Geol 430 Exam 3 Ch. 13

Front 1

Why is it important to have user familiarity with spatial analysis techniques and not just the processing functions?

Back 1

The techniques and approaches can be applied beyond geographic space.

Spatial analysis assists in turning raw data into useful information, adding value, supporting decisions, and revealing patterns/anomalies.

Effective spatial analysis requires an intelligent user, not just a powerful computer.

Front 2

Spatial analysis

Back 2

A set of methods whose results change when the locations of the objects being analyzed change.

Front 3

Deductive

Back 3

Refers to an approach that focuses on testing known theories/principles against data

Example: Snow's theory of water-borne cholera miasma

Front 4

Inductive

Back 4

Refers to the approach that examines empirical evidence in search of patterns that might support new theories or general principles.

Example: Mark 1 leukemia study

Front 5

Normative

Back 5

Refers to the approach that applies spatial analysis to develop or prescribe a new or better design

Example: ESRI's business analytics

Front 6

Coastline weave problem

Back 6

Refers to the creation of silvers resulting from two datasets containing the same boundary lines but with minor locational differences from digitizing.

Front 7

What is meant by the spurious polygon problem? What are the underlying reasons? How can this problem be rectified when attempting polygon overlays?

Back 7

Creation of slivers by overlaying polygons.

This problem came about when two datasets containing the same boundary lines have minor locational differences from digitizing.

Tolerance must be used to eliminate the slivers.

Front 8

Metric

Back 8

Rule for determining distances between points

Front 9

What is the difference between 1st and 2nd order cluster processes?

Back 9

1st order process - involves points being located independently, but may still result in clusters because of varying point density.

2nd order process - involves interactions between points, leading to clusters when interactions are attractive in nature and dispersion when they are competitive or repulsive.

Front 10

Interpret a k function output

Back 10

The pattern is random - points are located independently, and all locations are equally likely.

The pattern is clustered - some locations are more likely than others, and the presence of one point may attract others to its vicinity.

The pattern is dispersed - the presence of one point may make others less likely in its vicinity.

Front 11

Kernel function

Back 11

A density surface estimated by an associated length measure and a specific distribution.

Front 12

Thiessen Polygons

Back 12

Method for interpolation that takes the closest actual measurement and universally applies it throughout the polygon of region of proximity.

Limit: Results in sharp breaks between adjacent polygons.

Front 13

IDW

Back 13

Known as Inverse-Distance Weighting, it is a method that interpolates the value as the distance-weighted average value of all proximate points.

Limits: It can only estimate values within the range of proximate measures; Eliminating both peaks and pits can have adverse effects on even flat lowlands by raising them to average.

Front 14

Kriging

Back 14

Theoretically grounded form of spatial interpolation that emphasizes smoothness as the most important property.

Limits: there will always be a measurement error; Requires user input and is not a black box option.

Front 15

Kriging sill

Back 15

The value of difference at the distance beyond which there are no more geographic surprises.

Front 16

What are the differences between interpolation and density surfaces?

Back 16

Interpolation - used for continuous fields where the points represent samples that require interpolation

Density - used for discrete objects where nothing exists between measured objects and the surface produced is only a count per unit area