Skip to content
Skip to main content

About this free course

Become an OU student

Share this free course

Digital humanities: humanities research in the digital age
Digital humanities: humanities research in the digital age

Start this free course now. Just create an account and sign in. Enrol and complete the course for a free statement of participation or digital badge if available.

4.2.1 Quantitative analysis

Quantitative analysis means employing measuring techniques and tools to address our research question(s). The choice of a quantitative design is linked to the broader objectives of our study. Typically, quantitative analysis tries to tackle the research questions by testing one or more theories and related hypotheses through some form of data measurement, like statistical analysis. The resulting synthesis of this deductive approach should travel beyond the collected data. In this case, we say the results are generalisable.

Returning to our Darwin letters example, a quantitative study might try to use Darwin’s network to answer questions and test hypotheses about the underlying structure of nineteenth-century scientific networks.

Quantitative techniques

Our quantitative techniques should answer the research questions but also reflect the limitations offered by our data. With the Darwin letters, if we lacked ‘relational variables’, such as the name of the sender and the name of the receiver, quantitative network analysis could not be employed. A non-exhaustive enumeration of exclusively quantitative techniques includes:

  • Descriptive statistics entails a numerical description of our data in order to summarise the data and show the measures of distribution and dispersion of the different variables.
  • Bivariate and Multivariate analysis can reveal important correlations between two (bivariate) or more variables (multivariate) within the limits of the sample. This analysis is a stepping stone to more elaborate statistical tests of significance.
  • Statistical Inference. Assuming we have a representative sample, we can generalise our results to the entire population through statistical inference.

Most of these techniques predate the digital but today’s analytical tools (e.g. the R software environment for statistical computing [Tip: hold Ctrl and click a link to open it in a new tab. (Hide tip)] ), and the analysed data tend to be either born-digital (e.g. social media post) or digitised (marked up Darwin correspondence). This combination of the availability of large amounts of digital data and powerful software led to big data analytics.