Spatial autoregressive models

Spatial Dependency:

• Spatial dependency refers to the phenomenon where the value of a variable at one location is influenced by the values of the same variable at neighboring locations. This is often captured using a spatial weights matrix, which defines the spatial relationships between different locations.

Spatial Weights Matrix:

• The spatial weights matrix is a key component of spatial autoregressive models. It is a square matrix where each element represents the strength of the spatial relationship between locations and . Common choices for include binary contiguity (neighboring locations have a weight of 1, others have 0) and distance-based weights.

Spatial Lag Model (SLM):

• The spatial lag model incorporates spatial dependency directly into the dependent variable. The model can be written as:

where is the vector of observations, is the spatial autoregressive parameter is the spatial weights matrix, X is the matrix of explanatory variables, is the vector of coefficients, and is the error term.

Spatial Error Model (SEM):

• The spatial error model incorporates spatial dependency into the error term. The model can be written as:

  where u is the spatially correlated error term, is the spatial autoregressive parameter for the error term, and is the independent error term.

Spatial Durbin Model (SDM):

• The spatial Durbin model combines elements of both the spatial lag and spatial error models. It includes spatial lags of both the dependent variable and the explanatory variables. The model can be written as:
  

  where represents the spatial lags of the explanatory variables, and is the vector of coefficients for these spatial lags.

Species Distribution Modeling:

• Spatial autoregressive models can be used to predict the distribution of species across a landscape. By incorporating spatial dependency, these models can capture the influence of neighboring habitats on species presence or abundance, leading to more accurate predictions.

Habitat Suitability Mapping:

• Habitat suitability models assess the quality of habitats for specific species. Spatial autoregressive models can improve these assessments by accounting for the spatial correlation in habitat quality, which is often influenced by neighboring habitats.

Environmental Indicator Mapping:

• Environmental indicators, such as air or water quality, often exhibit spatial dependency. Spatial autoregressive models can be used to map these indicators, providing insights into the spatial patterns and hotspots of environmental degradation or improvement.