AP Statistics Ch 2.3 Experimental Design

treatment

conditions assigned by experimenter, also called explanatory variables or factors

response variable

measured at the end of an experiment, used to compare treatments

experimental units

smallest unit to which a treatment is applied

confounding (extraneous) variable

could impact the results, not an explanatory variable

blocking

splitting experimental units into groups based on a common characteristic, often an extraneous variable

randomization

treatments are randomly assigned to experimental units

replication

having multiple experimental units per experiment

control group

a group that receives no treatment or a placebo treatment

placebo treatment

a treatment that looks like other treatments, but has no active ingredient

single blind

whether either the experimental unit or the person analyzing the data does not know which treatment was assigned to the experimental unit

double blind

when both the experimental unit or the person analyzing the data does not know which treatment was assigned to the experimental unit

direct control

keeping certain conditions or extraneous variables the same across all treatment groups to minimize the impact of those conditions

completely randomized design

NO blocking is involved. subjects are immediately randomly assigned to treatments, or treatments are randomly assigned to subjects

blocked design

create homogenous blocks first to directly control extraneous variables, then randomly assign subjects to treatments or treatments to subjects

matched pairs design

a special type of blocked design. Consists of subjects that are assigned BOTH treatments in random order, or 2 subjects that are similar or homogenous with each being randomly assigned to a SEPARATE treatment