Unit 3: Collecting Data

population

the entire group of individuals we want information about

sample

the subset of individuals we collect data from

census

a collection of data from every individual in a population

sample survey

a study that collects data from a sample to learn about the entire population that sample was chosen from

random sampling

using a chance process to determine which individuals from a population are chosen for a sample

observational study

study that observes individuals and measures variables but does not attempt to influence responses

prospective observational study

an observational study tracking data into the future

retrospective observational study

an observational study examining existing data from a sample

an experiment

a study that imposes treatments and influences individuals to measure their responses

simple random sample

a sample chosen in a way that every group of individuals within that population has an equal chance of being selected

sampling without replacement

when an individual has been selected, that same individual cannot be selected again

sampling with replacement

when an individual has been select, that same individual can be selected again

stratified random sample

a sampe selected by choosing an SRS from each stratum and combining the SRS into one overall sample (Some From All)

strata

groups of individuals in a population that share characteristics thought to be associated with the variable being studied

cluster sample

a sample selected by randomly choosing clusters and including each member of the selected cluster (All From Some)

cluster

a group of individuals from a population that are located near each other

systematic random sample

a sample selected from an ordered arrangement of the population by randomly selecting one of the first k individuals and choosing every kth individual thereafter

convenience sample

a sample done with easy to reach individuals

bias

if a statistical study is likely to overestimate or underestimate the value we want

a voluntary response sample

a sample that consists of people who choose to be in the sample by responding to a general invitation

undercoverage

when some members of the population are less likely to be chosen or cannot be chosen in a sample

undercoverage bias

when underrepresented individuals differ from the population in a way that affects their responses

voluntary response bias

when a group of individuals that chooses to respond differs from the population in a way that affects their responses

nonresponse

when an individual chosen for a sample can’t be contacted or chooses not to respond

nonresponse bias

when individuals who cannot be contacted or refuse to respond differ from the population in ways that affect their responses

response bias

when there is a consistent pattern of inaccurate responses to a survey question

explanatory variable

the variable that helps explain or predict changes in the response variable

response variable

the variable that measures the outcome of a study

confounding

when two variables are associated in a way that their effects on a response variable cannot be distinguished from each other

treatment

a specific condition applied to individuals in an experiment/a combo of specific values of several explanatory variables if the experiment has several explanatory variables

experimental unit/suject

the object to which a treatment is randomly assigned

placebo

a treatment with no active ingredient but is otherwse like other treatments

factor

an explanatory variable that is manipulated and may cause a change in the response variable

level

a different value of a factor

a control group

treatment group use to provide a baseline for comparing effects of other treatments

the placebo effect

the fact that some subject in an experiment will respond favorably to any treatment, even inactive treatment

a single-blind experiment

an experiment where either the subjects or people interacting with them know what treatment the subject is receiving

a double-blind experiment

an experiment where neither the subjects nor the people interacting with them know what treatment the subject is receiving

random assignment

when treatments are assigned to experimental units by chance processes

a completely randomized design

when treatments are assigned completely at random

replication

the act of giving each treatment to enough experimental units so a difference in effects of treatments can be distinguished from chance variation due to random assignment

to control other variables

to keep them constant for the entire group of experimental units

a block

a group of experimental units that are known to be similar before the experiment in some way that is expected to affect the response to treatment

randomized block design

when the random assignment of experimental units to treatments is carried out separately within each block

matched pairs design

a common experimental design for comparing two treatments using blocks of size two

statistically significant results

results where an observed differance between groups in an experiment is so large that it is unlikely to be explained by chance variation in random assignment

the scope of inference

the method of describing the types of conclusions we can make based on how the data was collected