- The branch of Epidemiology, a cornerstone of public health, is based on the practice of identifying risk factors for disease and shapes policy decisions finding patterns and abnormalities in the evidence.
- Among other factors, spatial variations in disease incidences and health outcomes can play a crucial role in evaluating policies around health-care distribution and performance. Analysis of visible spatial patterns in data, using Moran's I, can lead to evidence of patterns of dependence and the level of noise in the data. Moran's I study provides with clustering patterns and concentrated abnormalities that allow the investigator to study to illuminate any unusual patterns and explore reasons for variations beyond normal in those areas. Detection of such patterns can be a crucial first step toward recognizing emerging environmental hazards or even persistent errors in data recording methodology.
- To accurately detect incidents on road/transportation networks for further investigation
- Examining how the value of a variable on a given segment of a network influences values of the variable on continuous segments. Examples of such a phenomena include traffic volume, traffic speed, and the number of vehicle crashes aggregated at the segment level. When the phenomenon of interest(vehicle crashes on the segments in this case) can be seen as a subset of a more generic spatial phenomenon(the entire traffic observed in the study region), Moran's I method is capable of taking into account the distribution of such a base phenomenon so that one can avoid the detection of spurious clusters merely reflecting the base distribution.
- Housing values are hard to correlate and understand the contributing factors for. Spatial autocorrelation anlaysis can help understand, the pattern of housing price variation - improving accuracy by correcting inconsistencies with respect to the location theory. Housing and retail prices are a factor of various contributing features, location being one of the largest ones. For example, nearby houses influence each other's prices due to proximity. Any error in measuring these factors can cause the prediction errors to exaggerate. Moran's I helps in the detection of such a phenomenon, if it is occurring, and in potentially correcting it to better analyze and predict the real estate market.
- Excessive accumulation of heavy metals in agricultural soils is a major source of pollution of surface and ground water, oceans and organisms. Spatial autocorrelation, specifically Moran's I is an established method widely being used to explore the spatial patterns of regionalized variables. It can be extremely dangerous to ignore outliers and clusters of pollution patterns which actually represent potentially severely polluted areas. Hence, Moran's I is widely used to describe the spatial distribution pattern of heavy metals in soils in turn revelaing areas that demand more focus and attention than others.