Appendix E: Glossary of Terms

This comprehensive glossary provides definitions for all terminology used throughout this textbook, organized alphabetically within four major categories: Basketball Terminology, Analytics Terminology, Statistical Terminology, and Programming Terminology.

E.1 Basketball Terminology

A

Alley-oop: An offensive play where one player throws the ball near the basket while a teammate jumps, catches it mid-air, and scores before landing. This play requires precise timing and coordination between the passer and the finisher.

And-one: A situation where a player is fouled while making a successful field goal and is awarded one free throw attempt. The player has the opportunity to complete a three-point play (or four-point play if the original shot was a three-pointer).

Assist: A pass that directly leads to a made basket. The assist is credited to the player who makes the final pass before the score, provided the scoring player moves immediately toward the basket.

B

Backcourt: (1) The half of the court containing a team's defensive basket. (2) Collectively, a team's point guard and shooting guard positions.

Ball handler: The player currently in possession of the basketball, responsible for advancing the ball and initiating offensive plays.

Bank shot: A field goal attempt where the ball is intentionally bounced off the backboard before entering the basket.

Baseline: The boundary line running along each end of the court, behind the baskets. Also called the end line.

Block: A defensive play where a player legally deflects a field goal attempt while the ball is on its upward trajectory.

Box out: A rebounding technique where a player positions their body between an opponent and the basket to gain advantageous position for securing the rebound.

C

Center: Traditionally the tallest player on the team, typically positioned near the basket on both offense and defense. Primary responsibilities include rebounding, interior defense, and scoring close to the rim.

Clear-out: An offensive strategy where players vacate one side of the court to create isolation opportunities for a teammate.

Corner three: A three-point shot taken from either corner of the court, the shortest three-point distance on an NBA court (22 feet).

Crossover: A dribbling move where the ball handler quickly switches the ball from one hand to the other to change direction and create separation from a defender.

D

Double-double: A statistical achievement where a player records double digits (10 or more) in two of the five main statistical categories (points, rebounds, assists, steals, blocks) in a single game.

Double team: A defensive strategy where two players guard a single offensive player simultaneously.

Drive: An offensive move where a player dribbles aggressively toward the basket, attempting to score or draw a foul.

Drop coverage: A pick-and-roll defensive strategy where the screener's defender sags back toward the paint to protect the rim while the ball handler's defender navigates around the screen.

E

Elbow: The area of the court where the free throw line meets the lane line, forming an "elbow" shape.

Euro step: A two-step move where the offensive player takes a lateral step in one direction, then quickly steps in the opposite direction while finishing at the rim.

F

Fastbreak: A quick offensive transition where a team attempts to score before the defense can set up, typically featuring numerical advantages.

Five-out offense: An offensive system where all five players position themselves outside the three-point line, maximizing floor spacing.

Floater: A high-arcing shot taken in the lane, typically released before the shooter reaches the rim to avoid shot blockers.

Foul trouble: A situation where a player has accumulated multiple fouls, limiting their ability to play aggressively without risk of disqualification.

Four-point play: When a player is fouled while making a three-point shot and subsequently makes the resulting free throw.

Frontcourt: (1) The half of the court containing a team's offensive basket. (2) Collectively, a team's small forward, power forward, and center positions.

G

Give-and-go: A fundamental offensive play where a player passes to a teammate and immediately cuts toward the basket to receive a return pass.

Green light: Authorization for a player to shoot freely whenever they have a reasonable opportunity.

H

Half-court offense: Offensive play executed after the defense has set up, as opposed to transition offense.

Help defense: A defensive principle where off-ball defenders position themselves to assist teammates who are beaten by their assigned offensive player.

High post: The area near the free throw line, typically occupied by a big man in certain offensive sets.

I

Isolation (ISO): An offensive play designed to create a one-on-one matchup between a skilled offensive player and their defender, with other offensive players clearing space.

J

Jab step: An offensive fake where a player quickly extends one foot toward the defender to gauge their reaction before making a move.

K

Key: The painted area encompassing the free throw lane and circle. Also called the paint or the lane.

