AP Statistics Experimental Design Vocabulary

Vocabulary flashcards covering core definitions, principles, and designs in experimental statistics based on the provided lecture transcript.

Experiment

A study in which treatments are explicitly imposed on experimental units to observe a response.

Explanatory Variable

The variable that explains the effect (independent variable), plotted on the $\text{x-axis}$; also known as a factor.

Response Variable

The variable measuring what has changed or the outcome being measured (dependent variable), plotted on the $\text{y-axis}$.

Confounded Variables

A state in which two or more variables are associated in such a way that it is impossible to determine which variable is contributing to the response.

Experimental Units

The smallest entities or objects that receive a treatment in an experiment.

Subjects

Experimental units that are human beings/people.

Placebo

A dummy treatment that contains no active ingredient.

Placebo Effect

The phenomenon in which experimental units or subjects show a positive response to a dummy treatment (placebo) even though it has no active ingredient.

Blinding

A condition where experimental units or subjects do not know which treatment group they have been assigned to.

Double Blinding

An experimental arrangement in which neither the subject receiving the treatment nor the person administering it knows which treatment group the subject belongs to.

Factor

Another name for an explanatory variable in an experiment.

Levels

The specific values or conditions of a factor that are applied in an experiment.

Number of Treatments

The total count of treatment combinations, determined by multiplying the number of levels of each factor ($\text{levels of Factor A} \times \text{levels of Factor B}$).

Control Group

A baseline group used for comparison that receives a placebo, no treatment, or an active control treatment.

Comparison

A principle of experimental design that requires comparing two or more treatments to determine their relative effects.

Random Assignment

A principle of experimental design that uses chance to assign experimental units to treatment groups.

Control (Principle of Design)

A principle of experimental design aimed at keeping other variables constant for all groups so that only one variable is changed at a time.

Replication

A principle of experimental design that involves using enough experimental units in each group so that treatment effects can be distinguished from chance variation.

Completely Randomized Design

An experimental design in which all experimental units or subjects are assigned to treatment groups entirely by chance.

Block Design (Blocking)

An experimental design in which experimental units are first separated into distinct groups (blocks) based on a trait of interest, followed by a completely randomized experiment within each block.

Matched Pairs Design

A specific type of block design where subjects are paired based on similarities, or where each subject receives both treatments to serve as their own control.

Statistically Significant

An observed result so unlikely to have occurred by chance alone that it indicates the imposed treatment caused the outcome.

Scope of Inference

The degree to which experimental results can be generalized to a broader population, or used to establish a cause-and-effect relationship.

Basic Data Ethics

Principles guiding research involving human subjects, requiring institutional review, informed consent, and confidentiality to protect participants.