Moran's I Autocorrelation Statistic

Share:

Description

Moran's I statistic measures autocorrelation between areas within a region. It is similar to the correlation coefficient:

I= n * [sum_i ( sum_j W_ij(Z_i-mean(Z))*(Z_j-mean(Z))]/[2 * (sum_i sum_j W_ij) * sum_k (Z_k-mean(Z))^2]

W is a squared matrix which represents the relationship between each pair of regions. An usual approach is set w_ij to 1 if regions i and j have a common boundary and 0 otherwise, or it may represent the inverse distance between the centroids of these two regions.

High values of this statistic may indicate the presence of groups of zones where values are unusually high. On the other hand, low values of the Moran's statistic will indicate no correlation between neighbouring areas, which may lead to indipendance in the observations.

moranI.stat is the function to calculate the value of the statistic for residuals or SMRs of the data.

moranI.boot is used when performing a non-parametric bootstrap.

moranI.pboot is used when performing a parametric bootstrap.

References

Moran, P. A. P. (1948). The interpretation os statistical maps. Journal of the Royal Statistical Society, Series B 10, 243-251.

See Also

DCluster, moranI.stat, moranI.boot, moranI.pboot

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.