GEOG 586 Syllabus

Geographic Information Analysis

Spring 2023

This syllabus is divided into several sections. You can read it sequentially by scrolling down the length of the document. It is essential that you read the entire document as well as material covered in the Course Orientation. Together, these serve as our course "contract."

Instructors

Spring 1, 2023, Section 001: January - March

Marcela Suarez
College of Earth and Mineral Sciences
The Pennsylvania State University

• Email: Please use the Canvas Inbox to send messages to the instructor
• Office Hours: By appointment

Spring 1, 2023, Section 002: January - March

Amy Griffin
College of Earth and Mineral Sciences
The Pennsylvania State University

• Email: Please use the Canvas Inbox to send messages to the instructor
• Office Hours: By appointment

Spring 2, 2023: February - May

Amy C. Burnicki, Associate Teaching Professor
Penn State Department of Geography

John A. Dutton e-Education Institute
2217 Earth and Engineering Sciences
College of Earth and Mineral Sciences, Penn State
University Park, PA 16802

• Email: Please use the Canvas Inbox to send messages to the instructor
• Office Hours: By appointment

NOTE: Instructors will read and respond to email and discussion forums at least once per day during the work week (Monday through Friday). You may also see us online occasionally on the weekends.

Class Support Services

Penn State Online offers online tutoring to World Campus students in math, writing, and some business classes. Tutoring and guided study groups for residential students are available through Penn State Learning.

Course Overview

Prerequisite: GEOG 485 or GEOG 486 or GEOG 487 or equivalent experience

Geography 586 is a required course in the Penn State Professional Masters in Geographic Information Systems. This section is being offered to students around the globe through Penn State's World Campus. It is a "paced" course, which means that there are established start and end dates and that you will interact with other students throughout the course. The course is 10 weeks in length (plus a required "Orientation Week"), at a rate of 1 lesson per week. The course is organized around six short weekly projects (due in weeks 1, 2, 3, 4, 6 and 7) and a more substantial term project pursued through all ten weeks of the course. Weekly projects include associated readings, quizzes, and discussions about the analysis of spatial data.

This is a course in analytical methods for handling spatial data analysis. The techniques introduced are often mathematically complex, but while these aspects are covered in the course, the emphasis is on the choice and application of appropriate methods for the analysis of the spatial data often encountered in applied geography.

Weekly projects are hands-on, using geographic information systems or other appropriate computational tools, so that students appreciate the practical complexities involved, and the relative limitations of these methods in contemporary desktop GIS. Each week, students acquire familiarity with the use of a single method or family of methods in standard desktop tools, so that they can focus on aspects of that method and develop a thorough understanding of its limitations and application. Problem scenarios range across demographic, planning, crime analysis, landscape analysis, and other application areas.

The term project is intended to allow students to formulate a research problem in a topic area of their own choosing, to gather and organize appropriate available datasets, and to understand how a variety of methods among those covered in the course can be applied in combination to thoroughly explore real questions. Students will be asked to engage with their peers' work during the project planning stage. Students with previous programming experience should consider developing customized tools to automate repetitive analysis tasks to enhance efficiency.

Throughout this course, there is a strong emphasis on the theory behind the methods you will be applying to help you understand which methods are appropriate and when. This is particularly important when deciding on the method to use since this may actually determine which GIS package you will use to tackle a given problem (because not all methods are supported by all GIS programs). Almost all the theory you need for the course is covered in the course text, supported by supplementary notes, readings, and commentary during the weekly lessons. This book covers considerably more material than we could ever get through in the 10 weeks of this course, but should serve as an important resource both now and in the future.

The general format each week is:

1. First, I will provide you with an overview of the lesson, which typically includes an introduction, lesson learning objectives, textbook reading assignments, and an outline of the deliverables for the lesson (i.e., things you need to submit by the end of that week).
2. Next, I will provide some commentary for the lesson, which you should read once you have completed the textbook reading assignments for the lesson. Think of the commentary as the "lecture notes" for the lesson. There, I will expand on the information covered in the readings, try to clarify any information you might find troublesome, and will link to additional information. You may find that it helps to read these notes before tackling the textbook reading—so that you have an idea of what to focus on.
3. Once you have read the textbook assignments and the commentary, you will complete a self-test quiz or discussion designed to help you assess your comprehension of the material. You have an unlimited number of attempts on each quiz and must score 90% or more.
4. Finally, I will wrap up each lesson with "Final Activities"—specific instructions for the lesson activities and/or how to submit the lesson deliverables.
5. Term project: In addition to these activities, a term project is required of you to complete the course. This is a more substantial piece of work, where you are expected to apply ideas and methods learned in the course. By prior agreement with me, ideas and methods not explicitly covered in the course, but which fall under the description 'spatial analysis,' may also be used. Each week, there are deadlines in the term project to keep you on track, so that you work consistently on the project throughout the term rather than leaving it all to the last minute. More details of the term project are provided on the Project Overview page.

