Special Topics in Geo-Business Data Analysis - PowerPoint PPT Presentation

Loading...

PPT – Special Topics in Geo-Business Data Analysis PowerPoint presentation | free to download - id: 21cf98-ZDc1Z



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

Special Topics in Geo-Business Data Analysis

Description:

Special Topics in Geo-Business Data Analysis. Week 3 Covering Topic 6. Spatial Interpolation ... Pockets of unusually high customer density are identified as more ... – PowerPoint PPT presentation

Number of Views:13
Avg rating:3.0/5.0
Slides: 17
Provided by: Jos956
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Special Topics in Geo-Business Data Analysis


1
Special Topics in Geo-Business Data Analysis
Week 3 Covering Topic 6 Spatial Interpolation
2
Point Density Analysis
Point Density analysis identifies the number of
customers with a specified distance of each grid
location
(Berry)
3
Identifying Unusually High Density
Pockets of unusually high customer density are
identified as more than one standard deviation
above the mean
(Berry)
4
Identifying Customer Territories
Clustering on the latitude and longitude
coordinates of point locations identify customer
territories
(Berry)
5
Map View vs. Data View
Mapped data are characterized by their geographic
distribution (maps on the left) and their
numeric distribution (descriptive statistics and
histogram on the right)
Geographic Distribution
Numeric Distribution
(Berry)
6
Estimating the Geographic Distribution
The spatial distribution implied by a set of
discrete sample points can be estimated by
iterative smoothing of the point values
(Berry)
7
Spatial Autocorrelation (Variogram)
A variogram plot depicts the relationship
between distance and measurement similarity
(spatial autocorrelation)
nearby things are more alike than distant
things
(Berry)
8
Spatial Interpolation Mechanics
Spatial interpolation involves fitting a
continuous surface to sample points
Roving Window (average)
(Berry)
9
Inverse Distance Weighted Technique
Inverse distance weighted interpolation
weight-averages sample values within a roving
window
(Berry)
10
Example Calculations (IDW)
Example Calculations for Inverse Distance Squared
Interpolation
11
16
15
14
(Berry)
11
Title
A wizard interface guides a user through the
necessary steps for interpolating sample data
MapCalc Spatial Interpolation Wizard
(Berry)
12
Comparing Geographic Distributions (IDW vs. Avg)
Spatial comparison of the project area average
and the IDW interpolated surface
(Berry)
13
Comparison Statistics (IDW vs. Avg)
Statistics summarizing the difference between the
IDW surface and the Average
big difference more than 75 of the project
area is more than /- 10 units different
(Berry)
14
Comparing Geographic Distributions (IDW vs Krig)
Spatial comparison of IDW and Krig interpolated
surfaces
(Berry)
15
Evaluating Interpolation Performance
A residual analysis table identifies the relative
performance of average, IDW and Krig estimates
(Berry)
16
Mapping Spatial Dependency
Spatial dependency in continuously mapped data
involves summarizing the data values within a
roving window that is moved throughout a map
compares the difference in values between the
adjacent neighbors (doughnut hole) and distant
neighbors (doughnut), assigns the spatial
dependency index to the center cell location then
moves to next location
(Berry)
About PowerShow.com