Instructor: Tony
E. Smith
274 Towne (898-9647)
tesmith@seas.upenn.edu
Office Hours: By Appointment
Instructor: Tony
E. Smith
|
|
There are no exams in this course. Grading is based entirely on the seven homework assignments. Each assignment is weighted equally in the final evaluation. But in "border-line" cases for final grades, I do look for improvement over the semester.
| Lectures | Day/Date | Topic | Homework |
| INTRO | Th/Jan.12 | Introduction | |
| 1 | Tu/Jan.17 | Point Pattern Data | |
| 2 | Th/Jan.19 | CSR Hypothesis | |
| 3 | Tu/Jan.24 | Nearest-Neighbor Methods | |
| 4 | Th/Jan.26 | Data Applications | PS1 due |
| 5 | Tu/Jan. 31. | K-Function Analysis | |
| 6 | Th/Feb.2 | Simulation Testing Methods | |
| 7 | Tu/Feb.7 | Bivariate K-Functions | |
| 8 | Th/Feb.9 | Tests of Pattern Similarity | |
| 9 | Tu/Feb.14 | Local K-Functions | PS2 due |
| 10 | Th/Feb.16 | Continuous Spatial Data | |
| 11 | Tu/Feb.21 | Spatial Variograms | |
| 12 | Th/Feb.23 | Variogram Estimation | |
| 13 | Tu./Feb. 28 | Simple Kriging Model | |
| 14 | Th/Mar.1 | Kriging Predictions | PS3 due |
| Tu/Mar. 6 | SPRING BREAK | ||
| Th/Mar. 8 | SPRING BREAK |
||
| 15 |
Tu/Mar.13 | Simple Regression Model | |
| 16 |
Th/Mar.15 | Generalized Least Squares | |
| 17 |
Tu/Mar. 20 | Universal Kriging Model | |
| 18 | Th/Mar. 22 | Universal Kriging Estimation | |
| 19 | Tu/Mar. 27 | Data Applications | PS4 due |
| 20 | Th/Mar. 29 | Data Applications | |
| 21 | Tu/Apr. 3 | Regional Spatial Data | |
| 22 | Th/Apr.5 | Spatial Autocorrelation | |
| 23 | Tu/Apr.10 | Spatial Concentration | PS5 due |
| 24 | Th/Apr.12 | Spatial Autoregression | |
| 25 | Tu/Apr.17 | Spatial Lag Model | |
| 26 | Th/Apr.19 | Spatial Diagnostics | |
| 27 | Tu/Apr.24 | Additional Regression Topics | PS6 due |
| PS7 | Mon/May 7 | Last Assignment | PS7 due |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Assignment 7 |
Using
LeSage Models. This gives a
brief introduction to the package of MATLAB
programs available on Jim Lesage's
web site.
ArcView 10 Manual. This manual, written by Amy
Hillier, provides a
brief
introduction to some of the
more useful procedures
in ArcView 10.
Using
MATHTYPE.
These notes show you how to access MATHTYPE in
WORD, and use it to write both mathematical
equations
and in-line expresssions in your reports.
Matrix Regression.
These slides give an introduction to
MATRIX ALGEBRA
in the context of MULTILE REGRESSION
CML
Data and Maps. This
is a set of instructions on how to download data sets
and map shapefiles from the Neighborhood
Information
System (NIS) in the Cartographic Modeling Lab
(CML).
Reference Materials.
This is a secure site containing
additional reference materials
for the course that are copyrighted.
Lab Data Access.
These notes are intended for those students who do not have
a class account, but would still like to access the class data sets and
use the software in the lab.
Remote Data Access.
These notes are intended for those
students who have access to
the
ARCMAP, JMP, and MATLAB software elsewhere, and
want to access the class data
sets from this remote location.
PENN CAMPUS RESOURCES
http://data.library.upenn.edu/index.html
http://www.library.upenn.edu/vanpelt/infofile/cdfram2.html
http://www.library.upenn.edu/lippincott/cdroms.html
http://www.cml.upenn.edu/
GENERAL SPATIAL DATA RESOURCES
http://www.geographynetwork.com/data/index.html
http://www.census.gov/geo/www/cob/index.html
http://www.dcrp.ced.berkeley.edu/research/footprint
http://fisher.lib.virginia.edu/index.html
http://www.gisdatadepot.com/
http://gis.about.com/
http://www.esri.com/data/download/index.html
http://www.maproom.psu.edu/dcw/
http://www.lib.ncsu.edu/stacks/gis/dcw.html
http://www.fedstats.gov/mapstats/
http://factfinder.census.gov/servlet/BasicFactsServlet
http://homer.ssd.census.gov/cdrom/lookup
http://www.nationalgeographic.com/maps/
http://nationalatlas.gov/natlas/natlasstart.asp
http://www3.cancer.gov/atlasplus/
http://www.csiss.org/clearinghouse/select-tools.php3
http://hope.hss.cmu.edu/(TrafficSTATS)
I. SPATIAL POINT PATTERN ANALYSIS
1.
