Scale of analysis is a fundamental issue in GIS. A natural phenomenon should not be studied in a single scale because the interfacing of a phenomenon in different scale can change. Even though there may be no single natural scale, many have argued that ecological phenomena tend to have characteristic spatial and temporal scales or spatiotemporal domains.

           

Geography is important in the analysis because issues such as the scale, grain, and extent of a study area, the modifiable area unit problem (MAUP), the nature of the boundaries of a study area, and spatial dependence/ heterogeneity are implicit in any spatial analysis. Grain is the minimum resolution of the data. For raster data, it defines the cell size, and for vector data, it defines the minimum mapping unit. Extent is the scope or domain of the data.

 

Spatial Autocorrelation

Cliff and Ord (1973) define spatial autocorrelation as: “if the presence of some quantity in a sampling unit makes its presence in neighboring sampling units more or less likely, we say that the phenomenon exhibits spatial autocorrelation.  Most organisms are not randomly distributed on Earth. The distribution of organisms follows a spatial pattern. Therefore, they are spatially autocorrelated. Moran’s I analysis is a tool in GIS that can determine spatial autocorrelation.

 

Modified Area Unit Problem (MAUP)

MAUP defines the uncertainty raised by choosing a scale for a study or from choosing zonal units. When the scale of a study is changed, the grain of the study changes correspondingly. Zonal unit of the analysis also directly influences the study result. Different areal arrangements of the same data can produce different results. Therefore, study result is not irrelevant to the units of analysis and resolution of the data.