R codes used to generate results

Histogram (lattice package):

histogram(x | y, type="count", main="Main title", ylab="Frequency", xlab = "Horizontal axis title, i.e. variable name")

x is a vector of values for which the histogram is desired and y is a factor, i.e. categorical variable.

R codes used to generate results

Box plot or box-whisker plot (lattice package):

bwplot(x | y, type="count", main="Main title", ylab="Frequency", xlab = "Horizontal axis title, i.e. variable name")

x is a vector of values for which the boxplot is desired and y is a factor, i.e. categorical variable.

R codes used to generate results

Stemplot, also known as stem and leaf plot (lattice package):

stem.leaf(x)

x is a vector of values for which the stemplot is desired.

Back-to-back stemplots

stem.leaf.backback(x1, x2)

x1 and x2 are vectors of values for which the back-to-back stemplots are desired. They were created using a factor, i.e. categorical variable. This only works when the categorical variable has two categories (e.g. Female, Male).

R codes used to generate results

Dot plot/Stripchart (stripchart function):

stripchart(x ~ y, type="count", main="Main title", ylab="Frequency", xlab = "Horizontal axis title, i.e. variable name")

x is a vector of values for which the dotplot is desired and y is a factor, i.e. categorical variable.

R codes used to generate results

Stripchart (lattice package):

stripplot(~x | y, type="count", jitter=TRUE, factor=2, main="Main title", ylab="Frequency", xlab = "Horizontal axis title, i.e. variable name")

x is a vector of values for which the stripchart is desired and y is a factor, i.e. categorical variable.

R codes used to generate results

Normal quantile plot, also known as QQ plot (lattice package):

qqmath(x | y, main = "Main title", ylab = "Variable name", xlab = "z-score", distribution=qnorm,  
   prepanel.qqmathline(x, distribution = qnorm, probs = c(0.25, 0.75), qtype = 7),
    panel=function(...){
    panel.qqmath(...)
    panel.qqmathline(...) 
    })  

x is a vector of values for which the QQ plot is desired and y is a factor, i.e. categorical variable.

R codes used to generate results

Correlogram (corrgram package):

corrgram(cor, order=TRUE, lower.panel=panel.shade, upper.panel=panel.pie, text.panel=panel.txt, main = "Correlogram")}

cor is a data frame or correlation matrix.

R codes used to generate results

Scatterplot (car package):

scatterplotMatrix(x, var.labels=colnames(x), diagonal=c("density", "boxplot", "histogram", "oned", "qqplot", "none"), main="Scatterplot Matrix")

x is a data matrix, numeric data frame.

R codes used to generate results

Box-Cox transformation (MASS package):

boxcox(x~1)

x is a vector of values for which the Box-Cox transformation is required.

R codes used to generate results

Descriptive statistics (base package):

summary(x)

x is a data frame.

Descriptive statistics (psych package):

describe(x, skew=FALSE, ranges=FALSE)

Descriptive statistics grouped by one of the categorical variables (psych package):

describeBy(x, group=y, skew=FALSE, ranges=FALSE)

y is a categorical variable.

Descriptive statistics (pastecs package):

stat.desc(x)

R codes used to generate results

Detecting outliers using 1.5IQR rule:

# Create space to store outliers and their indices
  Outliers <- c()
  idxOutliers <- c()

# Get the lower/upper values in the 1.5IQR rule
  Upper <- quantile(x,0.75, na.rm=TRUE) + (IQR(x, na.rm=TRUE) * 1.5 )
  Lower <- quantile(x,0.25, na.rm=TRUE) - (IQR(x, na.rm=TRUE) * 1.5 )

# Get the id's using which
  index <- which(x < Lower | x > Upper)

# Output the value of outliers 
  Outliers <- c(Outliers, x[index])

# Append the outliers list
  idxOutliers <- c(idxOutliers, index) 

  output <- cbind(idxOutliers, Outliers)

x is a numeric vector.

R codes used to generate results

Correlation matrix:

cor(x, use="pairwise.complete.obs")

x is a matrix or data frame.

Calculating P-values Hmisc package:

signif(cor$P, 2)

cor is a correlation matrix.

R codes used to generate results

t-tests (t.test):

# One sample t-test
t.test(x, mu=m0)    # Ho: mu = m0

x is a numeric.

# Two sample t-test
t.test(x, y)

x and y are numeric.

# Match paired t-test
t.test(x, y, paired=TRUE)  # Both `x` and `y` must be the same length. 

The following options are available:

• To specify equal variances and a pool variance estimate: var.equal=TRUE.
• To specify confidence level of the interval: conf.level=0.095.
• To specify alternative hypothesis: alternative=c("two.sided, "less", "greater").

R codes used to generate results

Bartlett test of homogeneity of variances (bartlett.test):

bartlett.test(x, y)

x is a numeric vector of data values and y a vector or factor object giving the group for the corresponding elements of x.

R codes used to generate results

Levene's test for homogeneity of variance across groups (car package):

leveneTest(x, y, center=c('mean', 'median'))

x is a numeric vector of data values and y a factor defining groups. center is the name of a function to compute the centre of each group; mean gives the original Levene test; the default, median, provides a more robust test.

R codes used to generate results

ANOVA (Analysis of variance) (aov function):

ANOVA <- aov(x ~ y)
summary(ANOVA)

x is a numeric vector and y is a factor, i.e. categorical variable.