AP STATS: Unit 3 Review

Population

All individuals from which a sample is drawn.

SRS (Simple Random Sample)

A method of sampling where every individual has an equal chance of being selected.

Convenience Sample

A sampling method that is NOT random, often involving individuals who are easiest to reach.

Voluntary Response Sample

A sample where individuals choose to participate.

Stratified Random Sample

A sampling method that includes some members from all groups.

Cluster Random Sample

A sampling method that includes all members from only some groups.

Systematic Random Sample

A method where you choose a random starting point and then sample at regular intervals.

Undercoverage

A sampling problem where some members of a population cannot be included or are left out.

Nonresponse Bias

A bias that occurs when individuals from a sample choose not to respond.

Response Bias

A pattern of inaccurate results due to various factors like lying or poorly worded questions.

Residual

The difference between the actual value and the predicted value (y - ŷ).

Slope

It indicates how much the response variable is predicted to increase or decrease for each additional unit of the explanatory variable.

Observational Study

A study where no treatment is applied, observations are made instead.

Experimental Units

The subjects or items being tested in an experiment.

Standard deviation of residuals (s)

A measure of how much the actual values typically deviate from the predictions made by the least squares regression line.

Coefficient of determination (r²)

A statistic indicating the proportion of variability in the response variable that is accounted for by the least squares regression line.

Outlier

An observation that lies an abnormal distance from other values in a dataset.

High leverage

Observations with very large or very small x-values that can significantly affect the slope of the regression line.

Influential Point

An observation that, when removed, would significantly change the slope, y-intercept, or correlation of the regression line.

A GOOD LSRL

Has low standard deviation of residuals (s) and high r² value close to 1.