R/summarySE.R

In jeffkimbrel/jakR: jakR Miscellaneous Scripts

#' Calculate Error Bars on a Dataframe
#'
#' Code borrowed from Winston Chang
#' http://www.cookbook-r.com/Graphs/Plotting_means_and_error_bars_(ggplot2)/
#'
#'
#'
#' @export

summarySE <- function(data = NULL, measurevar, groupvars = NULL, na.rm = FALSE, conf.interval = .95, .drop = TRUE) {

  #require("plyr")
  require("dplyr")

  # New version of length which can handle NA's: if na.rm==T, don't count them
  length2 <- function (x, na.rm = FALSE) {
    if (na.rm) sum(!is.na(x))
    else length(x)
  }

  # This does the summary. For each group's data frame, return a vector with
  # N, mean, and sd
  datac <- plyr::ddply(data, groupvars, .drop = .drop, .fun = function(xx, col) {
                   c(N    = length2(xx[[col]], na.rm = na.rm),
                     mean = mean   (xx[[col]], na.rm = na.rm),
                     sd   = sd     (xx[[col]], na.rm = na.rm)
                   ) },
              measurevar
            )

  # Rename the "mean" column
  #datac <- rename(datac, c("mean" = measurevar))

  datac$se <- datac$sd / sqrt(datac$N)  # Calculate standard error of the mean

  # Confidence interval multiplier for standard error
  # Calculate t-statistic for confidence interval:
  # e.g., if conf.interval is .95, use .975 (above/below), and use df = N - 1
  ciMult <- qt(conf.interval/2 + .5, datac$N - 1)
  datac$ci <- datac$se * ciMult

  return(datac)
}