L

Low post: The area near the basket along the lane line, where post players typically establish position for scoring opportunities.

M

Man-to-man defense: A defensive scheme where each defender is assigned to guard a specific offensive player.

Motion offense: A structured yet flexible offensive system emphasizing ball movement, player movement, and reading defensive reactions.

O

Off-ball: Actions or positioning of players who do not have possession of the basketball.

Outlet pass: A pass made after securing a defensive rebound to initiate a fastbreak.

Over-and-back violation: An illegal return of the ball to the backcourt after the offensive team has established frontcourt possession.

P

Paint: The rectangular area between the baseline and free throw line, typically painted a different color. Also called the key or the lane.

Pick: A screen set by an offensive player to free a teammate from their defender.

Pick-and-pop: A play where the screener sets a pick and then moves to an open spot (typically for a jump shot) rather than rolling to the basket.

Pick-and-roll: A fundamental offensive play where a player sets a screen for the ball handler and then rolls toward the basket looking for a pass.

Point forward: A forward who handles primary ball-handling and playmaking duties typically assigned to a point guard.

Point guard: The primary ball handler and playmaker, typically the smallest player on the court. Responsible for running the offense and distributing the ball.

Post-up: An offensive technique where a player establishes position with their back to the basket, typically in the low post area.

Power forward: A frontcourt position combining elements of center and small forward play. Responsibilities include rebounding, interior scoring, and increasingly, perimeter shooting.

R

Rebound: Securing possession of the ball after a missed field goal or free throw attempt.

Rim protector: A player, typically a center, whose primary defensive value comes from protecting the basket and deterring or blocking shots at the rim.

S

Screen: A legal blocking move by an offensive player to create space for a teammate.

Shooting guard: A backcourt position primarily responsible for scoring, particularly from mid-range and three-point range.

Shot clock: A timer (24 seconds in the NBA) that limits the amount of time an offensive team has to attempt a field goal.

Sixth man: A team's primary substitute who plays significant minutes but does not start games.

Small forward: A versatile position combining elements of guard and forward play. Typically responsible for scoring, defense, and rebounding.

Spacing: The strategic positioning of offensive players to maximize court coverage and create driving lanes.

Stretch four/five: A power forward or center who can shoot three-pointers effectively, forcing their defender away from the basket and creating interior space.

Switch: A defensive technique where defenders exchange their assigned offensive players, typically after a screen.

T

Three-and-D: A player archetype specializing in three-point shooting and perimeter defense.

Transition: The phase of play between a change of possession and the establishment of half-court offense or defense.

Triple-double: A statistical achievement where a player records double digits in three of five main statistical categories in a single game.

Turnover: A loss of possession to the opposing team without a field goal attempt.

Z

Zone defense: A defensive scheme where players are assigned to guard specific areas of the court rather than individual opponents.

E.2 Analytics Terminology

A

Adjusted Efficiency: A team or player efficiency metric adjusted for opponent strength and other contextual factors.

APM (Adjusted Plus-Minus): A plus-minus metric that uses regression to control for teammate and opponent strength.

AST% (Assist Percentage): The percentage of teammate field goals a player assisted while on the floor.

AST:TO (Assist-to-Turnover Ratio): The ratio of assists to turnovers, measuring a player's ball security relative to their playmaking.

B

BLK% (Block Percentage): An estimate of the percentage of opponent two-point field goal attempts blocked by a player while on the floor.

Box Plus-Minus (BPM): A box score-based estimate of a player's contribution per 100 possessions relative to league average.

BREF: Basketball Reference, a primary source for historical basketball statistics.

C

Catch-and-shoot: A shot taken immediately after receiving a pass, without dribbling. Often tracked separately in analytics.

Contested shot: A field goal attempt where a defender is within a specified distance of the shooter.

CREBL (Calculated Regularized Expected Box-score Loss): An advanced metric combining box score and on-off data.

D

DARKO: A projection system using machine learning to forecast player performance.

DBPM (Defensive Box Plus-Minus): The defensive component of Box Plus-Minus.

Defensive Rating (DRtg): Points allowed per 100 possessions, used for both teams and individuals.

