Fri Sep 30, 2016

5NG

Today:

  1. Scatterplot AKA bivariate plot
  2. Linegraph
  3. Boxplot
  4. Barplot AKA Barchart AKA bargraph
  5. Histogram

Example

If I know your name, I can guess your age.

Statistics Terminology

  • All the plots with either blue/yellow bars red dots are boxplots (without whiskers) that indicate the 3 quartiles
    • 1st quartile i.e. 25th percentile
    • 2nd quartile i.e. 50th percentile
    • 3rd quartile i.e. 75th percentile

Statistics Terminology

  • The 2nd quartile is also called the median. It is a measure of center
  • The width of the bars (3rd quartile - 1st quartile) is the interquartile range (IQR)
  • The IQR contains the middle 50% of observations. It is a measure of spread

Boxplots

Why Boxplots?

You can compare distributions of values in different groups with a single line.

Look at the chart in this Planet Money article. In this case, you can compare cities with a single vertical line.

Today

Before we lay out boxplots however, we have two digressions:

  • Facets: spliting a plot on a categorical variable
  • Summary statistics