Surveys and Sampling Methods Flashcards
Population
The entire group of individuals that we want information about
Sample
The part of the population that we actually examine in order to gather information.
Sampling
Involves studying a part of the population to gain information about the whole.
Census
Attempts to contact every individual in a certain population.
Bias
Systematically favoring certain outcomes (want to avoid)
Sampling Methods: Voluntary Response
Flawed method because people with strong opinions are most likely to respond.
Sampling Methods: Convenience
Flawed by choosing individuals who are easiest to reach.
Sampling Methods: Simple Random Sample (SRS)
Each member is equally likely to be selected and each possible group (sample) is equally likely. One population/ One sample
Systematic Sample
Begin at a random point; select every nth member.
Sampling Methods: Stratified Sample
Divide the population into similar groups (strata) and then pick a random sample within each strata.
Sampling Method: Cluster Sample
Divide population into groups. Randomly pick a group and then use each individual in that group
Observational Study
Good: Ethical, easier to conduct (people are already doing the behavior)
Bad: Can’t conclude anything
Experiment
Good: Can use control to conclude causality between the explanatory and response
Bad: Can be unethical, harder and time consuming to set it up
Placebo Effect
When an untreated subject incorrectly believes that they are receiving real treatment and reports an improvement
Control Group
Group of patients who receive a fake treatment; enables control over outside variables on the outcome
Principles of Experimental Design: Replication
Use enough subjects/trials to reduce chance variation. Natural variability occurs.
Principles of Experimental Design: Randomization
Use of chance to assign experimental units to treatments
Statistically Significant
The finding is unlikely under the assumption of what should happen. Rarely happen by chance.
Principles of Experimental Design
Control, Replication, and Randomization
Block Design
Another form of control. The same idea for an experiment as stratified is to selecting a sample.
Match Paris Design
Subjects are matched in pairs to compare responses to two treatments. Pairs could be 2 subjects with similar characteristics that would influence response or 1 subject with both treatments done, with their own control.
Single Blind Experiment
Subjects are unaware of what treatment they receive
Double Blind Experiment
Neither the Subjects nor those who measure the response know which treatment the subject received. Contributed to controlling the Placebo Effect; ensures no unconscious bias on the doctors part
Confounding Response
When variables can’t be distinguished from each other.
Common Response (Lurking variables)
EX: Response to medication is often confounded with better health/health - care in general
Sample Survey
It is a study that uses an organized plan to choose a sample that represents some specific population.
Sample Size
It is the number of individuals, items, or data points selected from a larger population to represent it statistically.
Sampling error/variability
The difference between the sample and the population that occurs due to chance
Probability sample
The selection of a sample from a population, when this selection is based on the principle of randomization, that is, random selection or chance.
Multistage Sample
Conducted by taking and selecting samples from a tiered system. EX: Surveying every county, then every town, then every block…
Strata
Subset (part) of the population (entire collection of items under consideration) which is being sampled.
Under coverage
Occurs when some groups in the population are left out of the process of choosing the sample.
Response Bias
Behavior of respondent courses bias in the sample results. EX: lying
Non response bias
Selected sample members being unable or unwilling to participate, leading to a distortion in the behavioral parameters of interest.
Random assignment
Is a way of placing participants from your sample into different treatment groups using randomization.
Factor
The variables in the study that we believe will influence the results.
Response
A concept, idea, or quantity that someone wants to measure.
Experimental Units
The individuals on which the experiment is done.
Levels
A classification that relates the values that are assigned to variables with each other.
Treatments
A specific experimental condition applied to the units.
Simulation
The imitation of a chance behavior, based on a model that accurately reflects the experiment under consideration.
Trial
A single performance of well-defined experiment
Wording Bias
The wording of a question systematically influences the responses.
