PTS AST TRB MP
Min. : 0.000 Min. : 0.000 Min. : 0.000 Min. : 0.50
1st Qu.: 3.700 1st Qu.: 0.700 1st Qu.: 1.700 1st Qu.:11.40
Median : 6.800 Median : 1.400 Median : 3.000 Median :18.50
Mean : 8.472 Mean : 2.002 Mean : 3.403 Mean :18.89
3rd Qu.:11.400 3rd Qu.: 2.700 3rd Qu.: 4.500 3rd Qu.:26.80
Max. :34.700 Max. :11.600 Max. :13.900 Max. :41.00
NA's :3 NA's :3 NA's :3 NA's :3
FG% 3P% FT% TOV
Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.000
1st Qu.:0.4080 1st Qu.:0.2860 1st Qu.:0.6853 1st Qu.:0.500
Median :0.4500 Median :0.3450 Median :0.7690 Median :0.800
Mean :0.4544 Mean :0.3207 Mean :0.7498 Mean :1.026
3rd Qu.:0.5000 3rd Qu.:0.3860 3rd Qu.:0.8390 3rd Qu.:1.400
Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :4.700
NA's :15 NA's :115 NA's :138 NA's :3
STL BLK
Min. :0.0000 Min. :0.0000
1st Qu.:0.3000 1st Qu.:0.1000
Median :0.6000 Median :0.3000
Mean :0.6138 Mean :0.3808
3rd Qu.:0.9000 3rd Qu.:0.5000
Max. :3.0000 Max. :3.8000
NA's :3 NA's :3 Final Project
Impacts on Production and Individual Impact on a Game in The NBA
Basketball is a sport where a player who is 6’2 can have just as much impact on a game as a player who is 7’0. Height is important, but what else contributes to success on an individuals impact on a game, specifically on the offensive side of the ball, but overall as well? This is what I will be answering in this analysis. Figuring out what contributes most to offensive production and overall impact (+/-) can give teams an advantage when they are signing/drafting players. Answering these questions can help teams when they are forming their strategies in terms of team building, in-game strategy, and the true impact a player can have upon their team. A player can be known as a high point scorer, but if you look deeper, they take a lot of shots to score such high points, and also have an overall negative impact when on the floor. I will not answer all of these questions, but this analysis will show a few of the impacts that answering these types of questions can have.
Questions to be Answered
The main questions that I will focus on in this analysis are as follows: Does a players position impact their overall production? (PTS + REB + AST)? Does age make any difference in offensive production (PTS & AST)? Does number of shots attempted relate to a positive or negative +/-? Does high PPG translate to wins for that players team? Is there a trade-off between FG% and shot volume (FGA)?
Introduction to Scraped Data Set
I am going to be performing an analysis on seasonal NBA player data, provided by scraping the Basketball Reference website. The first data set records information about each player in the NBA from 2023-2025, along with that players individual average statistics from each season they have played in that time period. Each row is a player (there are instances of a player getting traded and their statistics from each team they were on that season being totaled * Team label is 2TM) and a season and each column is a statistic or descriptive information specific to each player (ex: awards won that year, age, team played for in that season). The statistics and information are explained below in the data dictionary. You can learn more about this data at this link: NBA 2023-2025 Player Statistics.
Data Dictionary
| Variable | Description |
|---|---|
Rank |
Player’s ranking in MVP (Most Valuable Player) voting for that season. |
Player |
Full name of the NBA player. |
Age |
Player’s age during the season. |
Team |
Abbreviation of the team the player played for. |
Pos |
Player’s primary position (e.g., PG, SG, SF, PF, C). |
G |
Games played during the season. |
GS |
Games started during the season. |
MP |
Total minutes played in the season. |
FG |
Field goals made. |
FGA |
Field goals attempted. |
FG% |
Field goal percentage (FG / FGA). |
3P |
3-point field goals made. |
3PA |
3-point field goals attempted. |
3P% |
3-point shooting percentage (3P / 3PA). |
2P |
2-point field goals made. |
2PA |
2-point field goals attempted. |
2P% |
2-point field goal percentage (2P / 2PA). |
eFG% |
Effective field goal percentage ((FG + 0.5 * 3P) / FGA). |
FT |
Free throws made. |
FTA |
Free throws attempted. |
FT% |
Free throw percentage (FT / FTA). |
ORB |
Offensive rebounds. |
DRB |
Defensive rebounds. |
TRB |
Total rebounds (ORB + DRB). |
AST |
Assists. |
STL |
Steals. |
BLK |
Blocks. |
TOV |
Turnovers. |
PF |
Personal fouls. |
PTS |
Total points scored. |
Awards |
Honors received (e.g., All-NBA, DPOY). |
Season |
Season represented (e.g., “2022”) |
Summary Statistics
Introduction to Nejc Zavodnik’s Kaggle Data Set
I also utilized a data set found on Kaggle that provided similar statistics to the above data set, along with some additional statistics I believe are useful to answer the questions that I am posing/answering. The data is statistics/information, with each instance being a player from the 2024-2025 NBA Regular Season, with statistics being a season average. The statistics and information are explained below in the data dictionary. You can find the link to the Kaggle data set at this link: Kaggle NBA 2024-2025 Player Data
Data Dictionary
| Variable | Description |
|---|---|
PPGRNK |
Player’s rank in points per game (PPG) among all players. |
Player |
Full name of the NBA player. |
Team |
Abbreviation of the NBA team the player was on. |
Age |
Player’s age during the season. |
GP |
Games played. |
W |
