GIS Spatial Statistics 3

Question 1

Ordinary Kriging differs from Simple Kriging because Ordinary Kriging:

Accepted Answer

Assumes an unknown, locally varying mean estimated from nearby data

Answer

Assumes a fixed, globally known mean across the study area

Answer

Does not require fitting a variogram model to the data

Answer

Is only applicable to categorical or nominal data types

Question 2

In a variogram model, the nugget effect represents:

Accepted Answer

Microscale variation or measurement error at distances approaching zero

Answer

The maximum semivariance reached at large separation distances

Answer

The distance threshold beyond which spatial autocorrelation ceases

Answer

The total variance of the entire sampled dataset

Question 3

The 'range' of a variogram model is defined as:

Accepted Answer

The distance beyond which pairs of points show no spatial autocorrelation

Answer

The maximum semivariance value achieved at the sill

Answer

The minimum required spacing between sample points

Answer

The total geographic extent of the study area

Question 4

Geographically Weighted Regression (GWR) differs from ordinary least squares (OLS) regression in that GWR:

Accepted Answer

Produces regression coefficients that vary spatially across the study area

Answer

Uses only categorical predictor variables in the regression model

Answer

Requires three-dimensional elevation data as an input

Answer

Can only be applied to regular raster grid data

Question 5

The Modifiable Areal Unit Problem (MAUP) in spatial analysis describes:

Accepted Answer

The sensitivity of statistical results to the choice of spatial units used for aggregation

Answer

Errors introduced when converting vector data to raster format

Answer

Inaccuracies in GPS positional data caused by urban canyon effects

Answer

Classification errors in satellite imagery due to mixed pixels

Question 6

A spatial lag model in spatial econometrics is characterized by:

Accepted Answer

Including a spatially weighted average of the dependent variable as a predictor

Answer

Including spatially lagged error terms to model residual autocorrelation

Answer

Applying geographically weighted coefficients at each observation location

Answer

Using ordinary least squares without accounting for spatial dependence

Question 7

Which method is most commonly applied to test for spatial autocorrelation in the residuals of a regression model?

Accepted Answer

Moran's I applied to the regression residuals

Answer

Durbin-Watson test for serial autocorrelation in time series

Answer

Kolmogorov-Smirnov test for distributional normality

Answer

Variance Inflation Factor (VIF) for multicollinearity detection