Course Information Course Description: Mlevins@purdue - Edu

Instructor: Prof.
Michael Levine
Office: HAAS 154
Phone (765) 496-7571
E-mail mlevins@purdue.edu
Course webpage http://www.stat.purdue.edu/~mlevins/STAT420/Stat420.html
Class meetings: TTh, 9 am-10.15 am (Section 1) and 10.30am-11.45 pm (Section 2), REC 122
Office hours: TTh 2pm-3pm or by appointment
COURSE INFORMATION
Course Description
This course is an introduction to time series analysis suitable for undergraduates in

actuarial science, engineering, and sciences. Topics covered are:
1.
2.
3.
4.
5.
Examples, simple descriptive techniques, trend, seasonality, the correlogram

Probability models for time series and stationarity
Moving average (MA), Autoregressive (AR), ARMA and ARIMA models
Estimating the autocorrelation function and fitting ARIMA models
Introduction to forecasting, exponential smoothing, forecasting from ARIMA
models.
6. Stationary processes in the frequency domain: The spectral density function, the
periodogram, spectral analysis
7. State-space models: Dynamic linear models and the Kalman filter
Prerequisite
STAT350 or equivalent and MA/STAT 416 or equivalent
Textbook
Chris Chatfield The Analysis of Time Series: An Introduction, 6th Edition,

Required
R Computer Software: We will use mostly R to perform data analysis in this class. The intent of
using software is to allow the computer to perform routine calculations and graphing, while we
focus on choosing the appropriate analysis tools and interpreting the results. Computer software is
NOT a substitute for understanding the statistical methods, and you will not have access to a
computer during exams. R is available in the Purdue computing labs.
Reading
I expect you to read the text as we cover the material. It is rather helpful if you do the first reading
before we discuss the given material in class. This does not mean that I expect you to learn it all
on your own; rather, your reading before class should be viewed as a first pass at the material.
When you read the material for the first time, dont lose the sight of the forest for the trees but
rather keep the big picture in mind! In particular, this means not getting bogged down in
formulas or details; just try to get a rough idea of the material and get familiar with the
vocabulary. This will prepare you for what is to come in the class, and will make the class easier
to follow. Later, as you are working on problem sets and studying for tests, you will find it
helpful to read the material again. This time, read at a much more detailed level. It will be a lot
easier to follow then, since you have heard this material in class already.
Lectures
To help you with studying, I will be posting the class notes in the form of slides on the course
web site. Slides will contain some basic theoretical points, examples and graphs that will be
mentioned in class; however, I will be fleshing them out in class to a much greater extent.
Therefore, your personal attendance will be of great help to you.
Homework
There will be regular homework assignments in this class. After the homework assignment is
given, the due date will always be one week from that day. Solutions for homework will be
provided soon after the due date and will be posted online on the course website. Collaboration
on homework assignments is permitted, even encouraged, but each student should write up
his/her own solution. Identical solutions are NOT acceptable. Your homework must reflect
YOUR understanding of the material. If identical solutions are found, all the parties involved will
receive a 0 on that assignment
No late homework will be accepted UNDER ANY CIRCUMSTANCES; instead, the two lowest
homework scores will be dropped at the end of semester. The homework is responsible for 25%
of your final grade.
Please do not pad your homework with endless software printouts. Only hand in those parts of the
output that are directly relevant to your solution. Homework must be stapled if it is longer than
one page. The first page must include your name, my name (Dr. Levine), the number of the
problem set (e.g., HW #2), your section number (1or 2, respectively), the due date and the course:
STAT 420
Exams
There will be three exams in this course two midterms and a final exam. Both midterms will be
evening exams. I will provide you the exam times/dates/locations once Purdue has scheduled
them on the exam web page. Each examination will contain both mathematical and conceptual
(written or short answer) components. Each exam, including the final, is worth 25% of your total
grade. The midterms are not cumulative but the final exam is. Contact me as soon as possible if
you are unable to take the exam at the scheduled time due to job interviews or exam conflicts. It
is YOUR responsibility to contact me IN ADVANCE to check if a make-up is possible. Students
having exam conflicts or requesting special accommodations (these should be documented) must
inform me as early as possible so that alternative plans may be arranged. You may use a
calculator during all exams if you wish. The exams are closed book but open notes. You can
bring one standard size cheat sheet of paper to each of the midterms written on both sides. This
allowance goes up to two cheat sheets for the final exam.
Re-grading: Since all humans make mistakes (including the professor and the grader), errors will
occur in the grading. The following procedure is required if you want your assignment re-graded.
1. Attach a new piece of paper to the front of the work to be re-graded which contains the
following information:
a) The word Re-grade displayed prominently.
b) Your name
c) The name of course - STAT 420 and your section number-1. Be sure that this is clear so we
know which course you are enrolled in.
d) Which homework or exam is involved (e.g., HW 1)
e) The relevant problem number(s) (e.g. problem 2a) or Addition error
f) A detailed explanation of the suspected error (Please look at problem 4 is NOT considered a
detailed explanation) or provide the total number of points which you calculated if the assignment
was added incorrectly
g) date of resubmission
2. Print out the solutions from the web page (at least the relevant portions) and circle the relevant
piece of the solution. Attach this behind the work to be re-graded. (This is not required if you
think that the points were added incorrectly.)
3. Give this packet to me, or put it in my mailbox.
Grades
Final Grade: The final scores will be determined as follows: homework 25%, midterm I 25%,
midterm II 25%, final exam 25%. Grades will be calculated on the 100% scale. Let the score be x;
then 90 < x 100 results in A, 80 < x 90 results in B, 70 < x 80 in C and 60 < x 70

