[转] Moran's I

李旭， Matlab: Moran's I 原文地址

Introduction

In statistics, Moran's I is a measure of spatial autocorrelation developed by Patrick Alfred Pierce Moran. Spatial autocorrelation is characterized by a correlationin a signal among nearby locations in space. Spatial autocorrelation is more complex than one-dimensional autocorrelation because spatial correlation is multi-dimensional (i.e. 2 or 3 dimensions of space) and multi-directional.

Global Moran's I is defined as

where w_ij is the weight between observation i and j, and S₀ is the sum of all w_ij's, n is equal to the total number of pixels.:

The z_I-score for the statistic is computed as:

Where:

the p-value for the null hypothesis is written as

this formula sources from Aki-Hiro Sato. Applied Data-Centric Social Sciences: Concepts, Data, Computation and Theory. Japan, Springer, 2014. pp. 137-138.

Negative/positive values indicate negative/positive spatial autocorrelation. Values range from -1 (indicating perfect dispersion) to 1 (perfect correlation). A zero value indicates a random spatial pattern. For statistical hypothesis testing (the null hypothesis of no autocorrelation is not equal to zero but given by I₀ = -1/(n-1).), Moran's I values can be transformed to z-scores in which values greater than 1.96 or smaller than -1.96 indicate spatial autocorrelation that is significant at the 5% level.

栅格数据的权重规则：In its simplest form, these weights will take values 1 for close neighbours, and 0 otherwise，并规定栅格邻接为四至，如Fig. 1，中间绿色的像元的四至是四个橘红像元，绿色像元与他们之间存在着公共边，四个蓝色像元虽与绿色像元临近但不存在公共边，故而，绿色像元与橘红像元的权重是1，而与蓝色像元权重是0。（Rooks Case, Bishops Case, Oueen's (Kings) Case）

Fig. 1

Example

四张NDVI影像测试本帖代码，计算有效区域（mask影像数值是1像元）的Global Moran's I。代码运算结果如Fig. 2，MODIS_NDVI_200308的Global Moran's I是0.95467222，Z-score是418.50598145，ArcGIS计算结果分别是0.954661和418.498382，两者计算结果非常接近，考虑到二者计算中间数值的精度不同，这很可能就是引起二者差异的主要原因。其他三张数据情况类似，代码计算结果与ArcGIS结果非常接近。

Fig. 2

仍以MODIS_NDVI_200308Z-score为例说明显著性水平。如Fig.3，非常形象地说明Z-score与p之间对应关系，Z-score等于418.50598145大于2.58，说明此时p小于0.01，该Global Moran's I等于0.95467222通过0.01显著性水平检验。

Fig. 3 

References

[1] Moran's I, from Wikipedia, the free encyclopedia.

[2] Geary's C, from Wikipedia, the free encyclopedia.

[3] How Spatial Autocorrelation (Global Moran's I) works.

[4] What is spatial autocorrelation (spatial dependency)?

[5] Spatial Autocorrelation, ArcGIS for Polygons.

[6] What is a z-score? What is a p-value?

没有整理与归纳的知识，一文不值！高度概括与梳理的知识，才是自己真正的知识与技能。 永远不要让自己的自由、好奇、充满创造力的想法被现实的框架所束缚，让创造力自由成长吧！ 多花时间，关心他（她）人，正如别人所关心你的。理想的腾飞与实现，没有别人的支持与帮助，是万万不能的。

  本文转自wenglabs博客园博客，原文链接：http://www.cnblogs.com/arxive/p/5087179.html ，如需转载请自行联系原作者