Cluster: a concentration of events, typically described by their close proximity to each other.

Coefficient of variability: a statistical measure that is used to describe how events change over time.

Continuous density surface: a map layer, made up from a grid network of fine grid cells, that represents the distribution of point events as a density surface. Areas where points are close together are represented across the surface by grid cells that have high density values. Areas where points are spread apart are represented by grid cells with low density values.

Dispersion: a term used to describe the level of separation between geographic events. For example, a set of geographic points that are dispersed would be seen to be widely spread across the area of interest.

Eastings: a geographic coordinate (often represented as a 6 figure number) that represents the location of an event along an east to west axis.

Enumeration district: an enumeration district (ED) is the smallest geographic area to which Census data can be associated. On average, an ED area represents approximately 200 households and aims to be homogenous in the physical and socio-economic characteristic of the area it represents. EDs are of varying sizes and shapes.

Geocode, geocoding (digital geocoding): Geocoding is the process of assigning geographic coordinates to attribute or event records for the purpose of mapping within a GIS environment. The process of geocoding recognises an address (or other locational reference) within a crime or disorder incident record and assigns the record an eastings and northings geographic coordinate. The geographic coordinate can then be used to map the crime or disorder record. For example, a crime record contains the address details ‘5 High Street’. The geocoding process recognises this address and assigns it its relevant eastings and northings coordinate. This coordinate maps the crime record to its address and can be viewed against base mapping street data in a GIS.

Geocoding hit rate: the term used to describe the percentage of records that have been successfully geocoded.

Geographical Information System (GIS): a computer system for capturing, managing, integrating, manipulating, analysing, and displaying data which is spatially referenced to the earth.

Geographical referencing: a process of linking information that is referenced to an address, location or area (e.g. enumeration district).

Global statistical tests: mathematical calculations that provide a general description that summarise the pattern, distribution, or charactersitics of the data that is being analysed.

Grid network: a group of cells (typically of a defined size) that make up an area that cover a region of interest.

Hotspot: a hotspot is a geographical area of higher than average crime or disorder. It is an area of crime or disorder concentration, relative to the distribution of crime and disorder across the whole region of interest (e.g. ward, district, or county). Hotspots are areas of clusters of crime or disorder that can exist at different scales of interest. See the section ‘What is a hotspot?’ for more details.

Incremental values of the mean: a thematic range where classes are separated by increasing values of the mean of all values.

Kernel density estimation: a method that creates a smooth surface of the variation in the density of point events across an area.

Mapped: the process of placing a record at its geographical location, or producing a geographical display of information.

Nearest Neighbour Index (NNI): a statistical test, usually applied to property or postcode precision point data, that can be used to reveal whether there is evidence of clustering, and therefore hotspots, in mapped crime or disorder data.

Northings: a geographic coordinate (often represented as a 6 figure number) that represents the location of an event along a north to south axis.

Polygon: a term use to describe a geographic object, usually representing a region or area of interest (e.g. an enumeration district, beat, or ward).

Precision: refers to the exactness with which a value is expressed, whether the value be right or wrong. Different levels of geographic precision exist. The highest precision possible is where a crime or disorder incident can be mapped to the exact location where the event occurred. On occasions, particularly for data protection purposes, the precision of an incident is lowered to a wider area, but which still accurately represents the location where the event occurred (e.g. the full postcode of the specific address).

Sanitising: the sanitising of data involves the removal of any information that could identify an individual, be it through a person’s name or a precise location. The geographic sanitising of location information requires data to be aggregated to a lower geographic precision. Most typically this involves aggregating crime or disorder information from a precise address describing the location of an incident to a wider area (e.g. full postcode unit, enumeration district, or ward). For example, to sanitise an incident that took place at 5 High Street would involve the removal of the street number, and the geocoding to the centroid of the full postcode that represented the address.

Spatial: a term used to describe any information about the location and shape of, and relationships among, geographic features.

Spatial autocorrelation: Spatial autocorrelation techniques test for the condition of whether the distribution of events are related to each other. In the case of crime and disorder data, where events are clustered (i.e. where there are hotspots) or where events close together have similar values than those that are further apart, positive spatial autocorrelation is said to exist.

Standard distance deviation: a statistical test, usually applied to property or postcode precision point data, that can be used to measure relative levels of dispersion between crime or disorder events or the same crime/disorder types for different periods of time.

Temporal change: the description of the variation or frequency of events over time. For example, this could refer to how crime events change over the course of several years, over seasons, by day of the week, or time of day

Thematic map: a thematic map is a method for displaying the geographic distribution of selected types of information that have a common theme. For crime and disorder, thematic maps typically represent the distribution of counts of incidents or rates by defined geographic areas (e.g. enumeration districts, beats, parishes or wards).

Thematic ranges: a group of methods used to distinguish the thematic settings in a thematic map into separate classes.

Equal ranges – classes defined by dividing the data range (the difference between the maximum and minimum values of the data) into equal increments.

Natural break – an approach that uses gaps or depressions in the frequency of the distribution to establish boundaries between classes

Standard deviation – the standard deviation is a statistical measure of the spread of data around the mean. Generally, classes are defined above and below the average in units of one standard deviation.

Custom range – a method that allows users to determine class intervals according to their own criteria, such as regional or national norms and thresholds that follow in a more logical and easier to interpret sequence.

Virtually automated: a process, often performed by computer software, that involves very little human interaction.

Weighted method: a statistical method that assigns probabilities to each time interval within the range that relates to when the incident may have occurred. These probabilities calculated for all incidents are then summed for each time interval to reveal trends in the change of incidents over time (typically by day of the week, or time of day).