Using the Lessons link in the menu bar above, you can navigate to any lesson in the course. From there, you can also access each page within the lesson. Each is clearly titled.

Each week, since course weeks run from Wednesday to the following Tuesday, I strongly advise that you aim to complete the reading and quiz (or quizzes) by Friday or Saturday so that you have plenty of time to tackle the weekly project and submit it by the Tuesday night deadline.

Discussion forums have been provided for students (you) and the instructor (me) to share comments, pose questions, and suggest answers. I strongly encourage you to get in the habit of checking this regularly. In an online course, this is particularly important to give everyone a sense of involvement with the course. It is also worth 5% of the final credit. I assign participation grades based on both the quantity and quality of your contributions to discussion, with quality being more important than quantity. Comments that explore ideas and help your fellow students grow in their understanding are valued more highly than simply stating 'I agree'. Posing questions about things you feel you do not fully understand is also a valued form of participation. You can be sure that if you are puzzling over something, other students likely are too, and by working together, you will collectively improve your understanding of the material.

We have worked hard to make this the most effective and convenient educational experience possible. How much and how well you learn is ultimately up to you. You will succeed if you are diligent about keeping up with the class schedule and if you take advantage of opportunities to communicate with me, as well as with your fellow students.

This course requires a minimum of 8-12 hours of student activity each week, depending on the speed at which you work. Included in the 8-12 hours each week is time to complete projects and related activities. Some weeks, you may spend less time than that, so keep this in mind in the tougher weeks (when you'll be making up the difference!). You'll be glad to know that you don't have to show up for class at a certain time! All you need to do is complete each project and a quiz before the published deadline at the end of the course week.

... And what you can expect from me (the course instructor).

I have to be organized in much the same way that you are in order to teach the course. I aim to answer any specific queries about the readings and commentary within 24 hours, unless otherwise indicated in course announcements, particularly relating to times when I am travelling during the term (which I do). If you are really stuck then also send me an email.

My answers may not always be direct - if it seems to me that you are relying too heavily on answers from me and others rather than on careful reading and your own efforts. I also won't answer questions that are rephrasings of the quiz questions! However, feel free to post questions about the quiz questions on the forums to see what others are thinking and initiate discussions.

Required Course Materials

In order to take this course, you need to have the required course materials listed below. All (other) materials needed for this course are presented online through Canvas. In order to access the online materials, you need to have an active Penn State Access Account user ID and password (used to access the online course resources). If you have any questions about obtaining or activating your Penn State Access Account, please contact Penn State IT Service Desk for World Campus students or Penn State IT Get Support (for students at all other campus locations).

You will need to purchase course materials from MBS Direct (the bookstore used by Penn State's World Campus) or another bookstore, such as Amazon. For MBS pricing and ordering information, please see MBS Direct. MBS Direct can also be contacted at 1-800-325-3252. Materials will be available at MBS Direct approximately three weeks before the course begins. Be sure to order early enough to allow for shipping and installation prior to the course start date

Textbook: The required textbook is:

Lloyd, Christopher D. 2011, Local Models for Spatial Analysis, Second Edition. (CRC Press, Boca Rotan, FL). ISBN 978-1-4398-2919-6.  

This text may be purchased from your preferred vendor and is available as an E-Book Option. An online version of this text will be available at no cost as a Penn State Library E-Book. You can access the E-Book through the Library Resources link in the course navigation in Canvas. Some E-Books will be available only online, while others will be available to download in full or in part. If available, the E-Book may be used as an alternative to purchasing a physical copy of the text. For questions or issues, you can contact the University Libraries Reserve Help (UL-RESERVESHELP@LISTS.PSU.EDU).

