Syllabus#

GEOG 172: Intermediate Geographical Data Analysis#

Course Description and Objectives#

This course builds on introductory level probability and statistics, focusing on analysis involving geographical data. There is a lab accompanying the course, requiring the use of statistical software (Python/GeoDa/ArcGIS/QGIS) for analyzing various spatial data types.

Fundamental methods used in quantitative geographic research will be covered. The primary objectives of this course are to:

  1. Introduce students to a range of useful approaches that may be helpful in geographic inquiry;

  2. Detail both theory and use of presented techniques;

  3. Provide a basis for understanding more advanced spatial data analysis methods.


Instructors and Teaching Assistants#

Instructor#

_images/yoda.jpg

Evgeny Noi

Email

noi[at]ucsb.edu

Lectures

MW: 9.30-10.45AM (Ellison 3621)

Office Hours

M: 3.00-5.00PM (Ellison 4829) or by appointment


Teaching Assistants#

_images/prat.jpeg

_images/feifei_zhao.jpg

Pratyush Tripathy

Feifei Zhao

Email

ptripathy[at]ucsb.edu

xiafeizhao[at]ucsb.edu

Labs

M: 5.00-6.50PM

T: 6.00-7.50PM

Lab rooms

Ellison 3620

Ellison 3620

Office hours

M: 12.00-1.00PM
T: 9.45AM-10.45AM

F: 1.00-3.00PM

Office

Ellison 5803

Ellison 4809


Textbook and Learning Resources#

Textbook#

O’Sullivan, D. and D. Unwin (2010). Geographic Information Analysis, 2nd edition (Wiley & Sons).

Supplementray Textbooks#

Python#

Rey, S. J., Arribas-Bel, D., & Wolfe, L. J. (2020). Geographic Data Science with Python. Jupyter Book. https://geographicdata.science/book/intro.html

Tenkanen, H., Heikinheimo, V. V., & Whipp, D. (2021). Introduction to Python for Geographic Data Analysis. Jupyter Book. https://pythongis.org/

GeoDa and ESDA#

Anselin, L. (2020). GeoDa: An Introduction to Spatial Data Science. https://geodacenter.github.io/

Statistics#

Tip

Most O’Reilly books are available through UCBS Library.

Bruce, P., Bruce, A., & Gedeck, P. (2020). Practical statistics for data scientists: 50+ essential concepts using R and Python. O’Reilly Media. PDF

Downey, A. (2014). Think stats: exploratory data analysis. ” O’Reilly Media, Inc.”. PDF

Online Courses and Various Python Resources#

Note

Supplemental readings consisting of journal articles and book chapters may also be assigned via GauchoSpace.


Prerequisites#

Coursework: Statistics and Applied Probability 5AA-ZZ or Ecology, Evolution & Marine Biology 30 or Psychology 5 or Communication 87, or equivalents.

Attention

While this is not a coding class, certain familiarity with programming environment is recommended, but not required. The students should be able to re-use and understand the code given during lectures and labs.


Evaluation / Assessment#

  1. Labs (40%): weekly lab assignments will provide students with practical skills on data processing and analysis. There will be a total of 8 labs in a quarter.

  2. Project (30%): the geographical analysis project will have four deliverables (data report [5%], interim report [5%], presentation [10%], and final report[10%]).

  3. Quizzes (20%): weekly quizzes will be based on lecture material and contain both multiple choice and short answer questions. The lowest quiz will be dropped.

  4. Class participation (10%). Attendance of labs and lectures is required to understand the complex statistical concepts taught in class.


Labs#

The labs will teach you practical skills on how to process and analyze spatial and spatio-temporal data. The labs will utilize Google Colab, which allows writing and executing Python code in your browser with zero configuration. The notebook environment is highly interactive and allows to streamline typical spatial analysis tasks, while also allowing to document your code and present it out-of-the-box.

The labs are held once a week on Monday and Tuesday. The attendance is taken and is counted towards your participation grades.

