AP Statistics Quiz 2

Explanatory Variable

(independent variable) changing this causes changes in response variable

Response Variable

(dependent variable) Variable that is affected by the explanatory variable and often the one being measured

Confounded (variables)

Variables that are mixed together, making it difficult to determine their individual effects on the response variable.

Observational Studies

researcher observes and records outcomes to answer specific questions, but no treatment is imposed.

Experiment

-actively impose a treatment on experimental units and responses are measured to answer specific questions.

-best way to show cause and effect

Treatments

The specific conditions or interventions applied to experimental units in an experiment to observe their effects

Experimental units

individuals or items that treatments are being imposed upon

• humans are called subjects

Levels of explanatory variables (factors)

The specific values, categories, or groups tested or observed for that categorical independent variable

• ex: Factor: Education Level

  • Levels: High School, Bachelor’s, Master’s, Doctorate

Placebo

fake treatment designed to mimic a real treatment without any therapeutic effect

Control group

A group that does not receive the treatment in an experiment, used for comparison with the experimental group.

Placebo effect

participants experience effects from placebo despite there being no actual imposed treatment

Double-Blind

Both the experimental unit (participant) and the researcher are unaware of which treatment is being administered, minimizing bias.

Single-Blind

only the experimental unit (participant) is unaware of which treatment is being administered, helping to reduce participant bias.

Basic Principles of Experimental Design

RRCC

• R: Random Assignment

• R: Replication

• C: Control

• C: Compare

Comparison

Use a design that compares two or more treatments

Random assignment

Use chance (i.e. slips of paper) to assign experimental units treatments.

Control

Keep other variables the same for all groups to avoid confounding and variation in response.

• easier to decide if treatment is effective

Replication

Impose each treatment on enough experimental units so the effects can be distinguished from chance differences

Completely Randomized Design

experimental units are assigned to treatments completely at random

Randomized Block Design

An experimental design that divides subjects into blocks based on specific characteristics and then randomly assigns treatments within those blocks to control for variability.

Matched Pairs Design

A specific type of experimental design that involves pairing subjects based on similar characteristics and giving each pair different treatments. Helps reduce variability and makes more accurate comparisons of treatment effects.

Sampling Variability

Different random samples of the same size from the same population produce different estimates.

• Sampling variability is reduced by increased sample size

Statistically Significant

When observed results of a study are too unusual to be explained by chance alone and indicate a real effect or relationship in the population.

Inference about a population

requires that the individuals taking part in a study be randomly selected from the population to ensure that the results can be generalized to the larger population.

Inference about cause and effect

Random assignment of experimental units to treatments

Institutional Review Board (IRB)

A group that reviews research proposals to ensure the protection of participants' rights and welfare during a study.

Informed consent

researchers explain the nature of the study to participants, ensuring they understand the risks and benefits before agreeing to participate.

confidentiality

the assurance that personal information collected during a study will be kept private and secure, preventing unauthorized access.