![]() You can recalculate all the statistics if you assume the original counts to be uniform within the units, one of the assumptions of demographic data discussed earlier. Figure 1B shows the units arbitrarily divided into 10 new units. Recalculating the values based on an arbitrary division of the original units reveals that spatially intensive measures, such as density, are not dependent on the size of the area, whereas spatially extensive variables, such as area or count, are spatially dependent.įigure 1A shows statistics for the number of persons, area, and density (people/area) for five enumeration units. Data for the five enumeration units shows the number of people, area, and population density for each unit. To understand this better, look at Figure 1. For example, dividing counts by area yields density or dividing the count for one unit by the sum of counts for all units yields a proportion. Spatially intensive data can be derived from spatially extensive data. If you divide the unit, the value will stay the same. These statistics are spatially intensive and do not depend on the size of the unit. ![]() In contrast, values such as population density or cancer rates can describe any part of the unit (if the unit is assumed to be homogeneous). If you change the size of the unit, these statistics will change. Perimeter is the sum of the length of line segments that make up the boundary of the unit. For example, totals are the sum of the items counted in the unit. The statistic is the sum of the properties of elements that make up the unit. These statistics are said to be spatially extensive. Counts or totals and measures, such as area and perimeter, are summary statistics for the unit and are only true when they represent the unit as a whole. You must also consider whether the statistic being mapped depends on the size of the unit. Spatially Extensive versus Spatially Intensive Data In addition to determining whether the data being evaluated has these characteristics, there is another thing you need to know before mapping it. ![]() Landscape indicators for watersheds or subwatersheds and tax values in cadastral parcels are two examples of data collected for the unit as a whole that are assumed to be distributed uniformly across the unit and change at unit boundaries. Tabulations and derived values for enumeration units are assumed to be uniform across the area and change at unit boundaries (i.e., they do not blend from one unit into another). They can also include characteristics that describe those features, such as age, race, and income to describe people or age and type of housing unit.Ĭounts and characteristics can be used to derive measures that express either summarizations (e.g., mean, median) or relationships (e.g., densities, proportions). The tabulations include the count of features, such as persons, households, housing units, or students, within those units. Demographic data, which can include data for race, gender, age, employment status, and other factors, is tabulated over enumeration units such as counties, census tracts, ZIP Code areas, or school districts. It shows the statistical characteristics of a population and is one of the most common types of data shown on statistical maps. Not all methods work for all quantitative data.ĭemographic data provides an example. However, to appropriately map quantitative data, you must understand it. Proportional symbol maps display results as points that vary in size based on their associated values.īecause most statistical data is quantitative in nature, this article focuses on mapping quantitative data. Choropleth mapping uses lightness to symbolize polygons. Quantitative data can also be effectively portrayed using symbol variations such as orientation and pattern spacing, but hue, shape, lightness, and size are most often used because they are the most easily and correctly understood symbols.Ī number of mapping methods have been developed that combine various map features and symbols. The categorical differences in qualitative data can be shown with symbols that vary by color hue (e.g., red, green, blue) and shape (e.g., circles, squares, triangles). While either type of data can be expressed in a map using points, lines, polygons, and raster cells, the methods for mapping these two types of data are somewhat different. Quantitative data communicates a message of magnitude. Qualitative data differentiates between various types of things. Qualitative versus Quantitativeįundamentally, maps display only two types of data: qualitative and quantitative. ![]() This article explores issues related to mapping statistical data. Judging the effectiveness of a statistical map is easier if you understand the data being mapped and the method used to map it. If the map is effectively executed, you will intuitively and correctly understand the statistic mapped.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |