Practical 2: Exploratory data analysis

This is the second practical lesson where we learn how to perform exploratory data analysis

Objectives

• Explore the data
• Summaries
  • Tabulation (One- and two-way tables)
  • Measures of central tendency, dispersion, distribution
• Graphics
  • Categorical
    • Barchart
  • Numeric
    • Histogram, density plot, boxplot, QQplot, violin plot,
  • Categorical vs Categorical
    • Barplot
  • Numeric vs numeric
  • Categorical vs Numeric

To do

Categorical variable

• We usetitanic.xlsx
• Statistics
  • Look out for missing
  • One-way tabulation of class of the passengers
  • Two-way tabulation of the class and outcome of the passengers
  • Multiple-way tabulation of class, sex and outcome of the passengers
• Graphics
  • One-way bar plot of
  • Two-way bar plot

Numeric variable

• Use “blood.xlsx”
• Statistics – Measure of central tendency
  • Mean
  • Median
  • Mode
• Statistics – measures of dispersion
  • Standard deviation
  • Variance
  • Range
  • IQR
  • Minimum, maximum
• Outliers
• Distribution
  • Skewness
  • Kurtosis
• Normality
• Graphics
  • Histogram
  • Density plot
    • Single
    • Comparative
  • Boxplot
    • Single
  • Comparative
  • Violin plot (+ data points)
    • Single
    • Comparative