The labs from the previous week must be submitted before the start of the lab section the following week. The labs must be submitted as exported .ipynb Colab notebook via GauchoSpace dropboxes. For labs conducted in non-Python environment, the format will be detailed in the corresponding lab instructions.

Warning

1% of your total grade will be deducted for each hour late. For instance, for the lab that was submitted 1 day (24 hours) late, 24% will be deducted. Please make sure to contact your TA well in advance if you need an extension on your lab assignments.

Lab

Topic

1

Working with Python, Google Colab and Markdown

2

Basic Statistics. Working with geographic data

3

Choropleth Mapping and Point Pattern Analysis

4

Correlation, Covariance and ANOVA

5

Spatial Autocorrelation

6

Local Spatial Autocorrelation

7

Spatial Regression

8

Spatial Clustering and Regionalization

9

Interpolation. Project Q&A

10

Project Presentations

Tip

If you would like to access lab rooms outside of your lab hours, please contact Patty Murray and fill out Lab Access form, so that your student card is activated to open the lab room.


Project#

The Geographical Analysis Project will provide the students with an opportunity to conduct hands-on analysis of real world data. The students will apply analytical skills acquired during the lectures in practice by generating a series of deliverables typical of on-the-job assignments for GIS Analysts. The projects must be submitted and presented individually.

The project will have four deliverables:

  • Data Report (5%)

  • Interim Progress Report (5%)

  • Presentation (10%)

  • Final Report (10%)

Note

More information will be provided and made available as we get closer to due dates for deliverables.


Quizzes#

The quizzes will be delivered remotely on Thursdays via GauchoSpace. The quiz will open at 8AM and close at midnight. Once you start taking the quiz you will have 30 minutes to complete it. Please make sure that you click ‘submit’ to record your answers after finishing the quiz.


Participation#

Participation in both lectures and labs is crucial for learning new concepts and interactive analytical environment in this course. Please make sure to attend all lectures and labs to get good grades in the course.


Tentative Lecture Schedule#

Wk

Date

Topics

Readings

1

09/26

Introduction/Review of Spatial Analysis

GIA Ch1

1

09/28

Review of Basic Statistics

TBD

2

10/3

Geographic Data

SD

2

10/5

Distance, adjacency and MAUP

GIA Ch2, SD

3

10/10

Geovisualization

GIA Ch3, GDS Choropleth

3

10/12

Point Pattern Analysis

GIA Ch5,6

3

10/16

Data Report Due

⚠️

4

10/17

Inferential Statistics and Hypothesis Testing

Chapters 11 and 12 from Learning Stats with Python

4

10/19

ANOVA

Rogerson (posted in GauchoSpace)

5

10/24

Spatial Autocorrelation 1

GIA Ch7

5

10/26

Spatial Autocorrelation 2

GeoDa Docs

6

10/31

LISA and Local Moran’s $I$

GIA Ch8

6

11/2

Point Pattern Clustering

PPA

7

11/7

Clustering and Regionalization

GDS Chapter 10

7

11/9

Spatial Regression 2

SR

7

11/13

Interim Data Report Due

⚠️

8

11/14

Spatial Clustering/Regionalization 1

CR

8

11/16

Spatial Clustering/Regionalization 2

9

11/21

Spatial Interpolation

GIA Ch9

9

11/23

Geostatistics

GIA Ch10

9

11/27

Presentation slides due

⚠️

10

11/28

Presentations 1

10

11/30

Presentations 2

11

12/7

Final Report Due

⚠️


Academic Integrity#

University Regulation 102.01 establishes academic misconduct as “dishonesty such as cheating, plagiarism, altering graded examinations for additional credit, or having another person take an examination for you.” The policy on academic integrity at UCSB states that “it is expected that all UCSB students will support the ideal of academic integrity and that they will be responsible for the integrity of their work.” See the instructor if you have any questions concerning academic integrity. Sanctions for academic dishonesty include exclusion from the course (i.e. failing the entire course) and referral to the Student-Faculty Committee on Student Conduct.

COVID-19 Policy#

Please refer to the dedicated UCSB COVID-19 response website to get most up-to-date regulations and developments on campus.