Do NBA Draft Picks Matter? Exploring Player Minutes with ANOVA

ANOVA
Hypothesis Testing
Python
This module uses NBA draft data to test for differences in average minutes played across early, mid, and late first-round picks using ANOVA and visualizations.
Authors
Affiliation

Vivian Johnson

St. Lawrence University

Robin Lock

St. Lawrence University

Ivan Ramler

St. Lawrence University

Published

May 19, 2026

Module

Please note that these material have not yet completed the required pedagogical and industry peer-reviews to become a published module on the SCORE Network. However, instructors are still welcome to use these materials if they are so inclined.

Introduction

Each year, the National Basketball Association (NBA) holds a draft, where prospective basketball players are able to be chosen to join one of the 30 professional teams across the United States and Canada.

The draft is comprised of 60 players and takes place over two rounds of 30 selections. Teams pick players in an order based on performance from the previous season, with teams that performed poorly getting earlier picks in order to create a seemingly more level playing field. It is important to note that there were not always 30 players selected in each round; the number made its way up to 30 as more teams were added into the NBA.

This activity focuses on players selected in the first round of the NBA Draft between 1990 and 2021. Students compare three groups of first-round picks: picks 1–10, picks 11–20, and picks 21–30. The response variable is average career minutes played per game.

The NBA Draft is designed to help distribute new talent across the league. Teams that miss the playoffs or finish with weaker records generally have access to earlier picks, although the first several picks are determined through the NBA Draft Lottery. Teams can also trade draft picks, so the team making a selection may not be the team that originally earned that pick.

Draft position matters because earlier picks are often viewed as higher-value prospects. Teams invest substantial resources in scouting, selecting, signing, and developing these players. As a result, high draft picks may receive more opportunities to play, especially early in their careers.

In order to be eligible for the draft, a player must be at least 19 years old and out of high school for at least one year. Prior to 2006, this rule was not in effect, and players could be drafted during or right out of high school.

The main research question is:

Is there evidence that average career minutes per game differs among NBA players selected with picks 1–10, picks 11–20, and picks 21–30 in the first round of the draft?

Students use graphical summaries and one-way ANOVA to compare average career minutes per game across the three draft-pick groups. They also consider whether the ANOVA conditions are reasonable and how choices such as the response variable and draft-pick grouping affect the conclusions that can be drawn.

This activity focuses on first-round picks because they are more directly comparable than all drafted players. First-round picks are typically expected to have a stronger chance of making an NBA roster and receiving playing time. Later picks, especially second-round picks, may have less guaranteed opportunity and more varied career paths.

Even within the first round, however, draft position can matter. A player selected near the top of the first round is often treated very differently from a player selected near the end of the first round.

Minutes per game is useful because it measures how much playing time a player earned during their NBA career. Players who receive more minutes are generally players coaches trust to contribute.

However, minutes per game is not a perfect measure of player quality. Playing time can also be influenced by injuries, roster depth, team strategy, coaching decisions, and team expectations. High draft picks may receive more opportunities because teams invested more in them or want to give them time to develop.

This could serve as an in class activity and should take roughly 30-45 minutes to complete (depending on the use of software).

By the end of this activity, students should be able to:

  1. Use graphical summaries to compare the distribution of a quantitative variable across multiple groups.

  2. Assess whether the conditions for a one-way ANOVA are reasonable in context.

  3. Conduct and interpret ANOVA results in context while recognizing the limitations of the response variable and grouping choices.

As a reinforcement module, students should have prior knowledge of conducting one-way analysis of variance tests and the implications. Students should be able to explain the different components of an ANOVA table as well as familiarity with the formulas necessary to complete the table or with using software to obtain the needed output.

There are three version of the handout:

  • In one version, no explicit technology is necessary other than a calculator.

  • Other two use R and Python respecitively to visualize the data and produce the ANOVA output.

Data

The nba_draft data set includes players selected in the NBA Draft between 1990 and 2021. Each row represents one drafted player and includes information about the player’s draft position, team, and NBA career statistics. Some players’ careers were still ongoing when the data were collected.

Variable Descriptions
Variable Description
draft_pick Overall pick number at which the player was selected in the NBA Draft
team NBA team that drafted the player
player_name Name of the player selected
college College the player attended; may be NA for players drafted from high school, international leagues, or other paths
years_played Number of years the player spent in the NBA
games_played Number of games the player played in the NBA
total_mins_played Total minutes the player played in the NBA
total_pts Total points the player scored in the NBA
total_rebounds Total rebounds the player recorded in the NBA
total_assists Total assists the player recorded in the NBA
fg_percent Field goal percentage during the player’s NBA career
three_pt_percent Three-point field goal percentage during the player’s NBA career
ft_percent Free throw percentage during the player’s NBA career
draft_year Year the player was drafted
mins_per_game Average number of minutes played per game during the player’s NBA career
pts_per_game Average number of points scored per game during the player’s NBA career
rebounds_per_game Average number of rebounds per game during the player’s NBA career
assists_per_game Average number of assists per game during the player’s NBA career
round_picked Round in which the player was selected; this module focuses on first-round picks
pick_in_round Pick number within the round in which the player was selected
draft_pick_group First-round draft-pick group used in this activity: picks 1–10, picks 11–20, or picks 21–30

Download nba_draft.csv

Data Source

The data are sourced from Kaggle and include draft information and NBA career statistics for drafted players.

Materials

“By-hand” worksheet

R/Quarto worksheet

Python notebook worksheet

Upon conclusion of this module, students will discover that there is strong evidence of a difference in average minutes per game based on which group a player was selected in the first round of the NBA draft. This learning module offers a valuable opportunity to explore the components of a one-way ANOVA test and interpret the results in context. Students will also consider why minutes per game is a useful but imperfect measure of player success, and choices, such as grouping picks into 1–10, 11–20, and 21–30, can affect the interpretation of the analysis.

Acknowledgements

Thumbnail Image credits: