Skip to main content Skip to navigation


Analysis is the process of presenting and interpreting data. Qualitative data (non-numeric data) is generally achieved by reducing the data, structuring it and desexualising it [1]. Quantitative data analysis is based on applied mathematics and uses standard statistical methods.


For qualitative data, it is a progression from the raw data (Results) to an explanation, understanding and interpretation of the replies and opinions that have been gathered. It requires an examination of the important and the figurative content of the qualitative data. You may be trying to illustrate some or all of the following:

  1. An individual’s understanding of a subject,
  2. Why this point of view has occurred,
  3. What led to this view being adopted,
  4. The individual’s involvement with the subject,
  5. How the view was communicated,
  6. The individual’s understanding of other peoples’ point of view.


From the Study Skills and Academic Writing workshops and e-learning content you will have learnt that common features of analytic methods include:

  1. Affixing codes to a set of field notes drawn from data collection
  2. Noting reflections or other remarks in margin
  3. Sorting or shifting through the materials to identify similar phrases, relationships between themes, distinct differences between subgroups and common sequences
  4. Isolating patterns and processes, commonalties and differences, and taking them out to the filed in the next wave of data collection
  5. Gradually elaborating a small set of generalisations that cover the consistencies discerned in the data base
  6. Confronting those generalisations with a formalised body of knowledge in the form of constructs or theories

One approach open to the researcher is to quantify the data - convert qualitative, text based data into numeric data. In some cases, this may enable some statistical analysis to be carried out if required.

Whatever technique or combination of techniques is used to analyse this rich, informative, but essentially cumbersome data, the researcher should bear in mind that good research requires that a logical, systematic and robust approach be taken to the treatment of the data, and one which is transparent to the reader.


a) Descriptive Statistics

Your research may generate a large quantity of data – a questionnaire comprising 30 questions, completed by 100 people will generate 3000 items of raw data. This will need to be organised and summarised, so that anyone reading it can understand what the data is showing. Descriptive or summary statistics (including ‘measures of central tendency ‘ and ‘measures of dispersion’) are frequently used to describe and/or summarise data.

b) Inferential Statistics

This infers the beliefs of the population from a knowledge of the beliefs of a sample. Usually it is not practical to interview the entire population.

For this, the sample must be representative of the population, and you must justify the selection of your sample group. However, the sample is still unlikely to truly reflect the beliefs of population in all aspects. This uncertainty can be quantified by statistical methods and needs to be recorded in your dissertation.

** More details of both of these can be found in the Study Skills content and you will be offered workshops on Quantitative and Qualitative data analysis methods later in the year**