This action might not be possible to undo. Are you sure you want to continue?

BooksAudiobooksComicsSheet Music### Categories

### Categories

### Categories

Editors' Picks Books

Hand-picked favorites from

our editors

our editors

Editors' Picks Audiobooks

Hand-picked favorites from

our editors

our editors

Editors' Picks Comics

Hand-picked favorites from

our editors

our editors

Editors' Picks Sheet Music

Hand-picked favorites from

our editors

our editors

Top Books

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Audiobooks

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Comics

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Sheet Music

What's trending, bestsellers,

award-winners & more

award-winners & more

Welcome to Scribd! Start your free trial and access books, documents and more.Find out more

Moran’s I Geary’s C

© Arthur J. Lembo, Jr. Salisbury University

Spatial Autocorrelation

• First law of geography: “everything is related to everything else, but near things are more related than distant things” – Waldo Tobler • Many geographers would say “I don’t understand spatial autocorrelation” Actually, they don’t understand the mechanics, they do understand the concept.

© Arthur J. Lembo, Jr. Salisbury University

1

Spatial Autocorrelation • Spatial Autocorrelation – correlation of a variable with itself through space. Lembo. Salisbury University Why spatial autocorrelation is important • Most statistics are based on the assumption that the values of observations in each sample are independent of one another • Positive spatial autocorrelation may violate this. Salisbury University 2 . if the samples were taken from nearby areas • Goals of spatial autocorrelation – Measure the strength of spatial autocorrelation in a map – test the assumption of independence or randomness © Arthur J. Jr. Jr. it is said to be spatially autocorrelated – If nearby or neighboring areas are more alike. Lembo. – If there is any systematic pattern in the spatial distribution of a variable. this is positive spatial autocorrelation – Negative autocorrelation describes patterns in which neighboring areas are unlike – Random patterns exhibit no spatial autocorrelation © Arthur J.

© Arthur J. since events tend to be concentrated. – If the observations. the twodimensional equivalent of redundancy • It measures the extent to which the occurrence of an event in an areal unit constrains. there are actually fewer number of independent observations than are being assumed. Jr. Salisbury University 3 . Salisbury University Spatial Autocorrelation • Non-spatial independence suggests many statistical tools and inferences are inappropriate. the estimates obtained from the correlation coefficient or OLS estimator will be biased and overly precise. Lembo. however. Jr.Spatial Autocorrelation • Spatial Autocorrelation is. Lembo. – They are biased because the areas with higher concentration of events will have a greater impact on the model estimate and they will overestimate precision because. the occurrence of an event in a neighboring areal unit. conceptually as well as empirically. © Arthur J. are spatially clustered in some way. – Correlation coefficients or ordinary least squares regressions (OLS) to predict a consequence assumes that the observations have been selected randomly. or makes more probable.

• Compares the value of the variable at any one location with the value at all other locations N ∑i ∑ j Wi . 1950). j )∑i ( X i − X ) 2 © Arthur J. Salisbury University Moran’s I • One of the oldest indicators of spatial autocorrelation (Moran. Lembo. Jr. Salisbury University 4 . Still a defacto standard for determining spatial autocorrelation • Applied to zones or points with continuous variables associated with them.Indices of Spatial Autocorrelation • • • • Moran’s I Geary’s C Ripley’s K Join Count Analysis © Arthur J. j ( X i − X )( X j − X ) I= (∑i ∑ j Wi . Lembo. Jr.

Lembo.0 – When autocorrelation is high. the coefficient is high – A high I value indicates positive autocorrelation © Arthur J. j ( X i − X )( X j − X ) (∑i ∑ j Wi . it varies between – 1. Jr. Salisbury University 5 . j )∑i ( X i − X ) 2 Where N is the number of cases Xi is the variable value at a particular location Xj is the variable value at another location X is the mean of the variable Wij is a weight applied to the comparison between location i and location j © Arthur J. the interaction receives a weight of 1 – Another option is to make Wij a distance-based weight which is the inverse distance between locations I and j (1/dij) – Compares the sum of the cross-products of values at different locations. two at a time weighted by the inverse of the distance between the locations • Similar to correlation coefficient.Moran’s I I= N ∑i ∑ j Wi .0 and + 1. Jr. Lembo. Salisbury University Moran’s I • Wij is a contiguity matrix – If zone j is adjacent to zone i.

Salisbury University 6 . j = unit unit + d ij mile mile + d ij 5280 5280 + d ij © Arthur J. Lembo. j = Wi . Lembo. Jr.Moran’s I • Problems with weights – Potential for distorted I value. j = Wi . – Wij is normalized by Wi . Salisbury University Testing the Significance • Empirical distribution can be compared to the theoretical distribution by dividing by an estimate of the theoretical standard deviation I − E(I ) Z (I ) = SE(I ) 2 S E ( I ) = SQRT [ N 2 ∑ij wij + 3(∑ij wij ) 2 − N ∑i (∑ j wij ) 2 ( N 2 − 1)(∑ij wij ) 2 ] © Arthur J. Jr.

0091 Z: 1.36 © Arthur J.515 Using Points: Moran’s I: . Salisbury University 7 . Jr.Example of Moran’s I – Per Capita Income in Monroe County Using Polygons: Morans I: .001 Using Points: I: . Salisbury University Example of Moran’s I – Random Variable Using Polygons: Moran’s I: . Jr.66 P: < .12 Z: 65 © Arthur J. Lembo.012 p: . Lembo.

Lembo. whereas the Geary coefficient is more sensitive to differences in small neighborhoods. Lembo. © Arthur J. but the deviations in intensities of each observation location with one another C= [( N − 1)[∑i ∑ j Wij ( X i − X j ) 2 ] 2(∑i ∑ j Wij ( X i − X ) 2 © Arthur J. Jr.Geary’s C • Similar to Moran’s I (Geary. Jr. Salisbury University Geary’s C C= [( N − 1)[∑i ∑ j Wij ( X i − X j ) 2 ] 2(∑i ∑ j Wij ( X i − X ) 2 • Value typically range between 0 and 2 • If value of any one zone are spatially unrelated to any other zone. Salisbury University 8 . rather than the covariation between the pairs. 1954) • Interaction is not the cross-product of the deviations from the mean. the expected value of C will be 1 – Values less than 1 (between 1 and 2) indicate negative spatial autocorrelation • Inversely related to Moran’s I • Does not provide identical inference because it emphasizes the differences in values between pairs of observations. • Moran’s I gives a more global indicator.

Jr.Testing the Significance • Example using Geary’s C Z (C ) = C − E (C ) S E (C ) © Arthur J. Salisbury University 9 . Lembo.

Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

We've moved you to where you read on your other device.

Get the full title to continue

Get the full title to continue listening from where you left off, or restart the preview.

scribd