DFG% (Opponent Field Goal Percentage): The field goal percentage of shots defended by a player.

DIFF% (Differential Percentage): The difference between a shooter's expected and actual field goal percentage when guarded by a specific defender.

DRB% (Defensive Rebound Percentage): The percentage of available defensive rebounds a player grabbed while on the floor.

DRTG (Defensive Real Plus-Minus): A regularized adjusted plus-minus metric focusing on defensive impact.

E

eFG% (Effective Field Goal Percentage): A shooting efficiency metric that adjusts for the additional value of three-point shots. Formula: (FG + 0.5 * 3P) / FGA.

EPM (Estimated Plus-Minus): A comprehensive plus-minus metric developed by Dunks & Threes.

Expected Value: The average outcome of a play or shot type over many repetitions.

F

Four Factors: Dean Oliver's framework identifying the four key factors of basketball success: shooting efficiency, turnover rate, rebounding rate, and free throw rate.

FT Rate (Free Throw Rate): The ratio of free throw attempts to field goal attempts, measuring a player's ability to get to the foul line.

G

Game Score: A single-number summary of a player's game performance, developed by John Hollinger.

L

LEBRON (Luck-adjusted player Estimate using Box priors and Regularized On-off): A comprehensive player metric combining box score and plus-minus data.

Leverage: A statistical concept describing the importance of a possession based on game situation.

Lineup data: Statistics for specific combinations of five players.

M

Marginal value: The additional value provided by a player compared to a replacement-level alternative.

N

Net Rating: The difference between offensive and defensive rating, representing points scored minus points allowed per 100 possessions.

O

OBPM (Offensive Box Plus-Minus): The offensive component of Box Plus-Minus.

Offensive Rating (ORtg): Points scored per 100 possessions, used for both teams and individuals.

On-off data: Statistics comparing team performance with a player on the court versus off the court.

ORB% (Offensive Rebound Percentage): The percentage of available offensive rebounds a player grabbed while on the floor.

P

Pace: The number of possessions a team uses per game or per 48 minutes.

PIPM (Player Impact Plus-Minus): A plus-minus metric combining box score priors with regularized adjusted plus-minus.

Plus-Minus (+/-): The point differential when a player is on the court.

Possessions: A single offensive opportunity, ending with a made field goal, defensive rebound, turnover, or certain free throws.

PPP (Points Per Possession): The average points scored or allowed per possession.

PER (Player Efficiency Rating): A per-minute rating that summarizes a player's statistical accomplishments, developed by John Hollinger.

R

RAPTOR (Robust Algorithm using Player Tracking and On-off Ratings): FiveThirtyEight's comprehensive player metric.

Raw plus-minus: The unadjusted point differential when a player is on the court.

Regularization: A statistical technique that constrains estimates toward the mean to reduce variance.

Replacement level: The expected performance of a freely available player, used as a baseline for value calculations.

RPM (Real Plus-Minus): ESPN's regularized adjusted plus-minus metric.

S

Shot quality: A measure of how good a shot attempt is based on location, defender proximity, and other factors.

Spacing: A quantitative measure of how spread out offensive players are on the court.

STL% (Steal Percentage): An estimate of the percentage of opponent possessions ending with a steal by a player.

T

TOV% (Turnover Percentage): An estimate of turnovers per 100 plays used.

Tracking data: Player and ball location data captured by optical tracking systems.

True Shooting Percentage (TS%): A shooting efficiency metric accounting for two-point field goals, three-point field goals, and free throws. Formula: PTS / (2 * (FGA + 0.44 * FTA)).

U

Usage Rate (USG%): An estimate of the percentage of team plays used by a player while on the floor.

V

VORP (Value Over Replacement Player): A box score estimate of the points per 100 team possessions a player contributed above replacement level.

W

WAR (Wins Above Replacement): An estimate of the number of wins a player adds to their team compared to a replacement-level player.

Win Shares: An estimate of the number of wins contributed by a player, developed by Dean Oliver.

WS/48 (Win Shares per 48 Minutes): Win Shares normalized to per-48-minute production.

