going places with spatial analysis  

spatial data = data with a geographical component connected to some place on the earth
geo-coding = the process of finding a geographic location based on other information, like a street address
gi science = science of dealing with spatial data and spatial issues
spatial interaction = measurement of movement of phenomena, such as the flow of goods, people, or information from place to place
spatial analysis allows us to solve complex problems and better understand what is happening in the world and where
analysis = the systematic examination of a problem to provide new information for what’s already known
geographic information system = the tool we use to capture, store, process, analyse, and visualize visualize spatial information
raster data = real world entities are represented as regular grids, like digital photographs
vector data = real world entities are represented as features in three basic shapes of points, lines, and areas
attribute data = information that describes what is known at any location

understanding and comparing places #

query = a request to select features or records from a database. a query is often written as a statement or logical expression/ knowledge about the data
three basic geometric shapes - points, lines, and areas/ polygons
scale = the ratio or relationship between a distance or area on a map and the corresponding distance or area on the ground, commonly expressed as a fraction or ratio
data coordinates and measurements - position, length, direction, area, proximity, volume
proximity tells us what is nearby - cost, time, distance
euclidean distance = straight line distance between two points on a plane. euclidean distance, or distance “as the crow flies,” can be calculated using the Pythagorean theorem
map projection = a mathematical method by which the curved surface of the earth is portrayed on a flat surface
a distorted reality - mercator (preserves direction over shape and area), mollweide (preserves area over shape and direction), bonne (preserves area: useful for mapping continents or smaller regions), goode homolosine land (preserves area: useful for world maps)
thematic map = a map designed to convey information about a single topic or theme

determining how places are related #

overlay analysis = stacking spatial data on top of each other and processing a combination of both spatial features and attributes to create a new layer
vector overlay = estimates the geometric intersection of multiple data-sets of the same or different geometries and combines then to create a new output data-set
modifiable areal unit problem = results can differ when the same data but different aggregation schemes are used
choropleth map = a thematic map in which areas are distinctly colored or shaded to represent classed values of a particular phenomenon

finding the best locations and paths #

topological data = information about the relative positions of spatial features
suitability analysis = weighs locations relative to each other based on given criteria using spatial and attribute queries and/ or overlay methods
boolean suitability = describes locations as either suitable or not suitable based on a true or false (logical) condition.
weighted suitability = assigns more important to some criteria than others to rank locations with relative suitability values
cost path analysis = finds best path between two locations that costs the least to traverse using the cost of time, or some other criteria

detecting and quantifying patterns #

kernel density estimation = measures the density of a point pattern based on sample observations. it creates a continuous surface showing the density of features
jenks natural breaks = optimizing method that uses data clustering. aims to minimize the variance within classes and maximize the variance between classes
tobler’s first law of geography = everything is related to everything else, but near things are more related to distant
inferential statistics = an approach used to test various, hypotheses, which is the basis of decision making
spatial autocorrelation = measure of similarity of objects within an area; the degree to which a spatial phenomenon is correlated to itself in space

making prediction #

regression = a statistical method for evaluating the relationship between a single dependent variable and one or more independent variables
gravity model = a model that assumes that the influence of phenomena or populations on each other varies inversely with the distance between them. In light of the First Law of Geography, this is a sensibly common approach to modeling spatial interaction
spatial autocorrelation = a measure of the degree to which a set of spatial features and their associated data viable values tend to be clustered together in space or dispersed
deterministic interpolation = techniques used to create surfaces from measured points, based on either the extent of similarity or the degree of smoothing
kriging = an interpolation technique in which the surrounding measured values are weighted to derive a predicted value for an unmeasured location
stationary = a property of a spatial process in which all statistical properties of an attribute depend only on the relative locations of attribute values