How to Find Standard Deviation in R?

				
					# Comprehensive grouped SD benchmark
benchmark_grouped_methods <- function(data, group_col, value_cols) {
  
  # Method 1: dplyr (modern, readable)
  dplyr_method <- function() {
    data %>%
      group_by(!!sym(group_col)) %>%
      summarise(
        across(all_of(value_cols), ~ sd(.x, na.rm = TRUE), .names = "sd_{.col}"),
        .groups = "drop"
      )
  }
  
  # Method 2: base aggregate (classic R)
  aggregate_method <- function() {
    aggregate(data[value_cols], list(grp = data[[group_col]]), sd, na.rm = TRUE)
  }
  
  # Method 3: data.table (high performance)
  dt_method <- function() {
    dt <- data.table::as.data.table(data)
    dt[, lapply(.SD, function(x) sd(x, na.rm = TRUE)), 
       by = group_col, .SDcols = value_cols]
  }
  
  # Method 4: Manual split-apply-combine
  manual_method <- function() {
    groups <- split(data, data[[group_col]])
    results <- lapply(groups, function(g) {
      sapply(g[value_cols], sd, na.rm = TRUE)
    })
    do.call(rbind, results)
  }
  
  # Benchmark all methods
  mb <- microbenchmark(
    dplyr = dplyr_method(),
    aggregate = aggregate_method(),
    data.table = dt_method(),
    manual = manual_method(),
    times = 20
  )
  
  return(mb)
}

# Standard grouped benchmark
mb_grouped <- microbenchmark(
  dplyr_grouped = X %>%
    group_by(grp) %>%
    summarise(across(all_of(names(X)[1:p]), ~ sd(.x), .names = "sd_{.col}"),
              .groups = "drop"),
  base_aggregate = aggregate(X[1:p], list(grp = X$grp), sd),
  data.table = {
    dt <- data.table::as.data.table(X)
    dt[, lapply(.SD, sd), by = grp, .SDcols = 1:p]
  },
  times = 20
)
print(mb_grouped)

# Analyze the impact of group size distribution
analyze_group_impact <- function() {
  # Create datasets with different group size distributions
  
  # Balanced groups (equal sizes)
  balanced_data <- data.frame(
    group = rep(1:10, each = 1000),
    value = rnorm(10000)
  )
  
  # Skewed groups (some very large, some small)
  group_sizes <- c(5000, 2000, 1000, 500, 200, 100, 50, 25, 15, 10)
  skewed_data <- data.frame(
    group = rep(1:10, times = group_sizes),
    value = rnorm(sum(group_sizes))
  )
  
  cat("Balanced groups performance:\n")
  mb_balanced <- microbenchmark(
    dplyr = balanced_data %>% group_by(group) %>% summarise(sd = sd(value)),
    aggregate = aggregate(balanced_data$value, list(balanced_data$group), sd),
    times = 10
  )
  print(mb_balanced)
  
  cat("\nSkewed groups performance:\n")
  mb_skewed <- microbenchmark(
    dplyr = skewed_data %>% group_by(group) %>% summarise(sd = sd(value)),
    aggregate = aggregate(skewed_data$value, list(skewed_data$group), sd),
    times = 10
  )
  print(mb_skewed)
}