in D. Any score below 60 equals the grade of F. Doubtful cases (within a few hundredth of the
dividing point) will result in the addition of the minus or plus to the respective grade.
Academic Dishonesty: Penalties for academic misconduct range from a 0 on the assignment to
failure in the course with referral to the Dean of Students for further sanctions. Note that we
punish not only the person who cheats but also the person who enables the cheater.
Attendance: Though I do not take roll in class, students are responsible for all material covered
in the lectures. Not all of the material discussed in class is available in the textbook. If a student
misses a class it is up to that student to check with their classmates to obtain the missed material.
Grief Absence Policy for Students: Purdue University recognizes that a time of bereavement is
very difficult for a student. The University therefore provides the following rights to students
facing the loss of a family member through the Grief Absence Policy for Students (GAPS). GAPS
Policy: Students will be excused for funeral leave and given the opportunity to earn equivalent
credit and to demonstrate evidence of meeting the learning outcomes for missed assignments or
assessments in the event of the death of a member of the students family.
Students with Disabilities: Purdue University is required to respond to the needs of the students
with disabilities as outlined in both the Rehabilitation Act of 1973 and the Americans with
Disabilities Act of 1990 through the provision of auxiliary aids and services that allow a student
with a disability to fully access and participate in the programs, services, and activities at Purdue
University. It is the student's responsibility to notify the Disability Resource Center of an
impairment/condition that may require accommodations and/or classroom modifications.
Emergencies: in the event of a major campus emergency or other circumstances beyond the
instructors control, course requirements, deadlines and grading percentages are subject to
changes that may be necessitated by a revised semester calendar. Relevant changes to this course
will be posted onto the course website; you can also e-mail me at mlevins@purdue.edu with any
questions you may have if/when this happens.

Course Information Course Description: Mlevins@purdue - Edu

Uploaded by

Copyright:

Available Formats

Course Information Course Description: Mlevins@purdue - Edu

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Course Information Course Description: Mlevins@purdue - Edu

Uploaded by

Copyright:

Available Formats

Instructor: Prof.

This course is an introduction to time series analysis suitable for undergraduates in

Examples, simple descriptive techniques, trend, seasonality, the correlogram

Chris Chatfield The Analysis of Time Series: An Introduction, 6th Edition,

then 90 < x 100 results in A, 80 < x 90 results in B, 70 < x 80 in C and 60 < x 70

You might also like