EAS XXXX Dealing with Data

Fall 2020
MWF 10:00 to 11:30 AM
Earth Science Building 234

Professor: Dr. Patricia MacQueen

email: [email protected]
Office Hours: Mon/Thurs, 9 to 10 AM, and by appointment

Credits: 4, (graded/sat/unsat/audit)
Pre-reqs: Calculus, Linear Algebra

Course Overview:
Many problems in Earth Science involve messy, incomplete data and experiments we can’t repeat (i.e.,
no, they won’t let us recreate Pangea, it’s just not in the course budget). So what to do? This course
covers a suite of analysis methods commonly used in Earth science that will equip you to get the most
out of your data sets while ensuring that your analysis is valid and supported by the data.

Course Goals:
After completing this course, the student will be able to:
1) Select the proper analysis tools for a given data set and scientific problem.
2) Apply different statistical methods to evaluate whether and how well data support a hypothesis.
3) Explore the signal and noise characteristics of new data sets using digital signal analysis
techniques
4) Critique the validity of data analysis in published papers

Philosophy:
You can learn statistics until you’re blue in the face (not recommended), but it won’t do you any good
unless you had the chance to practice on real data. With that in mind, this course will be 25-50%
lecture, 50-75% in class work and projects. I will give you the information, resources, and help you
need to succeed in this course, but ultimately you are responsible for your own learning. You will learn
by working with real live, real messy data sets, on problems that may or may not have only one right
answer. You will also be working with each other, as you would out in the “real world”. With this in
mind, attendance is important for this class, and you will feel pretty darn silly if you don’t come to
class prepared. My hope, however, is that this class will be awesome enough that you will want to
come to class, and actively participate in your own learning!

HOWEVER…. I recognize that you are all human and adults, and that life happens. The point of this
class is for you to learn, so I do want to support your ability to learn by supporting the whole concept
of you having a life and existence outside of this class. Please see the section on course policies for
more details on how this works out in practice. In general, if there is anything you need to be able to
learn in this course, do let me know.

Course Materials:
• “Introduction to Statistics & Data Analysis” by Paul Wessel
◦ Available for $15 from this website: https://paul-wessel.selz.com/
 • Canvas: All assignments and information on the individual project can be found on the course’s
Canvas site. Please let me know if you are unable to access the site!
• Students are strongly encouraged to bring their own laptop to class to work on in-class
assignments. If this is a problem, please see me – we can work something out.

Course Policies:

Accessibility and Inclusion: I am committed to a course that is inclusive by design – I want ALL of you
to learn, yes, you too! If you anticipate any barriers to your being able to participate in this class,
please let me know immediately so we can adapt and adjust. Please don’t hesitate to come forward – it
is more than likely that any changes you suggest will help other students as well. If you have a
disability or think you may have one, you are encouraged to work with UNIVERSITY’S disability
office (INFO INFO INFO).

Mental Health and Stress Management Resources: If you are feeling overwhelmed, or are worrying
about a friend, please reach out to one of your instructors or your academic advisor. We can try to help
or we can put you in touch with someone who can help. Cornell has trained counselors available to
listen and help: Empathy, Assistance, and Referral Service (213 Willard Straight Hall, 607-255-3277),
Cornell Health's Counseling and Psychological Services (CAPS, 607-255-5155), and Let’s Talk.

Academic Integrity: Each student in this course is expected to abide by the Cornell University Code of
Academic Integrity. Any work submitted by a student in this course for academic credit will be the
student's own work.

Communication with instructor: If there are problems/questions/concerns, PLEASE let me know,

via email, office hours, or carrier pigeon.
• I promise I am not (intentionally) a gargoyle, I do want to help you succeed in this course. I
can’t help you with something if I don’t know it’s an issue (the whole PhD process does not,
thankfully, confer mind-reading abilities)!
• If my normal office hours (Mon/Thurs 9 to 10 AM) do not work for you, feel free to email me
to set up another time.
• Note: As I take my responsibilities to my family as seriously as I take my responsibilities to this
class, I will not typically answer emails between 9 PM and 9 AM and on weekends, except for
the weekend/days before important course deadlines.

Group work: A significant portion of your grade will come from group work - you will meet your
classmates!
• Groups will be assigned for each week. Depending on the assignment for that week, each group
member will be responsible for certain content or a certain role within the group.
• 1% of your grade (see below) for each group assignment will be based on your peer’s
evaluation of your performance in the group.
• If you anticipate that working in a group will be a barrier to you fully participating in this
course, please let me know and we will find a solution.
• While conflict and disagreements are a natural, and even healthy, part of working in a group,
bias, harassment, and intimidation are not. Treat your group members with the respect! If you
experience or witness bias, harassment, or intimidation, please let me know. Not sure what
 counts as bias, intimidation, or harassment? Please check out THIS UNIVERSITY
RESOURCE.

Attendance: Attendance is not mandatory for this course, but you will be unable to complete the in
class assignments and quizzes if you do not attend, which constitute a significant portion of your grade.
If needed, remote participation can be arranged if I am given at least a week’s advance warning.

Late work: All assignments (homework and in-class) are due on Fridays at the start of class (see
schedule). Late assignments will be deducted 2% for each day past the due date. If your assignment
will be more than 10 days late, please talk to me so we can work something out. Note that all
assignments are posted in advance on Canvas, and you are encouraged to work ahead if this will help
you stay on track later!

Dropped assignments: The lowest grades for in-class quizzes and group homework/in-class
assignments will be automatically dropped, even if the grade is a zero.

Grading Distribution:
In-class group final (cumulative): 8%
Individual Data analysis project: 20%
Final Report: 10%
Final Presentation: 5%
Progress Presentation: 2%
Initial Abstract: 1%
Peer Feedback: 2%
In-class quizzes (non-cumulative): 28% (28 total, 1% each)
Group homework/in-class assignments: 42% (6 total, 7% each, of which 1% is peer evaluation)
Week 1 assignment: 2%
Grading Scale:

97-100% A+ 77-79% C+

93-96% A 73-76% C

90-92% A- 70-72% C-

87-89% B+ 67-69% D+

83-86% B 63-66% D

80-82% B- 60-62% D-

59-0% F
Course Schedule:
Week Dates Topic Assignments Due
1 8/28 (Friday only) Course overview, getting to know you, getting
to know data
2 8/31 – 9/4 Linear Algebra + Calculus Review Week 1 assignment
3 9/9 – 9/11 (no class Exploring and plotting your data In-class assignment 1;
Mon.) 9/9 Last day to add
credits!
4 9/14 – 9/18 Basic Data statistics tools
5 9/21 – 9/25 Data “cleaning” Group homework 1
6 9/28 – 10/2 Basic probability Project Abstract
7 10/5 – 10/9 By the power of Gauss!! (Probability In-class assignment 2
distributions, multivariate distributions)
8 10/14 – 10/16 (no Least-Squares Analysis; Project Progress Project Progress
class Mon.) Presentations Presentations
9 10/19 – 10/23 More advanced Least-squares analysis Oct. 21 Last day to
drop/change grading!
10 10/26 – 10/30 Bayesian analysis Group Homework 2
11 11/2 – 11/6 Hypothesis testing
12 11/9 – 11/13 Digital signal analysis (FFT) In-class assignment 3
13 11/16 – 11/20 Digital signal analysis (Power spectrum and
other friends)
14 11/23 (no class Digital signal analysis (hypothesis testing) Group homework 3
Wed/Fri)
15 11/30 – 12/4 Final Project Presentations Final Project
Presentations
16 12/7 (no class Final Project Presentations Final Project
Wed/Fri) Presentations, Final
Report