RinAction - Basic Statistics & Grouped Statistics

gistfile1.r

#-----------------------------------------------------------------------------#
#-----------------------------------------------------------------------------#
#                 R in Action - Basic Statistics 
#             - Descriptive Statistics
#-----------------------------------------------------------------------------#
#-----------------------------------------------------------------------------#

install.packages(c('npmc', 'ggm', 'gmodels', 'vcd', 'Hmisc','pastecs', 'psych', 'doBy', 'reshape'))

##############################################
##############################################
# -------- Descriptive Statistics ---------- #
##############################################
##############################################

vars <- c("mpg", "hp", "wt")
head(mtcars[vars])

#############################
### A. Simple Descriptive Stats 
#############################

# 1 - descriptive stats via summary

summary(mtcars[vars])

# 2 - descriptive stats via sapply()

mystats <- function(x, na.omit = FALSE) {
  if (na.omit) 
    x <- x[!is.na(x)]
  m <- mean(x)
  n <- length(x)
  s <- sd(x)
  skew <- sum((x - m)^3/s^3)/n
  kurt <- sum((x - m)^4/s^4)/n - 3
  return(c(n = n, mean = m, stdev = s, skew = skew, kurtosis = kurt))
}

sapply(mtcars[vars], mean)
mystats(mtcars[vars],na.omit=TRUE)
a <-lapply(mtcars[vars], mystats)
b <-sapply(mtcars[vars], mystats)
c <- apply(mtcars[vars],2,mystats)


# 3 - Descriptive statistics (Hmisc package)

library(Hmisc)
describe(mtcars[vars])

# 4 - Descriptive statistics (pastecs package)

library(pastecs)
stat.desc(mtcars[vars])

# 5 - Descriptive statistics (psych package)

library(psych)
describe(mtcars[vars])

###################################
### B. Descriptive Stats BY GROUP
###################################

# 6 - Descriptive statistics by group with aggregate() # Only allows single value funtion for each call

aggregate(mtcars[vars], by = list(am = mtcars$am), mean)
aggregate(mtcars[vars], by = list(am = mtcars$am), sd)

# 7 - Descriptive statistics by group via by() # allows multiple functions per call

dstats <- function(x)(c(mean=sapply(x,mean), sd=sapply(x,sd)))
by(mtcars[vars], mtcars$am, dstats)

# 8 Summary statists by group (doBy package)

library(doBy)
summaryBy(mpg + hp + wt ~ am, data = mtcars, FUN = mystats)

# 9 - Summary statistics by group (psych package)

library(psych)
describe.by(mtcars[vars], mtcars$am)

# 10 Summary statistics by group (reshape package)

library(reshape)
dstats <- function(x) (c(n = length(x), mean = mean(x), 
                         sd = sd(x)))
dfm <- melt(mtcars, measure.vars = c("mpg", "hp", 
                                     "wt"), id.vars = c("am", "cyl"))
cast(dfm, am + cyl + variable ~ ., dstats)