Software: You will also need to have access to the following:

• R Studio and R the free statistical analysis software package.
• GeoDa, free exploratory spatial data analysis software available from Chicago University: The Center for Spatial Data Science. Once at the GeoDa homepage, click on the Software tab to visit the software download page.
• Esri's ArcGIS and/or ArcGISPro that includes the Geostatistical Analyst and Spatial Analyst extension. Make sure you have installed ArcGIS Pro 3.0.3 or later. There is a bug in version 2.9 that will cause you drama with some of the lessons if you don't upgrade. If you have an existing install, you can upgrade the software in Project > About. If you don't have an existing install, the best way to request access to the software is to visit GIS @ Penn State. NOTE: ArcGIS is a commercial software package that is restricted to personal use by the student. It is unlawful for anyone to use this software package without the appropriate commercial license from Esri Inc. to generate personal or corporate profit or revenue.
• the required course website that contains the online lessons and communications tools, such as message boards and an email system.
• Zoom: available through Penn State

Additional recommended texts:

Additional resources will be introduced during the relevant lessons each week.

Additional Statistics books. These are all useful in different ways. One stats book will not cover all the information you need. As you use stats you will find yourself dipping in and out of different resources. Find a resource that you find useful.

• Tector, P. 2011. R Cookbook
• Kassambara, A. 2013. gglots2: Guide to Create Beautiful Graphics in R
• Crawley, M. J., 2013 The R book. Second Edition.
• Wickham, H. and Grolemund, G 2017. R for Data Science
• Bruce, P. and Bruce A. Practical Statistics for Data Scientists: 50 essential concepts
• RStudio. 2018. R Markdown
• RStudio. 2018. Shiny

Assistance with Textbooks:

Penn State honors and values the socioeconomic diversity of our students. If you require assistance with the costs of textbooks for this course, contact the Office of Student Care and Advocacy, 120 Boucke Building, 863-4926. For additional needs related to socioeconomic status please visit Project Cahir.

Assignments and Grading

Your course grade will be based on four components:

• Weekly Quizzes - 20% of course grade. This means that each quiz is worth about 2% of the final course credit. Note that the primary purpose of the quizzes is to encourage you to do the reading and and to test your knowledge. Weekly quizzes must be completed by the stated deadline. Any quiz that you fail to complete by the stated deadline will count for 0. Each quiz is treated as equal value. Deadlines will be rigidly applied: Canvas will not allow you to submit results after the deadline.
• 6 Weekly Project activities - 45% of grade (7.5% each):
  • Week 1: Spatial Analysis and why it is special: Exploring the Modifiable Area Unit Problem.
  • Week 2: Geospatial Data Science and Analysis: integrating the two and understanding what is in your data. An exercise using R and applying descriptive statistics.
  • Week 3: Geospatial Data Science and Spatial Statistical Analysis: Point Patterns and why statistical analysis is important for quantifying what you see. An exercise using R to examine crime in St Louis using point pattern analysis.
  • Week 4: Cluster Analysis & Spatial Autocorrelation: An exercise applying spatial autocorrelation measures to assessing ethnic segregation in Auckland, New Zealand using GeoDa.
  • Week 6: Interpolation Methods simple to advanced: Practical experience with interpolation methods so that you develop a feel for the characteristics of the surfaces produced by different methods using ArcGIS/ArcGIS Pro.
  • Week 7: Surface Analysis: Using surface analysis to determine potential sites for a new school in the Centre County region of Pennsylvania (around Penn State). This will show how complex analysis tasks can be performed by combining results from a series of relatively simple analysis steps using ArcGIS /ArcGIS Pro.
• Weekly projects must be submitted by the stated deadline. Please see each week's rubric for details on the possible points and further guidance on the lesson expectations.

When submitting each project, you should use the drop box supplied in that week's lesson materials. You may submit in either PDF or Word doc formats.

• 1 Term Project - 30% of grade: Throughout this course, a major ongoing activity is a personal GIS project that you will develop and research on your own (with lots of input from everyone else taking the course!). This is a more substantial piece of work than the weekly projects, where you are expected to apply concepts learned in the course. By prior agreement with me, ideas and methods not explicitly covered in the course, but which fall under the description 'spatial analysis' may also be used. Many students enrolled in the MGIS program find this project to be a great opportunity to explore an idea for their capstone project. You should expect to work on different activities in the term-long project each week. This is designed to keep you on track, so that you work consistently on the project throughout the term rather than leaving it all to the last minute. Waiting until the last minute is never a good practice in spatial statistics.

