Statistical disclosure control methods for Census 2021

The UK Data Service and the Office for National Statistics (ONS) are running this free webinar to help users get to grips with statistical disclosure control in the Census 2021 for England and Wales.

For Census 2021, ONS used three key methods:

• Record swapping: targeting unusual records in the data and swapping them with similar ones in nearby areas, and swapping a small percentage of all records.
• Cell Key perturbation: adding ‘noise’ to the values, with a higher likelihood that smaller values will be changed, to add uncertainty. Where the same records are represented in a cell in any table, the level of perturbation is the same.
• Suppression rules: these are built into the Create a custom dataset system on the ONS website and prevent datasets being available if they fail to meet certain thresholds.

What this means for researchers: Readily available research data at a mouse click, with variables and classifications decided by you. Where the system suppresses data, you may be able to get less detailed data for the same area, or the same detail for a larger area.

Due to perturbation, totals do not necessarily add up to the same figure all the time, though this should be a very minor difference that doesn’t inhibit research. Small area analysis should bear this in mind when handling small numbers of population – they may be from a different area, again this should not be at a level that inhibits research.

The webinar will take place in MS Teams.

Book a place to find out more.