Overview
Data is essential for informed decision-making and understanding trends in our society.
This guide provides fundamental knowledge to help you better navigate, interpret, and use official statistics responsibly. It explains where data comes from, how to analyse it correctly, how to communicate findings responsibly, and why seasonal adjustments matter.
How to analyse data
Unit of analysis
The unit of analysis refers to the entity that is being studied in a dataset. For example, in clinical trials, the unit of analysis could be an individual (such as the patient). Macroeconomic studies may consider a whole country as a unit of analysis, e.g. comparing the productivity of workers between countries.
Units of analysis commonly found in the data published by DOS include:
- Individuals, on Population Structure (by Residency, Age, etc.), Marital Status, etc.
- Households, on Household Expenditure, Household Income from Work, etc.
- Firms, on Productivity, Value-added, Business Receipts Index, Retail Sales Index etc.
Types of data
In general, there are 2 types of data:
-
Qualitative data: Non-numerical which relate to words, pictures or even videos. It helps to answer ‘what’ or ‘why’ questions, and can be analysed by grouping the data into themes or categories.
An example is sentiment data which describe how individuals are feeling.
-
Quantitative data: Numerical in nature. It helps to answer questions pertaining to ‘how much’ or ‘how many’ and can be analysed using statistical analysis.
Examples of quantitative data include:
Data collected over a single time period (e.g. records are from a specific year). It allows the comparison of characteristics between units or groups at a fixed point in time.
In the example below, it can be seen that in 2022, there were 6 males and 4 females. Of the 4 females, only 1 lives in HDB housing while the rest live in private estates.
Primary and secondary data
Primary data refers to data directly collected from the data source. This can be through surveys, interviews, or experiments. It is generally considered reliable and objective. However, due to limitations such as cost and complexity of data, collecting primary data may not always be possible.
Secondary data refers to data collected by another party. One drawback is that secondary data are often not tailored to accommodate the specific needs of the researcher. It may also be costly to purchase if it is not freely available to the public.
Types of graphs and charts
Graphs and charts [PDF, 1MB] help to present complex data in a visually appealing and simple-to-understand manner. Common types of graphs and charts include: