every population in the group has a chance to be selected and will represent population it was taken from:
Click the card to flip 👆
1 / 43
Terms in this set (43)
every population in the group has a chance to be selected and will represent population it was taken from:
simple random sample
sampling frame
the list of units from which the sample is selected
undercoverage; this is a part of what bias?
If the sampling frame does not cover the entire
population of interest, we have undercoverage. this is a part of selection bias.
Extreme Selection Bias
Responses from a self-selected group, volunteer
sample, convenience sample or haphazard sample
often don't represent any larger group.
Nonparticipation (nonresponse) bias occurs when
a representative sample is chosen but a subset cannot be contacted or chooses not to participate (respond). Response to surveys is voluntary. Those who respond
are likely
Response bias (biased response) occurs when:
participants respond, but they provide incorrect
information, intentionally or not. , or questions are worded biasedly.
In a completely randomized design:
In a completely randomized design, all units
are randomly assigned to treatment conditions.
How to choose simple random sample:
Number the people in the population from 1 to 10,000. and choose 10 random numbers.
Stratified Random Sampling
• Divide population of units into homogeneous groups and take a simple random sample
from each of the strata. Example: Want to know how UCI undergraduate
students feel about shuttle service. Stratify by
Housing Area:
- Take simple random sample from each of 8 strata - the
seven housing areas (Arroyo Vista, Campus Village,
Mesa Court, Middle Earth, Vista del Campo, Vista del
Campo Norte, Camino del Sol), and commuters.
Other examples:
- When measuring weight, stratify by sex (male/female).
- When measuring women's opinions on men, stratify
by marital status (married/single/divorced/widowed).
Cluster Sampling :
Divide population of units into small
heterogeneous groups (called clusters), take a
simple random sample of clusters. and survey EVERYONE in the randomly chosen clusters. • A cluster typically comprises units that are
physically close to each other in some way, but
still have variability in the variables of interest.

Examples:
- For a survey of UCI students, use classes as
clusters when measuring hours of sleep.
- When measuring length of lunch breaks in a very
large office building, use floors as clusters.