title: “Basketball” author: “Laura Werner” date: “2025-10-28” output: html_document
library(readxl)## Warning: package 'readxl' was built under R version 4.4.3library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggplot2)## Warning: package 'ggplot2' was built under R version 4.4.3library(purrr)
library(ggcorrplot)## Warning: package 'ggcorrplot' was built under R version 4.4.3library(ppcor)## Warning: package 'ppcor' was built under R version 4.4.3## Loading required package: MASS##
## Attaching package: 'MASS'## The following object is masked from 'package:dplyr':
##
## selectlibrary(dplyr)load_team_data <- function(sheet_name, file_path = "NBA Team Total Data 2024-2025.xlsx") {
df <- read_excel(file_path, sheet = sheet_name)
df <- df %>%
mutate(
Team = sheet_name,
Won_award = ifelse(is.na(Awards), 0, 1),
PRA = PTS + TRB + AST,
STOCKS = STL + BLK
)
return(df)
}
file_path <- "NBA Team Total Data 2024-2025.xlsx"
team_sheets <- excel_sheets(file_path)
all_teams_list <- lapply(team_sheets, load_team_data, file_path = file_path)
nba_data <- bind_rows(all_teams_list)
head(nba_data)## # A tibble: 6 × 35
## Rk Player Age G GS MP FG FGA `FG%` `3P` `3PA` `3P%` `2P`
## <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 Jalen… 24 79 22 2031 246 620 0.397 122 362 0.337 124
## 2 2 Keon … 22 79 56 1925 303 779 0.389 126 401 0.314 177
## 3 3 Nic C… 25 70 62 1882 320 568 0.563 5 21 0.238 315
## 4 4 Camer… 28 57 57 1800 355 747 0.475 159 408 0.39 196
## 5 5 Ziair… 23 63 45 1541 214 520 0.412 103 302 0.341 111
## 6 6 Tyres… 25 60 11 1315 189 465 0.406 99 282 0.351 90
## # ℹ 22 more variables: `2PA` <dbl>, `2P%` <dbl>, `eFG%` <dbl>, FT <dbl>,
## # FTA <dbl>, `FT%` <dbl>, ORB <dbl>, DRB <dbl>, TRB <dbl>, AST <dbl>,
## # STL <dbl>, BLK <dbl>, TOV <dbl>, PF <dbl>, PTS <dbl>, `Trp-Dbl` <dbl>,
## # Awards <chr>, Team <chr>, Won_award <dbl>, PRA <dbl>, STOCKS <dbl>,
## # Pos <chr>conference_lookup <- read_excel("Team Conferences.xlsx")
nba_data <- nba_data %>%
left_join(conference_lookup, by = "Team") %>%
mutate(Conference_binary = ifelse(Conference == "East", 1, 0))
head(nba_data)## # A tibble: 6 × 37
## Rk Player Age G GS MP FG FGA `FG%` `3P` `3PA` `3P%` `2P`
## <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 Jalen… 24 79 22 2031 246 620 0.397 122 362 0.337 124
## 2 2 Keon … 22 79 56 1925 303 779 0.389 126 401 0.314 177
## 3 3 Nic C… 25 70 62 1882 320 568 0.563 5 21 0.238 315
## 4 4 Camer… 28 57 57 1800 355 747 0.475 159 408 0.39 196
## 5 5 Ziair… 23 63 45 1541 214 520 0.412 103 302 0.341 111
## 6 6 Tyres… 25 60 11 1315 189 465 0.406 99 282 0.351 90
## # ℹ 24 more variables: `2PA` <dbl>, `2P%` <dbl>, `eFG%` <dbl>, FT <dbl>,
## # FTA <dbl>, `FT%` <dbl>, ORB <dbl>, DRB <dbl>, TRB <dbl>, AST <dbl>,
## # STL <dbl>, BLK <dbl>, TOV <dbl>, PF <dbl>, PTS <dbl>, `Trp-Dbl` <dbl>,
## # Awards <chr>, Team <chr>, Won_award <dbl>, PRA <dbl>, STOCKS <dbl>,
## # Pos <chr>, Conference <chr>, Conference_binary <dbl>ggplot(nba_data, aes(x = PRA, y = STOCKS, color = factor(Conference_binary))) +
geom_point(size = 3, alpha = 0.7) +
labs(color = "Conference (1=East, 0=West)",
x = "PRA (Points + Rebounds + Assists)",
y = "STOCKS (Steals + Blocks)",
title = "Offensive vs Defensive Performance by Conference") +
theme_minimal()
The scatterplot shows a positive relationship between offensive (PRA)
and defensive (STOCKS) metrics. Teams with higher PRA have slightly
higher STOCKS. Western teams (blue) cluster higher in defensive metrics
than Eastern teams (red).
ggplot(nba_data, aes(x = PRA, fill = factor(Conference_binary))) +
geom_histogram(position = "dodge", bins = 15, alpha = 0.7) +
labs(fill = "Conference (1=East, 0=West)",
x = "PRA",
y = "Number of Players",
title = "Distribution of PRA by Conference") +
theme_minimal()
cor_pra <- cor.test(nba_data$Conference_binary, nba_data$PRA)
cor_stocks <- cor.test(nba_data$Conference_binary, nba_data$STOCKS)
cor_pra##
## Pearson's product-moment correlation
##
## data: nba_data$Conference_binary and nba_data$PRA
## t = -1.8195, df = 650, p-value = 0.0693
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.147164250 0.005629906
## sample estimates:
## cor
## -0.07118475cor_stocks##
## Pearson's product-moment correlation
##
## data: nba_data$Conference_binary and nba_data$STOCKS
## t = -2.094, df = 650, p-value = 0.03665
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.157650363 -0.005105577
## sample estimates:
## cor
## -0.08185737The correlation matrix indicates that PRA and STOCKS are positively correlated, showing teams that perform well offensively also perform well defensively. Age shows little to no relationship with PRA and STOCKS. The correlation shows that the conference (East vs West) has little effect on offensive metrics (PRA), but a small negative effect on defensive metrics (STOCKS). This shows that Western teams are lightly stronger defensively.
cor_matrix <- nba_data %>% dplyr::select(Age, PRA, STOCKS)
cor_matrix <- nba_data %>%
dplyr::select(Age, PRA, STOCKS) %>% # pick columns
cor(use = "pairwise.complete.obs") # calculate correlations
ggcorrplot(cor_matrix, lab = TRUE, title = "Correlation Matrix: Age, PRA, STOCKS")## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## ℹ The deprecated feature was likely used in the ggcorrplot package.
## Please report the issue at <https://github.com/kassambara/ggcorrplot/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
Age does not affect the link between offensive and defensive
performance, so the relationship appears mostly similar across team
ages.
partial_res <- pcor.test(nba_data$PRA, nba_data$STOCKS, nba_data$Age)
partial_res## estimate p.value statistic n gp Method
## 1 0.8395996 3.657553e-174 39.37587 652 1 pearsonDear Commissioner Silver,
After reviewing the 2024–2025 NBA team data, we found a moderate link between offensive performance (PRA) and defensive performance (STOCKS). In other words, teams that excel offensively generally also contribute defensively. There are small differences between the Eastern and Western Conferences, with Western teams showing slightly stronger defensive performance, but the gap is minor. Age does not appear to have a meaningful effect on this relationship.
One limitation of this analysis is that it only considers a single season. Looking at multiple seasons in future studies could provide a clearer picture of trends over time. Additionally, incorporating advanced metrics like Player Efficiency Rating could offer deeper insight into overall team performance.