Number of games won by the player’s team. |
L |
Number of games lost by the player’s team. |
Min |
Total minutes played. |
PTS |
Total points scored. |
FGM |
Field goals made. |
FGA |
Field goals attempted. |
FG% |
Field goal percentage (FGM / FGA). |
3PM |
3-point field goals made. |
3PA |
3-point field goals attempted. |
3P% |
3-point field goal percentage (3PM / 3PA). |
FTM |
Free throws made. |
FTA |
Free throws attempted. |
FT% |
Free throw percentage (FTM / FTA). |
OREB |
Offensive rebounds. |
DREB |
Defensive rebounds. |
REB |
Total rebounds (OREB + DREB). |
AST |
Assists. |
TOV |
Turnovers. |
STL |
Steals. |
BLK |
Blocks. |
PF |
Personal fouls. |
FP |
Fantasy points (a calculated score based on performance metrics). |
DD2 |
Number of double-doubles (10+ in two statistical categories). |
TD3 |
Number of triple-doubles (10+ in three statistical categories). |
+/- |
Plus-minus: point differential when the player is on the court. |
Summary Statistics
PTS AST REB FG%
Min. : 0.000 Min. : 0.000 Min. : 0.000 Min. : 0.00
1st Qu.: 4.000 1st Qu.: 0.800 1st Qu.: 1.800 1st Qu.: 40.60
Median : 7.200 Median : 1.500 Median : 3.200 Median : 44.80
Mean : 8.887 Mean : 2.085 Mean : 3.596 Mean : 44.61
3rd Qu.:12.100 3rd Qu.: 2.700 3rd Qu.: 4.800 3rd Qu.: 49.60
Max. :32.700 Max. :11.600 Max. :13.900 Max. :100.00
3P% FT% TOV PF
Min. : 0.0 Min. : 0.00 Min. :0.000 Min. :0.000
1st Qu.: 26.7 1st Qu.: 67.90 1st Qu.:0.500 1st Qu.:1.000
Median : 33.8 Median : 76.30 Median :0.900 Median :1.600
Mean : 29.9 Mean : 72.02 Mean :1.089 Mean :1.544
3rd Qu.: 37.7 3rd Qu.: 82.90 3rd Qu.:1.500 3rd Qu.:2.100
Max. :100.0 Max. :100.00 Max. :4.700 Max. :3.500 Impact of Age on Offensive Production (2023- 2025 PTS & AST)
This scatter plot, which examines the relationship between age and offensive production through average points (PTS) and assists (AST) for players aged 19 to 42, clearly shows that age significantly impacts offensive performance. Players in their early to mid-20s demonstrate the highest production. Most players average 2–4 assists and 5–15 points, but a noticeable decline begins after age 30, where players typically score below 10 points and 2 assists, and the oldest players (39–42) drop to around 5 points and 0–1 assists. This indicates that younger players, likely in their physical prime, consistently produce more offensively, while aging leads to a steady decrease in both points and assists, confirming that age does indeed make a significant difference in offensive production.
Relationship between FGA on +/- (2024/2025)
We see that most players cluster around moderate FGA and near-zero +/- values. However, there’s a mild trend suggesting that players with higher shot volumes tend to have higher plus/minus ratings, indicating that high-usage players often contribute positively to team performance — but it’s not a strong universal rule, with the data revealing that FGA alone doesn’t predict +/- consistently, as there are multiple points in both positive and negative ranges at various shot attempt levels.
Does high PPG translate to wins for that player’s team?
This boxplot shows a clear trend that players who score more points per game are generally on teams with more wins. As PPG increases, the median number of wins rises across each scoring tier, with the highest-scoring players (25+ PPG) typically associated with the most successful teams. While many factors influence team performance, the data suggests a positive relationship between individual scoring and team success. Disregard the NA result.
Position Impact on Overall Production? (PTS + REB + AST)
This graph indicates that point-guards have the most overall impact on their teams (in terms of avg. PTS + REB + AST), with centers second, followed by power-forwards, small forwards and then shooting-guards. Point-guards typically have the ball in their hands at the highest rate, with centers having more opportunities to get rebounds (due to height advantage and usual approximation to the backboard). These are two of the most important positions in the sport, and the positions that to succeed, it is important to have someone with high production in that spot.
Trade-off between FG% and shot volume (FGA) (2024-2025)
The trend line in the above point graph slopes downward, indicating a negative correlation between FGA and FG%. As the number of field goal attempts (FGA) increases, the field goal percentage (FG%) tends to decrease. This suggests a trade-off: players who take more shots (higher FGA) generally have a lower shooting accuracy (lower FG%). The spread of data points around the trend line shows some variability, but the overall pattern supports the existence of a trade-off between shot volume and shooting percentage.
Conclusion
Overall, the visual analyses reveal key patterns in player performance: younger players (especially in their 20s) drive higher offensive output, while aging reduces production; players who take more shots tend to help their teams more, but high shot volume doesn’t always guarantee a better plus/minus; higher individual scoring generally correlates with more team wins; point guards and centers contribute the most all-around value to their teams; and lastly, there’s a noticeable trade-off between shooting volume and efficiency, with higher field goal attempts linked to lower accuracy. These findings underscore how player role, age, and style of play influence both individual and team success.