GEO-SCI591D Spatial Data Analysis

Department of Geosciences

University of Massachusetts - Amherst

3 cr, Spring 2014

Go to class schedule Syllabus in Print version  (PDF)

Course Location:        Lecture Time:   Instructor:    Office hours:

Morrill IV South 159, lab in 271 GIS lab TuTh 2:30PM - 3:45PM Dr. Qian Yu, Morrill IV South 267, qyu@geo.umass.edu MonTh 11:00-12:00pm or by appointment

Purpose: The course covers a broad range of spatial data analysis methods from basic statistics to advanced computational techniques. The topics include point pattern analysis, spatial prediction based on deterministic methods and Geostatistical theory, spatial autocorrelation and regression, and raster analysis. The labs are based on ArcGIS and statistical software.

The goal of this course is to introduce students various quantitative methods, particularly multivariate regression and spatial analysis, used in geographical data and applications; to teach students to understand these concepts and to be able to apply them in geographical problems.

Teaching Format

60% lectures and class discussions, 40% class exercises including computer lab and project.  Take home exercises and lab practice will be assigned to students to get familiar with the concepts discussed in class.

Prerequisite 

- Basic statistical knowledge

- Introductory level GIS and know how to use ArcGIS

References

David O'Sullivan, David J. Unwin, Geographic Information Analysis, Wiley, Inc, Hoboken, New Jersey, ISBN: 978-0-470-28857-3, 2^nd ed, Hardcover, 432 pages, March 2010

Bailey TC, Gatrell AC,  Interactive spatial data analysis. Harlow, Essex, England: Longman, 1995.

Isaaks EH, Srivastava RM, An Introduction to Applied Geostatisitics, Oxford University Press, 1989.

Peter, Rogerson, Statistical methods for Geography, a student’s guide, Sage, 2010.

Lab software: ArcGIS and R.

Course Evaluation: Assignment 40%, Class Participation 10%, Reading and discussion 10%, Project (including presentation and report) 40%

Final Project

All students are required to complete a project either individually or with another student upon instructor’s approval. Students are encouraged to define the objective of your project, collect all necessary data and perform spatial analysis. A final report is due on May 10. Refer to Final Project handout for requirements.

Policies

- Attendance to both lecture and lab is required in the normal circumstances. It is the responsibility of the student to obtain any materials (i.e. notes) from other students in the event the student cannot attend class for some reasons.

- All exercises must be turned in by the date the exercises are due. Any late submission without advance permission by the instructor will cause a grade deduction by half. No exercise will be accepted after one week following the due date.

- Absence of final project presentation will lead to failing the class.

Class schedule and reading

Available at http://www.geo.umass.edu/courses/geo591d/. It will be updated with classes progressing.

Notes, assignments, notices and announcement will be published on the Moodle.

Class arrangement (Tentative)

Week	Class	Arrangement	Topic	Reading
1 Jan 20	Tu	Lecture 1	Concepts in spatial data and models	O'Sullivan's ch1-2
	Th	Lecture 2.1	Point Pattern Analysis: point pattern measure and test	O'Sullivan's ch3-5
2 Jan 27	Tu	Lecture 2.2	Cont…
	Th	Lab 1	Demo: measure geographic distribution
3 Feb 3	Tu	Lab 1, cont…	Point Pattern Test (Average Nearest Neighbor R test, Ripley’s K test)
	Th	Lecture 3	Point Pattern Analysis: Multiple sets of events; space-time clustering
4 Feb 10	Tu	Lecture 4	Exploring spatial continuous data	Bailey's p155-181
	Th		snow day
5 Feb 17	Tu		Monday schedule, no class
	Th		class canceled
6 Feb 24	Tu	Lecture 5.1	Modeling spatial continuous data, variogram and simple kriging	Bailey's p181-201
	Th	Lecture 5.2	Modeling spatial continuous data, extensions of simple kriging, geospatial analyst in ArcGIS	Bailey's p181-201
7 Mar 3	Tu	Lab 2	Variogram exploration and Kriging prediction
	Th	Lecture 6.1	Area objects and spatial autocorrelation,  Moran’s I, Geary’s C	Bailey's p261-291
8 Mar 10	Tu	Lecture 6.2	Cont…
	Th	Lab 3	Area data analysis (demo in class)
9 Mar 17	Spring recess
10 Mar 24	Tu	Lecture 7a Lab 4a	Modelling area data: Generalized Least Square and GWR Lab 4a Geographically weighted regression	Bailey's p261-291
	Th	Lecture 7b Lab 4b	Modelling area data: Spatial autoregressive models Lab 4b Spatial regression model: Spatial lag model and spatial error model
11 Mar 31	Tu	Special topic 1	Introduce Model Builder
	Th	Special topic 2	Iteration in Model Builder
12 Apr 7	Tu		AAG conference, no class
	Th		AAG conference, no class
13 Apr 14	Tu		Graduate Paper presentation
	Th	Special topic 3	Geocoding and Working with Census data
14 Apr 21	Tu	Special topic 4	Network analysis
	Th		Work on final project
15 Apr 28	Tu		Final project presentation
May 10			Final project report due