Welcome to the course!

Statistical Techniques in Tableau

Maarten Van den Broeck

Content Developer at DataCamp

Exploratory Data Analysis (EDA)

  • Main characteristics of your data
  • Spot extreme values
  • Suggest hypotheses
  • Assess assumptions

General goal: get an idea of the overall structure of your data

Univariate EDA

  • Summary table
  • Bar plot
  • Histogram
  • Box plot
Statistical Techniques in Tableau

Tables & bar plots

Visualize the distribution of a single, categorical variable

Category
A
B
A
B
B
C
A
B
C

A count table, summarizing the number of occurrences per category

 

A bar plot, with the occurrences per category now represented as horizontal bars

Statistical Techniques in Tableau

When to use a table vs. a plot

  • Focus is on individual values (snapshot) and not on trends
  • Dataset contains few values
  • Small difference between values is crucial
  • Data is presented in a non-interactive way

A count table, with four categories with extreme low and high values.

 

The same data, with extreme low and high values, now as a bar plot. The extreme low values are not visible anymore.

Statistical Techniques in Tableau

Histograms

Visualize the distribution of a single, continuous variable

  • Lowest/highest value
  • Most common value(s)
  • Splitting variable in bins

A histogram of quantities of items ordered per customer, with bin size of one item.

Statistical Techniques in Tableau

Size of bins

Binwidth = 1.5 The same histogram as before, now with bin size of 1.5, keeping some detail of the distribution.

Binwidth = 4 The same histogram as before, now with bin size of 4, losing some detail of the distribution.

Statistical Techniques in Tableau

Modality

Three histograms displaying unimodal, bimodal, and trimodal distributions, with one, two, and three peaks respectively.

Mode: most occurring value

Statistical Techniques in Tableau

Let's practice!

Statistical Techniques in Tableau

Preparing Video For Download...