Data types
On this page
In medical research, the purpose of collecting data is to obtain meaningful information about a specific clinical or research question. The type of data collected directly influences how it can be summarised, analysed, and interpreted using statistical methods.
The choice of appropriate statistical tests depends on the type of data collected.
1. Categorical Data
Categorical data represents variables that fall into distinct categories. Each individual or observation fits into one and only one category.
Categorical data can be further classified as:
A special form of categorical data is:
Converting Quantitative to Categorical Data
Quantitative data are sometimes converted to categorical variables for ease of presentation (e.g. dividing age into age groups). While useful for summarisation, this conversion:
Statistical implications:
Data Classification
Data can be broadly classified into two categories:- Categorical (Qualitative) Data
- Quantitative (Numerical) Data
The choice of appropriate statistical tests depends on the type of data collected.
1. Categorical Data
Categorical data represents variables that fall into distinct categories. Each individual or observation fits into one and only one category.
Categorical data can be further classified as:
- Nominal Data: Categories that are named but have no inherent order (e.g. blood group, gender, marital status).
- Ordinal Data: Categories with a natural, ranked order (e.g. pain scores, tumour staging), but the intervals between values are not necessarily equal.
A special form of categorical data is:
- Binary (Dichotomous) Data: A type of nominal data with only two categories (e.g. yes/no, male/female, positive/negative test result).
Note: Categorical data are often easier to summarise but may lose information if derived from originally quantitative data.
2. Quantitative Data
Quantitative data consist of numerical values that represent measurable quantities. These are divided into:- Discrete Data: Numeric values that are counted and can take only specific, separate values (e.g. number of children, number of ED visits).
- Continuous Data: Data that can take any value within a given range and are usually measured (e.g. weight, height, blood pressure).
Example: Age is technically continuous, but it is often treated as discrete (e.g. 'age at last birthday') in practice.
Converting Quantitative to Categorical Data
Quantitative data are sometimes converted to categorical variables for ease of presentation (e.g. dividing age into age groups). While useful for summarisation, this conversion:
- Reduces the richness of information
- Decreases statistical power
- Should be avoided for inferential analysis unless clinically justified
Statistical implications:
- The type of data determines which statistical tests are appropriate.
- Continuous variables allow for more powerful statistical testing than categorised versions of the same data.
- Choosing the wrong statistical method for the data type can lead to inaccurate conclusions.