The 30% credit available will be divided as follows:

• post topic ideas (week 1)
• develop a project proposal (week 2)
• organize interactive peer-review time and date with your group (week 3)
• peer review feedback for project proposal (week 5)
• refine and submit a final project proposal (week 6)
• final project is due at the end of week 9
• discussions of final projects (week 10)

Items in the term project will have drop-boxes and deadlines will be rigidly enforced by the Canvas course management system.

• Participation - 5% of course grade: Class participation is expected throughout the course on discussion forums and in feedback to other students. In addition to participation in weekly discussion forums, your thoughts and reactions to the article on multiple regression analysis in Week 5 contributes to your participation grade. Because you get points assigned directly for peer review discussions about the term-long project, your participation in them is not considered directly in this component of your grade.

While posting questions is considered participation, you should also try to help others out with their questions. Consistently constructive input will be the most valued and beneficial.

• Late Submission - Each late submission is subject to a late penalty.

Letter grades will be based on the following percentages:

Percentages refer to the proportion of all possible points earned by the student.

Final overall grades may be determined based on relative performance of all students, and not on a fixed points basis, especially if overall percentages are too high or too low.

GEOG 586 Course Schedule

Printable Schedule

Below, you will find a summary of the primary learning activities for this course and the associated time frames. This course is ten weeks in length, with an orientation week preceding the official start of the course. See our Calendar in Canvas for specific lesson time frames and assignment due dates.

