Mastering AP Statistics Unit 3: Experimental Design

Observational Study

A study where the researcher observes individuals and measures variables without influencing responses.

Experiment

A study where the researcher imposes treatments to measure responses and determines causation.

Experimental Units

The smallest collection of individuals to which treatments are applied.

Explanatory Variable (Factor)

The variable being manipulated to predict changes in the response variable.

Levels

The specific values chosen for a factor in an experiment.

Treatments

The specific conditions applied to individuals in an experiment.

Control

Keeping other variables constant to prevent confounding in an experiment.

Randomization

Assigning experimental units to treatments using a chance process.

Replication

Using enough experimental units to identify the treatment effect from chance variation.

Completely Randomized Design

A design where all experimental units are allocated at random among treatments.

Randomized Block Design

A design that reduces variability by grouping similar experimental units into blocks.

Matched Pairs Design

A design comparing two treatments, where subjects are paired based on similarity.

The Placebo Effect

The phenomenon where subjects show a response to a dummy treatment due to their beliefs.

Single-blind

An experiment where subjects do not know which treatment they receive.

Double-blind

An experiment where neither subjects nor researchers know which treatment is administered.

Confounding Variable

An outside variable that relates to both explanatory and response variables, making it hard to determine causation.

Scope of Inference

The conclusions that can be drawn from an experiment based on its design.

Random Sampling

Selecting a subset of individuals to represent a population.

Random Assignment

Assigning subjects to treatment groups in a way that is random.

Bias

A systematic error favoring a specific outcome in an experiment.

Correlation

A statistical measure that expresses the extent to which two variables change together.

Causation

The action of causing something; a relationship where one event directly affects another.

Control Group

A group in an experiment that receives no treatment or a baseline treatment for comparison.

Lurking Variables

Variables that are not included in the study but affect the results.

Nuisance Variable

An extraneous factor that complicates the outcome of an experiment.

Statistical Analysis

Using quantitative methods to interpret and draw conclusions from data.

Statistical Significance

A statistical statement of how likely it is that an obtained result occurred by chance.

Random Number Generator (RNG)

A tool used in random assignment to ensure fair distribution among treatments.