This data set has NBA player statistics from the 2017 season. It includes player names, team, game played, position, turnover percentage, rebound percentage, assist percentage, and field goal percentage. The data was created from a Kaggle source that was originally scraped from basketball reference.
2026-03-28
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ── ## ✔ dplyr 1.2.0 ✔ readr 2.2.0 ## ✔ forcats 1.0.1 ✔ stringr 1.6.0 ## ✔ ggplot2 4.0.2 ✔ tibble 3.3.1 ## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2 ## ✔ purrr 1.2.1 ## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ── ## ✖ dplyr::filter() masks stats::filter() ## ✖ dplyr::lag() masks stats::lag() ## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ggplot2) library(plotly)
## ## Attaching package: 'plotly' ## ## The following object is masked from 'package:ggplot2': ## ## last_plot ## ## The following object is masked from 'package:stats': ## ## filter ## ## The following object is masked from 'package:graphics': ## ## layout
About dataset
Load data
nba <- read.delim("nba_positions_full.tsv")
names(nba)
## [1] "Player" "Team" "Games" "Position" "TurnoverPct" ## [6] "ReboundPct" "AssistPct" "FieldGoalPct"
head(nba)
## Player Team Games Position TurnoverPct ReboundPct AssistPct ## 1 Alex Abrines OKC 68 ShootingGuard 8.3 4.5 5.5 ## 2 Quincy Acy TOT 38 PowerForward 9.7 11.0 4.9 ## 3 Quincy Acy DAL 6 PowerForward 9.8 9.7 0.0 ## 4 Quincy Acy BRK 32 PowerForward 9.6 11.1 5.4 ## 5 Steven Adams OKC 80 Center 16.0 14.2 5.4 ## 6 Arron Afflalo SAC 61 ShootingGuard 8.4 4.6 7.4 ## FieldGoalPct ## 1 39.3 ## 2 41.2 ## 3 29.4 ## 4 42.5 ## 5 57.1 ## 6 44.0
data cleaning
nba_df <- nba %>%
mutate(
RoleGroup = case_when(
Position %in% c("PointGuard", "ShootingGuard") ~ "Guard",
Position %in% c("SmallForward", "PowerForward") ~ "Forward",
Position == "Center" ~ "Center",
TRUE ~ "Other"
)
)
summary(nba_df)
## Player Team Games Position ## Length:595 Length:595 Min. : 1.00 Length:595 ## Class :character Class :character 1st Qu.:24.00 Class :character ## Mode :character Mode :character Median :55.00 Mode :character ## Mean :48.43 ## 3rd Qu.:73.00 ## Max. :82.00 ## ## TurnoverPct ReboundPct AssistPct FieldGoalPct ## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.00 ## 1st Qu.: 9.70 1st Qu.: 6.20 1st Qu.: 6.20 1st Qu.: 40.00 ## Median :12.50 Median : 8.90 Median :10.10 Median : 44.20 ## Mean :12.89 Mean :10.03 Mean :12.77 Mean : 44.12 ## 3rd Qu.:15.60 3rd Qu.:13.00 3rd Qu.:17.50 3rd Qu.: 48.50 ## Max. :43.60 Max. :56.40 Max. :57.30 Max. :100.00 ## NA's :2 NA's :2 ## RoleGroup ## Length:595 ## Class :character ## Mode :character ## ## ## ##
ggplot 1: Assist vs Turnover
This plot compares the assist percentage and turnover percentage trends across different player positions
ggplot 2: Rebound by Position
The box plot shows how rebound percentages differs across positions. Centers and forwards rebound more.
Interactive Plotly Plot
This version of the Assist Percentage vs Turnover Percentage is interactive and lets you explore the relationship more closely
Plotly 2: 3D Interactive Plot
This 3D interactive plot helps compare 3 variable at once at various player positions
Statistical Analysis
[1] 0.2463049
Call:
lm(formula = TurnoverPct ~ AssistPct, data = nba_stats)
Residuals:
Min 1Q Median 3Q Max
-17.0308 -3.0953 -0.5802 2.1962 29.5726
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 10.94813 0.38539 28.408 < 2e-16 ***
AssistPct 0.15169 0.02455 6.178 1.21e-09 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.42 on 591 degrees of freedom
Multiple R-squared: 0.06067, Adjusted R-squared: 0.05908
F-statistic: 38.17 on 1 and 591 DF, p-value: 1.208e-09
Statistical Analysis Commentary
This analysis highlights the relationship between assist percentage and turnover percentage using correlation and linear regression. The correlation value is 0.246 shows a weak positive relationship between the 2 variables. This means that players with higher assist percentages tend to also have slightly higher turnover percentages, but the relationship is not very strong. The regression results also supports this pattern. The AssistPct coefficient is positive, which means turnover percentage tends to increase as assist percentage increases. The p-value is extremely small, showing that this relationship is statistically significant. However, the R-squared value is only about 0.061, which means assist percentage explains only a small portion of the variation in turnover percentage. Overall, the result suggest there is a real but weak positive relationship between assists and turnover.
Conclusion
This analysis showed that player statistics vary by position and role group. Guards generally contribute more to the assist, while bigger players tend to show stronger rebound numbers. The visualization and statiscal analysis sugesst that positions helps explain differneces in how players contribute on the court