GEOG 586 Schedule

Week / Lesson	Course Objectives	Assignments and Activities
Week 0 Course Orientation	Articulate your own course expectations as a student in GEOG 586. Understand the expectations we have of you as a student in GEOG 586. Locate key information about the course, including assignments, due dates, technical information, places to get help, and course policies. Become familiar with the library and materials available to you as a Penn State Student. Understand the rules and regulations regarding Academic Integrity and plagiarism at Penn State. Understand how to communicate in this course environment.	Please post a brief personal introduction to the "Introductions" discussion forum and then review those your peers have posted to learn more about them. Term Project: Familiarize yourself with the schedule for the term-long project.
Week 1 Why spatial data is special	List four major problems in the statistical analysis of geographic information: autocorrelation, the modifiable areal unit problem, scale dependence, edge effects. Outline the concepts of distance, adjacency, interaction, and neighborhood, and show how these can be recorded using matrices. Explain how proximity polygons and Delaunay triangulation are developed for point objects, and relate this technique to concepts of distance, adjacency, interaction, and neighborhood. Explain how point data sets can be converted into a set of areal units using proximity polygons. Describe how a set of areal units can be converted into a set of point data by assignment of values to centroids. Outline how point data may be converted to field data by density estimation.	Complete the self-test quiz satisfactorily (you have an unlimited number of attempts and must score 90% or more). Weekly Project: Complete Project 1 activities. Term Project: Familiarize yourself with the schedule for the term project and post a topic idea.
Week 2 Geospatial Data Analysis: Dealing with data	Explain spatial and statistics data analysis, concepts and how the two are integrated. Understand how the research framework works and will be applied. Understand data types and why spatial data is special. Explain basic concepts in inferential statistics including descriptive statistics, and samples and populations. Practice creating visualizations, summarizing data and presenting information.	Complete the self-test quiz satisfactorily (must score 90% or more). Weekly Project: Complete Project 2 activities. Term Project: Provide a project proposal outline.
Week 3 Point Pattern analysis and why statistical analysis is important	Describe and provide examples of simple deterministic and stochastic spatial processes. List the two basic assumptions of the independent random process (i.e., no first or second order effects). Outline how the idea of a stochastic process might be applied to the line, area, and field objects. Define point pattern analysis and list the conditions necessary for it to work well. Explain how quadrat analysis of a point pattern is performed and distinguish between quadrat census and quadrat sampling methods. Discuss relevant factors in determining an appropriate quadrat size for point pattern analysis. Describe in outline kernel density estimation and understand how it transforms point data into a field representation. Describe distance-based measures of point patterns (mean nearest neighbor distance and the G, F, and K functions). Explain how distance-based methods of point pattern measurement are derived from a distance matrix. Describe how the independent random process and expected values of point pattern measures are used to evaluate point patterns and to make statistical statements about point patterns. Explain how Monte Carlo methods are used when analytical results for spatial processes are difficult to derive. Discuss the merits of point pattern analysis versus cluster detection, and outline the issues involved in real-world applications of these methods.	Complete the self-test quiz satisfactorily (must score 90% or more). Weekly Project: Complete Project 3 activities. Term Project: Organize peer-review session with your group.
Week 4 Cluster Analysis & Spatial Autocorrelation	Define spatial autocorrelation with reference to Tobler's 'first law' of geography and distinguish between first and second order effects in a spatial distribution. Differentiate between isotropic and anisotropic spatial distributions. Justify, compute, and test the significance of the joins count statistic for a pattern of area objects. Compute Moran's I and Geary's C for a pattern of attribute data measured on interval or ratio scales. Explain the importance of spatial weights matrices to the development of autocorrelation measures and variations of the approach, particularly lagged autocorrelation. Explain how autocorrelation measures can be generalized to compute and map Local Indices of Spatial Association (LISA). Describe how Monte Carlo methods may be used to determine significance for LISA.	Complete the self-test quizzes satisfactorily (must score 90% or more). Weekly Project: Complete Project 4 activities. Term Project: Refine Project Proposal.
Week 5 Regression Analysis	Perform descriptive statistics on data to determine if your variables meet the assumptions of regression. Test data variables for normality. Understand how correlation analysis can help you to understand relationships between variables. Create scatterplots to view relationships between variables. Run a regression analysis to generate an overall model of prediction. Interpret the output from a regression analysis. Test the regression model for assumptions.	Complete the self-test quiz satisfactorily (must score 90% or more). Read Paper and post in the Discussion forum. Weekly Project: None. Term Project: Interactive peer-review of proposals in an online forum.
Week 6 Interpolation: Simple to Advanced	Explain the concept of a spatial average and describe different ways of deciding on inclusion in a spatial average. Describe how spatial averages are refined by inverse distance weighting methods. Outline the basis of interpolation by spline-fitting, or piece-wise polynomial fitting. Explain why the above interpolation methods are somewhat arbitrary and must be treated with caution. Show how regression can be developed on spatial coordinates to produce the geographical technique known as trend surface analysis. Explain how a variogram cloud plot is constructed and, informally, show how it sheds light on spatial dependence in a dataset. Outline how a model for the semi-variogram is used in kriging and list variations on the approach. Make a rational choice when interpolating field data between inverse distance weighting, trend surface analysis, and geostatistical interpolation by kriging. Explain the conceptual difference between interpolation and density estimation.	Complete the self-test quiz satisfactorily (must score 90% or more). Weekly Project: Complete Project 6 activities. Term Project: A revised (final) project proposal for the term project is due this week.
Week 7 Surface Analysis	Describe data models for field data: regular grid, triangulated irregular network, closed-form mathematical function, control points; and discuss how the choice of model may affect the subsequent analysis. Explain the map algebra concept and describe focal operations, local operations, and between-map operations. Understand the idea of slope and aspect as a vector field. Explain how slope or gradient can be determined from a grid of height values. Describe how surface aspect may be derived from a grid of height values. Re-express these operations as local operations in map algebra. Describe how map algebra operations can be combined to develop complex functionality.	Complete the self-test quiz satisfactorily (must score 90% or more). Weekly Project: Complete Project 7 activities. Term Project: Continue the work on term project.
Week 8 Overlay analysis	Formally describe Boolean map overlay. Explain how this technique has been widely used in suitability mapping. Understand why co-registration of input maps in the overlay is critical to the success of the analysis. Describe how co-registration is achieved by a combination of translation, rotation, and scaling transformations. Outline how the overlay is implemented in vector and raster GIS. Outline approaches to overlay based on alternative ways of combining layers-additive and indexed schemes, fuzzy methods, and weights of evidence methods. Describe how model-based overlay approaches and regression are related to one another.	Complete the self-test quiz satisfactorily (must score 90% or more). Weekly Project: None. Term Project: Continue with your term-long project.
Week 9 Project work time (no new content this week)	School's out...! Note that there are no other course activities at all this week, to give you plenty of time to work on the completion of the project.	Term Project: Complete the term-long project work and post a report with links to data, maps, charts etc., summarizing project activities and results. Post the final report at the end of this week.
Week 10 Putting it all together: applied research using GIS	Course and project reviews	You are DONE! Well almost. This week's lesson will pull together all that we have learned during the course, by critically and constructively evaluating each other's project work. This is a process we will all participate in using online forums.

Course Policies