Calculate homecourt advantage for each NBA team

nba_hca_by_team.R

library(sportsTools)
library(dplyr)
library(ggplot2)

start.year <- 2001
end.year <- 2015

all.games <- data.frame()

for (year in start.year:end.year) {
  
  schedule <- GetSchedule(year, 'regular')
  
  # Create model matrix where home teams have a 1, away teams have a -1
  home.model <- model.matrix(~ home.name + 0, data = schedule)
  away.model <- model.matrix(~ away.name + 0, data = schedule)
  model <- data.frame(home.model - away.model)
  colnames(model) <- gsub('home.name(.*)', paste0('\\1.', year), colnames(model))
  
  # Add more columns to represent home court location with a 1
  model <- cbind(model, data.frame(home.model))
  colnames(model) <- gsub('home.name(.*)', paste0('\\1.Home'), colnames(model))
  
  # Add outcome column
  model$Outcome <- schedule$home.margin
  
  all.games <- bind_rows(all.games, model)
}

# Replace all NA with 0
all.games[is.na(all.games)] <- 0

# Remove NOP / OKC home column
bad.col <- which(colnames(all.games) == 'New.Orleans.Oklahoma.City.Hornets.Home')
all.games <- all.games[, -bad.col]

# Combine Charlotte Bobcats and Charlotte Hornets
old.col <- which(colnames(all.games) == 'Charlotte.Bobcats.Home')
new.col <- which(colnames(all.games) == 'Charlotte.Hornets.Home')
all.games[, new.col] <- all.games[, old.col] + all.games[, new.col]
all.games <- all.games[, -old.col]

# Combine New Orleans Hornets and New Orleans Pelicans
old.col <- which(colnames(all.games) == 'New.Orleans.Hornets.Home')
new.col <- which(colnames(all.games) == 'New.Orleans.Pelicans.Home')
all.games[, new.col] <- all.games[, old.col] + all.games[, new.col]
all.games <- all.games[, -old.col]

# Compute regression and save coefficients
fit <- lm(Outcome ~ ., data = all.games)
results <- as.data.frame(summary(fit)$coefficients)
intercept <- results[1, ]
results <- results[grep('Home', row.names(results)), ]

# Incorporate intercept
results$Estimate <- results$Estimate + intercept[1, 1]
#results$`Std. Error` <- sqrt(results$`Std. Error`^2 + intercept[1, 2]^2)

# Calculate quantity for each home
results$Sample <- sapply(row.names(results), function(x) sum(all.games[, x]))

# Calculate 90% confidence interval for each home
results$crit.T <- qt(.95, results$Sample - 1)
results <- results[, c(1, 2, 6)]
results$Upper <- results[, 1] + results[, 2] * results[, 3]
results$Lower <- results[, 1] - results[, 2] * results[, 3]

# Clean Up Results
results$Team <- row.names(results)
row.names(results) <- NULL
results <- results[, c('Team', 'Estimate')]
results$Team <- gsub('\\.', ' ', results$Team)
results$Team <- gsub(' Home', '', results$Team)
results <- results[order(results$Estimate, decreasing = TRUE), ]

write.csv(results, 'hca_results.csv', row.names = FALSE)

The loading error you encountered blanks the home‑court advantage calculations, stopping the win loss differential from displaying. Treat the file like a proper Suffolk Court Lawyers by confirming it’s a clean CSV or JSON and validating the schema before processing. When the data loads, the adjusted percentages instantly reveal which teams truly dominate their own courts. Including opponent strength and travel fatigue, as you suggest, sharpens the model and avoids a common analyst blind spot.