Once the data have been prepared, we can start the analysis. This is where the value is created and the insights gained can be then used further. There are many tools available that allow data visualisation and analysis.

Data visualisation – graphical analysis – can be a very useful tool in data exploration, as it it generally easier to see patterns and identify outliers by looking at graphed data. Figures (graphs, charts, plots) can also be a great help when discussing data and results of analyses with colleagues, funders and general public.

Statistical analysis – the use of conventional statistics (e.g. ANOVA, regressions) and descriptive statistics (e.g. cluster analysis, principal component analysis) to analyse collected data. Model runs and simulations may also be used to analyse data.

Reproducibility – reproducible research is the idea that scientific claims and analyses are conducted in such a way that they can be repeated – and verified – by others. In order to do that analyses should be published with their data and code. However, the idea of reproducibility is important even when you will not (or cannot) publish your data openly.

If you ensure that your data are well organised and described, that your analysis and code are annotated throughout you will have no problem getting your collaborators up to speed, or handing the project over to a new member of the team. Even if you are the only person working on the project these practices are beneficial – for instance when you come back to a project after a break.

Particularly relevant keywords:

  • data visualisation
  • reproducibility