E.3 Statistical Terminology

A

Alpha (a): The significance level in hypothesis testing, representing the probability of rejecting a true null hypothesis.

ANOVA (Analysis of Variance): A statistical method for comparing means across multiple groups.

B

Bayesian inference: A statistical framework that updates probability estimates as new evidence becomes available.

Beta coefficient: The slope parameter in regression analysis, representing the change in the dependent variable for a one-unit change in the predictor.

Bias: The systematic deviation of an estimate from the true value.

Binomial distribution: A probability distribution describing the number of successes in a fixed number of independent trials.

Bootstrap: A resampling technique for estimating the sampling distribution of a statistic.

C

Causal inference: Statistical methods for determining cause-and-effect relationships from data.

Central limit theorem: The principle that sample means approach a normal distribution as sample size increases.

Coefficient of determination (R-squared): The proportion of variance in the dependent variable explained by the independent variables.

Confidence interval: A range of values that is likely to contain the true population parameter with a specified probability.

Confounding variable: A variable that influences both the independent and dependent variables, potentially leading to spurious correlations.

Correlation coefficient: A measure of the linear relationship between two variables, ranging from -1 to 1.

Covariance: A measure of how two variables change together.

Cross-validation: A technique for assessing model performance by testing on held-out data.

D

Degrees of freedom: The number of independent values that can vary in a statistical calculation.

Dependent variable: The outcome variable being predicted or explained in a statistical model.

E

Effect size: A measure of the magnitude of a phenomenon, independent of sample size.

Expected value: The probability-weighted average of all possible outcomes.

F

F-statistic: A test statistic used in ANOVA and regression to compare model fits.

H

Heteroscedasticity: Non-constant variance in the residuals of a regression model.

Hypothesis testing: A statistical procedure for making decisions about population parameters based on sample data.

I

Independent variable: A predictor variable used to explain or predict the dependent variable.

Interaction effect: When the effect of one variable depends on the level of another variable.

L

Least squares: A method for estimating regression coefficients by minimizing the sum of squared residuals.

Likelihood: The probability of observing the data given specific parameter values.

Linear regression: A statistical method for modeling the relationship between a dependent variable and one or more independent variables.

Logistic regression: A regression method for binary outcomes, modeling the log-odds of success.

M

Maximum likelihood estimation (MLE): A method for estimating parameters by maximizing the likelihood function.

Mean: The arithmetic average of a set of values.

Median: The middle value in an ordered dataset.

Mixed-effects model: A regression model containing both fixed and random effects.

Mode: The most frequently occurring value in a dataset.

Multicollinearity: High correlation among predictor variables in a regression model.

N

Normal distribution: A symmetric, bell-shaped probability distribution characterized by its mean and standard deviation.

Null hypothesis: The default assumption of no effect or no difference, tested against an alternative hypothesis.

O

Ordinary least squares (OLS): The standard method for estimating linear regression coefficients.

Outlier: An observation that lies far from other values in a dataset.

Overfitting: When a model captures noise rather than signal, performing well on training data but poorly on new data.

P

P-value: The probability of observing results at least as extreme as those obtained, assuming the null hypothesis is true.

Poisson distribution: A probability distribution describing the number of events occurring in a fixed interval.

Population: The complete set of individuals or observations of interest.

Posterior distribution: In Bayesian statistics, the updated probability distribution after observing data.

Prior distribution: In Bayesian statistics, the probability distribution before observing data.

R

Random variable: A variable whose value is determined by chance.

Regression to the mean: The tendency for extreme observations to be followed by more typical ones.

Residual: The difference between an observed value and a predicted value.

Ridge regression: A regression method that adds a penalty term to reduce coefficient magnitudes.

S

Sample: A subset of the population used for statistical analysis.

Sampling distribution: The probability distribution of a statistic over repeated samples.

Significance level: The threshold for determining statistical significance, typically 0.05.

Standard deviation: A measure of dispersion, the square root of variance.

Standard error: The standard deviation of a sampling distribution.

Statistical significance: When an observed effect is unlikely to have occurred by chance alone.