Examples of Point Patterns
1.1 Clustering
versus Uniformity
1.2 Comparisons
between Point
Patterns
2.
Complete Spatial Randomness
2.1 Spatial Laplace Principle
2.2 Complete Spatial Randomness
2.3 Poisson Approximation
2.4 Generalized Spatial Randomness
2.5 Spatial Stationarity
3.
Testing Spatial Randomness
3.1 Quadrat Method
3.2 Nearest-Neighbor
Methods
3.2.1 Nearest-Neighbor Distribution under CSR
3.2.2 Clark-Evens Test
3.3 Redwood Seedling
Example
3.3.1 Analysis of Redwood Seedlings using JMPIN
3.3.2 Analysis of Redwood
Seedlings using MATLAB
3.4 Bodmin Tors Example
3.5 A Direct Monte
Carlo Test of CSR
4. K-Function Analysis of Point
Patterns
4.1 Wolf-Pack
Example
4.2 K-Function Representations
4.3 Estimation of K-Functions
4.4 Testing the CSR Hypothesis
4.5 Bodmin Tors Example
4.6 Monte Carlo Testing Procedures
4.6.1 Simulation Envelopes
4.6.2 Full P-Value Approach
4.7 Nonhomogeneous CSR Hypotheses
4.7.1 Housing Abandonment Example
4.7.2 Monte Carlo Tests of Hypotheses
4.7.3 Lung Cancer Example
4.8 Nonhomogeneous CSR Hypotheses
4.8.1 Construction of Local K-Functions
4.8.2 Local Tests of Homogeneous CSR Hypotheses
4.8.3 Local Tests of
Nonhomogeneous CSR Hypotheses
5. Comparative Analyses of Point Patterns
5.1 Forest
Example
5.2 Cross K-Functions
5.3 Estimation
of Cross K-Functions
5.4 Spatial Independence Hypothesis
5.5 Random-Shift
Approach to Spatial Independence
5.5.1 Spatial Independence Hypothesis for Random Shifts
5.5.2 Problem of Edge Effects
5.5.3 Random Shift Test
5.5.4 Application to the Forest Example
5.6 Random-Labeling Approach to Spatial Independence
5.6.1 Spatial Indistinguishability Hypothesis
5.6.2 Random Labeling Test
5.6 3 Application to the
Forest Example
5.7 Analysis of
Spatial Similarity
5.7.1 Spatial Similarity Test
5.7.2 Application to the
Forest Example
5.8 Larynx and
Lung Cancer Example
5.8.1 Overall Comparison of the Larynx and Lung Cancer Populations
5.8.2 Local Comparison in the Vacinity of the Incinerator
5.8.3 Local Cluster Analysis of Larynx Cases
II. CONTINUOUS SPATIAL DATA ANALYSIS
1. Overview of Spatial Stochastic Processes
1.1 Standard Notation
1.2 Basic Modeling
Framework
2.
