collects data from every individual in the population
census
statistical study of the entire group of individuals we want information about
population
subset of individuals in the population from which we actually collect data
sample
- state exactly what population we want to describe
- state exactly what we want to measure
sample survey
choosing individuals from the population who are easy to reach results in a ____.
-often produces unrepresentative data & is bias
convenience sample
using a method that favors some outcomes over others
bias
if you’re asked to describe how the design of a study leads to bias, you’re expected to do two things:
1) identify a problem with the design
2) explain how this problem would lead to an underestimate or overestimate
another term for voluntary response samples
self selected samples
- consists of people who choose themselves by responding to a general invitation
- people who feel strongly about an issue
- most responders share same opinion leading to bias
voluntary response sample
usually not representative of a larger population of interest
-uses a chance process to determine which members of a population are included in the sample
ex- pulling names out of a hat
random sampling
-resulting sample of a random sampling method
-size n is chosen in a way which every group of n individuals in the population has an equal chance to be selected as the sample
ex- drawing 20 slips out of a hat containing 200 identical slips
simple random sample (srs)
stratified random sample and strata
- classifying population into groups of similar individuals (strata)
- choosing separate SRS in each stratum and combine these SRSs to form the sample
- works best when the individuals in each stratum are similar with respect to what is being measured
cluster sample
- classify the population into groups of individuals that are located near each other (clusters)
- choose an SRS of the clusters
list of individuals from which a sample will be drawn
sampling frame
bad sampling methods
convenience sampling or voluntary response
occurs when some members of the population cannot be chosen in a sample;
ex- a sample survey of households will not account for homeless people
under coverage
- occurs when an individuals chosen for the sample can’t be contacted or refuses to participate
- can only occur after sample has been selected
non response
-systematic pattern of inaccurate answers in a survey
ex- people lying about age, income, or drug use
response bias
confusing or leading questions that can lead to strong bias
wording of questions
- observes individuals and measures variables of interest but does not attempt to influence the responses
- used to describe group or situation, compare groups, or examine relationships between variables
observational study
- deliberately imposes some treatment on individuals to measure their responses
- only true source of cause and effect
experiment
when two independent variables cannot be distinguished from each other as what is really affecting the dependent variable
confounding
specific condition applied to individuals in an experiment
treatment
experimental units
smallest collection of individuals to which treatments are applied
factors
explanatory variables in an experiment
level
each treatment that is form by combining a specific value of each of the factors
random assignment
experimental units are assigned to treatments using a chance process
replication
using enough experimental units to distinguish a difference in the effects of the treatments from chance variation due to random assignment
principles of experimental design
- comparison
- random assignment
- control
- replication
control
- prevent confounding
- reduce variability in response variable
experimental units are assigned to the treatments completely by chance
completely randomized design
provides baseline for comparing effects of the other treatments
control group
placebo effect
response to a dummy treatment
double blind experiment
neither subjects or researcher knows which is the control group and which receives treatment
single blind experiment
researcher knows difference between the two groups but participants are unaware if they are receiving treatment or placebo
observed effect so large that it would rarely occur by chance
statistically significant
does imply causation
group of experimental units that are known before the experiment to be similar in some way that is expected to affect the response to the treatments
block
randomized block design
- random assignment of experimental units to treatments is carried out separately within each block
- allows us to account for variation in response
matched pairs design
- type of randomized block design for comparing two treatments
- create blocks by matching pairs of similar experimental units
random selection of individuals allows inference about the ____
population
random assignment of individuals to groups permits inference about ____
cause and effect
institutional review board
charged with protecting safety and we being of subjects
basic data ethics
- institutional review board
- informed consent
- confidentiality
lack of realism
can prevent us from generalizing results