T

T-statistic: A test statistic following a t-distribution, used for hypothesis testing with small samples.

Type I error: Rejecting a true null hypothesis (false positive).

Type II error: Failing to reject a false null hypothesis (false negative).

V

Variance: A measure of dispersion, the average squared deviation from the mean.

Z

Z-score: The number of standard deviations an observation is from the mean.

E.4 Programming Terminology

A

API (Application Programming Interface): A set of protocols for building and interacting with software applications. Basketball data is often accessed through APIs.

Array: A data structure containing a collection of elements, typically of the same type.

B

Boolean: A data type with two possible values: True or False.

C

Class: In object-oriented programming, a blueprint for creating objects with shared attributes and methods.

Concatenation: Joining two or more strings or data structures end-to-end.

CSV (Comma-Separated Values): A plain text file format for storing tabular data.

D

DataFrame: A two-dimensional data structure in pandas, similar to a spreadsheet or SQL table.

Data type: The classification of data that determines possible values and operations (e.g., integer, string, float).

Dictionary: A data structure storing key-value pairs, allowing lookup by key.

Docstring: A string literal documenting a function, class, or module in Python.

E

Exception: An error that occurs during program execution.

Expression: A combination of values, variables, and operators that evaluates to a single value.

F

Float: A data type representing decimal numbers.

For loop: A control structure that iterates over a sequence of elements.

Function: A reusable block of code that performs a specific task.

G

Git: A version control system for tracking changes in source code.

GitHub: A web-based platform for version control and collaboration using Git.

I

IDE (Integrated Development Environment): Software providing comprehensive facilities for software development (e.g., VS Code, PyCharm).

Import: A statement that makes code from external modules available in the current program.

Index: A numerical position identifying an element in a sequence or data structure.

Integer: A data type representing whole numbers.

Iteration: The repetition of a process, typically using loops.

J

JSON (JavaScript Object Notation): A lightweight data format for storing and exchanging data.

Jupyter Notebook: An interactive computing environment for creating documents containing code, visualizations, and text.

K

Kernel: The computational engine that executes code in Jupyter notebooks.

L

Lambda function: An anonymous, single-expression function in Python.

Library: A collection of pre-written code providing specific functionality (e.g., pandas, NumPy).

List: An ordered, mutable collection of elements in Python.

List comprehension: A concise way to create lists in Python using a single line of code.

M

Matplotlib: A Python library for creating static, animated, and interactive visualizations.

Method: A function associated with an object or class.

Module: A file containing Python definitions and statements.

N

NaN (Not a Number): A value representing missing or undefined data.

NumPy: A Python library for numerical computing with support for arrays and matrices.

O

Object: An instance of a class containing data (attributes) and functionality (methods).

P

Package: A collection of Python modules organized in directories.

pandas: A Python library for data manipulation and analysis.

Parameter: A variable in a function definition that accepts input values.

pip: Python's package installer for installing libraries from PyPI.

Plot: A visual representation of data.

PyPI (Python Package Index): A repository of Python packages.

Python: A high-level programming language widely used for data analysis.

R

R: A programming language designed for statistical computing and graphics.

Regex (Regular Expression): A sequence of characters defining a search pattern.

Repository: A storage location for code, typically managed with version control.

Return value: The output produced by a function.

S

Scikit-learn: A Python library for machine learning.

Seaborn: A Python data visualization library built on Matplotlib.

Series: A one-dimensional labeled array in pandas.

SQL (Structured Query Language): A language for managing and querying relational databases.

String: A data type representing text.

Syntax: The rules governing the structure of code in a programming language.

T

Tuple: An ordered, immutable collection of elements in Python.

V

Variable: A named storage location for data in a program.

Vectorization: Performing operations on entire arrays rather than individual elements.

Virtual environment: An isolated Python environment for managing project dependencies.

W

Web scraping: Automatically extracting data from websites.

While loop: A control structure that repeats code while a condition is true.

Quick Reference Index

For rapid lookup, key terms are indexed by their first appearance in the textbook:

This glossary is intended as a reference companion to the main text. Terms are defined in the context of basketball analytics; definitions may differ in other domains.