Canada
- sample pop = people from the source pop who are approached to participate in the study. Ex: random sample from those listed
- study population = people who actually took part in the survey. Ex: those who agree to take part
What is probability sampling?
using selection techniques where the probability of selecting each sampling unit is known
- What is sampling bias?
- What is non-random sampling bias?
- occurs when the individuals sampled for a study systematically are not representative of the source pop as a whole
- when each individual in the source pop does not have an equal chance of being selected for the sample pop
Explain each type of probability-based sampling techniques:
1. simple random sampling
2. systematic sampling
3. stratified sampling
4. cluster sampling
5. multistage sampling
- each person has an equal chance of being selected. Ex: 12/36 people randomly selected
- after a random start point, every nth person is selected. Ex: order people into a random line and then select every 3rd person
- simple random samples selected from each of several strata. Ex: group people based on sex (male, female, other) then randomly select 3 people from each group.
- Natural clusters are selected for inclusion instead of individuals (schools, neighborhoods). Observation is made on all units within a cluster. Ex: 4/10 clusters are randomly selected. All within the selected cluster are recruited in the study
- primary sampling units are randomly selected (municipalities) and secondary units are randomly selected from the primary units (individuals). Ex: 5/10 clusters are randomly selected. Within the selected clusters, another 5/10 people are randomly selected
- What is non-probability based sampling?
- explain each type of non-prob sampling techniques:
a) convenience sample
b) purposive sampling
- a method of selecting units from a population using a subjective (i.e. non-random) method
- a) Selection from a nonprobability-based source population due to ease of access to those individuals, schools, workplaces, organizations, or communities
b) Recruitment of the participants for a qualitative study based on the special insights they can provide. involves key informants
what are key informants?
individuals selected to participate in a study because they have expertise relevant to the study question - non random sampling
what is external validity
the extent to which you can generalize the findings of a study to other situations, people, settings, and measures
what is the difference between sampling vs selection bias?
sampling bias = occurs when some members of a population are systematically more likely to be selected in a sample than others; threat to external validity because it limits the generalizability of the study
selection = when members of the study population are not representative of the source population from which they were drawn. Ex: when healthier or educated people are more likely to volunteer for research
Explain each type of selection bias:
1. berkson’s bias
2. healthy worker bias
3. exclusion bias
- berkson’s bias = when cases and controls for a study are recruited from hospitals and therefore are more likely than the general population to have comorbid conditions
- healthy worker bias = can occur when participants are recruited from occupational populations and therefore are healthier than the general population
- exclusion bias = when different eligibility criteria are applied to cases and control, such as when controls with health conditions related to an exposure are excluded but cases with those comorbidities are not excluded
- What are some examples of vulnerable populations? Why is recruiting them unethical?
- systematic __________ is also unethical
- young children, serious health issues, people in prison, no ability to make independent choices. they have limited ability to make an autonomous decision about volunteering to participate. They could have more potential risks
- exclusion
recruiting too many participants ______ _________
recruiting too few participants makes the study __________
wastes resources
invalid
Null means that there is no _________ or _________ association
exposure or outcome association
What are Type 1 (a) errors?
What are Type 2 (b) errors?
Type 1 (a) errors = false positive. occurs when a study population yields a statistically significant test result even though a difference of association does NOT actually exist
Ex: Telling a man they are pregnant
Type 2 (b) errors = false negative. occurs when a study population finds no significant results even though a significant DIFFERENCE in association exists Ex: telling a pregnant women she is not pregnant
1 - B is referred to as the ________ of the study. This shows how much the study is able to detect a _____________ and should be calculated (before/after) the study is completed
power, true association, after
- What is an interview? Pros and cons?
- what is a self administered survey? Pros and cons?
- process of verbally asking a participant questions and recording that person’s responses. Pros = train interviewers to ensure accurate and complete questionnaires. Cons = time and money commitments
- a questionnaire form that participants complete by themselves using a paper and pencil version or online. Pros = cost and time efficient, can get lots of participants, get answers to sensitive questions. Cons = hard for those with low literacy, limited internet access, or do not know how to use computers
