Datalab 02: Findings & Data Visualisations

This data-lab day will focus on making clear and helpful data visualisations! First, we'll learn some rules on how to plot data and what makes a good graph. Then, we're going to use our new skills to create some good graphs and visualisations for our data-lab project!

Learning objectives: Build upon the basic understanding of data representations by learning to create data visualisations which are:

  • Informative: of the data (distribution).
  • Meaningful: relevant to the data-drive research question.
  • Unbiased: towards your own expectations.
  • Visually Clear & Appealing.
  • Have appropriate legends and additional labels and comments where needed.

Table of contents:

  1. Workshop: 3 hours
  2. Project: 5 hours

Good luck!

0) Workshop part: Exploratory Data Analyses

Start where you left off yesterday with the Exploratory Data Analysis and finish modules 6 and 7.

If you don't have the swirl course, then you download the R swirl course Exploratory Data Analysis by running the following code in the R-studio console:

swirl::install_course("Exploratory Data Analysis")

1) First things second

Before starting, look at the feedback you have received on your poster by navigating to your GitHub repository and clicking on the ‘Pull requests' header. There should be a feedback thread over there. Process the feedback and then continue as described below.

For those of you who haven't done so already: start uploading your script to our GitHub repository. That way, you never lose (too much) of your work, and we can also help you from a distance if there's something which you can't resolve or don't understand! :)

Do you feel like you could use some extra help or examples to deal with SDG data? Well, it's best for your educational process if we don't take you by the hand and walk you through everything… But, I couldn't resist helping you a bit, so I made a short script that looks at an outcome variable for a given country, and I outlined my thinking process using in-line comments (a description of what the line of code does). Click here for the script and the dataset, download both files and take a look at the graphs I plotted. The Swirl courses should have taught you everything you need to know to generate your descriptive statistics and graphs! However, I added two packages that generate some cool descriptive statistics "Hmisc" and "psych". You can also download them like that and play with them yourself, especially the ‘describe()' function of both is great!

Now, go and have some fun with R! Or frustration, it's part of working with data as well… haha

2) Creating the findings section

Create appropriate graphical representations and tables of your data to fill the poster, which are:

  • Informative: of the data (distribution).
  • Meaningful: relevant to the data-driven research question.
  • Unbiased: towards your own expectations.
  • Visually clear & appealing.
  • Have appropriate legends and additional labels and comments where needed.
Tip: If you are done early, and want to learn some extra fancy data visualisations skills: do modules 8, 9 and potentially 10 as well of the Exploratory Data Analysis course in Swirl. But, let me emphasize this clearly: it's an extra and by no means a requirement for this course.

2) In-Class discussion

At 16:00, we'll all get together in Datalab to discuss our progress and reflect on today activities.

Tomorrow, we're going to continue with probability theory.

Questions or issues?

In case you have any questions, please first ask your peers or send us a message on teams instead!

Resources