Examples of Continuous Spatial Data
2.1 Rainfall in the Sudan
2.2 Spatial Concentration of PCBs
3. Spatially-Dependent Random Effects
3.1 Random Effects at a Single Location
3.1.1 Standardized Random Variables
3.1.2 Normal Distribution
3.1.3 Central Limit Theorems
3.1.4 CLT for the Sample Mean
3.2 Multi-Location Random Effects
3.2.1 Multivariate Normal Distribution
3.2.2 Linear Invariance Property
3.2.3 Multivariate Central Limit Theorem
3.3 Spatial Stationarity
3.3.1 Example: Measuring Ocean Depths
3.3.2 Covariance Stationarity
3.3.3 Covariograms and Correlograms
4.1 Expected Squared Differences
4.2 The Standard Model of Spatial Dependence
4.3 Non-Standard Spatial Dependence
4.4 Pure Spatial Dependence
4.5 The Combined Model
4.6 Explicit Models of Variograms
4.6.1 The Spherical Model
4.6.2 The Exponential Model
4.6.3 The Wave Model
4.7 Fitting Variogram Models to Data
4.7.1 Empirical Variograms
4.7.2 Least-Squares Fitting Procedure
4.8 The Constant-Mean Model
4.9 Example: Nickel Deposits on Vanvouver Island
4.9.1 Empirical Variogram Estimation
4.9.2 Fitting a Spherical Variogram
4.10 Variograms versus Covariograms
4.10.1 Biasedness of the Standard Covariance Estimator
4.10.2 Unbiasedness of Empirical Variogram for Exact-Distance Samples
4.10.3 Approximate Unbiasedness of General Empirical Variograms
5. Spatial Interpolation Models
5.1 A Simple Example of Spatial Interpolation
5.2 Kernel Smoothing Models
5.3 Local Polynomial Models
5.4 Radial Basis Function Models
5.5 Spline Models
5.6 A Comparison of Models using the Nickel Data
6. Simple Spatial Prediction Models
6.1 An Overview of Kriging Models
6.1.1 Best Linear Unbiased Predictors
6.1.2 Model Comparisons
6.2 The Simple Kriging Model
6.2.1 Simple Kriging with One Predictor
6.2.2 Simple Kriging with Many Predictors
6.2.3 Interpretation of Prediction Weights
6.2.4 Construction of Prediction Intervals
6.2.5 Implementation of Simple Kriging Models
6.2.6 An Example of Simple Kriging
6.3 The Ordinary Kriging Model
6.3.1 Best Linear Unbiased Estimation of the Mean
6.3.2 Best Linear Unbiased Predictor of Y
6.3.3 Implementation of Ordinary Kriging
6.3.4 An Example of Ordinary Kriging
6.4 Selection of Prediction Sets by Cross Validation
6.4.1 Log-Nickel Example
6.4.2 A Simulated Example
7. General Spatial Prediction Models
7.1 The General Linear Regression Models
7.1.1 Generalized Least Squares Estimation
7.1.2 Best Linear Unbiasedness Property
7.2 The Universal Kriging Model
7.2.1 Best Linear Unbiased Prediction
7.2.2 Standard Error of Predictions
7.2.3 Implementation of Univesal Kriging
7.3 Geostatistical Regression and Kriging
7.3.1 Iterative Estimation Procedure
7.3.2 Implementation of Geostatistical Regression
7.3.3 Implementation of Geostatistical Kriging
1. Covariograms for Sums of Independent Spatial Processes
2 . Expectation of the Sample Estimator under Sample Dependence
3 . A Bound on the Binning Bias of Empirical Variogram Estimators
4. Some Basic Vector Geometry
5 . Differentiation of Functions
6 . Gradient Vectors
7 . Unconstrained Optimization of Smooth Functions
7.1 First-Order Conditions
7.2 Second-Order Conditions
7.3 Application to Ordinary Least Squares Estimation
8 . Constrained Optimization of Smooth Functions
8.1 Minimization with a Single Constraint
8.2 Minimization with Multiple Constraints
8.3 Solution for Universal Kriging
III. AREAL DATA ANALYSIS
IV. SOFTWARE
1. ARCMAP
1.2.1 Importing Text
Files to
ARCMAP
1.2.2 Changing Path
Directories
in Map Documents
1.2.3 Making a Column
of Row
Numbers in an Attribute Table
1.2.4 Masking in ARCMAP
1.2.5 Making Spline Contours in Spatial Analyst
1.2.6 Excluding Values
from
Map
Displays
1.2.7 Importing ARCMAP
Images
to
the Web
1.2.8 Adding Areas to
Map
Polygons
1.2.9 Adding Centroids to Map Polygons
1.2.11 Converting Strings to Numbers in ARCMAP
1.2.12 Displaying Proper Distance Units
1.2.14 Exporting Maps from ARCMAP to WORD
1.2.15 Making Legends for Exported Maps
1.2.16 Making Voronoi Tessellations in ARCMAP as Shapefiles
1.2.17 Running Local G* Tests of Concentration in ARCMAP
1.2.18 Joining Point Date to Polygon Shapefiles in ARCMAP
1.2.19 Saving Map Documents with Relative Paths
1.2.20 Increasing Unique Values for Editing Raster Outputs (in Version 9.3)
2. JMPIN
2.2.1 Printing Results from
JMP
2.2.2 Making a Random
Reordering
of Row Numbers
3. MATLAB
3.1 Opening MATLAB
3.2 Tips for using MATLAB
3.2.1 Exporting
Graphics from MATLAB to WORD
3.2.2 Making Boundary-Share
Weight Matrices in MATLAB
3.2.3