Spatial data
Spatial data refers to data that are associated with a specific location or geographical area. The spatial data published in our database are mostly on county or municipality level. Many indicators are published at county and/or municipality level, making them valuable spatial data. Such data are essential for comparing the competitiveness and development of various regions and serve as a foundation for evidence-based policymaking. Spatial data help to create better strategies and make decisions that support the sustainable development and well-being of regions.
Statistics Estonia's map application utilises data from the statistical database to allow users to visualise data and thereby better understand them. To ensure greater data literacy, each layer includes a timeline of at least a couple of years, allowing users to compare past and present figures. This helps to create a more informed understanding of changes and developments across various fields.
Developed in collaboration with the Estonian Land and Spatial Development Board, the map application is a data visualisation tool that helps users to better understand the content and scope of our datasets, and thereby draw informed conclusions and make sound decisions.
Extracts of spatial data
We are making INSPIRE grid maps more accessible. The maps are compiled for Eurostat under the INSPIRE directive. The grid map consists of a 1 x 1 km grid covering Estonia, where each cell represents the number of people residing in that specific area. This provides an accurate overview of the population distribution across the country.
Additionally, we are making available another dataset published under the INSPIRE directive: NUTS 3 regions and the corresponding population numbers by age groups.
Perturbing confidential values on the population grid map
On the population grid map, small values are perturbed to ensure confidentiality. This is done in two stages. First, for all grid cells with a population of fewer than three, a new inhabited grid cell located as close as possible is identified. The condition for perturbation is that the new grid cell must be within the same municipality. A grid cell’s belonging to a municipality is determined based on the largest area overlap. The more sparsely populated the area, the farther people are perturbed. In the second stage, the cell key method is applied to perturb descriptive attributes. Noise is added to values across multiple attributes in a similar way. This means that the perturbed values differ slightly from the original ones but the aggregated values for sex or age groups per grid cell remain identical.
The final result is obtained by combining the outcomes of both stages. For each grid cell, we publish the total population perturbed in the first stage. For most grid cells, this reflects the true population, and summing all grid cells gives us the actual population of Estonia at the observation moment. We also publish the perturbation of residents by sex and age group for each grid cell. These values are calculated using the cell key method, and their sum may differ from the total population calculated in the first stage.
The cell key method is applied to grid maps starting from 2025.
The data calculated using the cell key method are also published in the statistical database tables RV068, RV0240, RV0232U, and RV0282U.
Read more Ensuring the confidentiality of statistical outputs
All data layers are available in SHP and CSV formats.