M 349R (Unique 55840)
Applied Regression and Time Series
Spring 2012
Introduction and Course Objectives
The purpose of this course is to provide students in statistics and applied
disciplines with an introduction to simple and multiple regression methods for analyzing
relationships among several variables, and to elementary time series analysis. The
emphasis will be on fitting suitable models to data, evaluating models using numerical
and graphical techniques and interpreting the results in the context of the original
problem, as opposed to derivation of mathematical properties of the models. At the end
of this course students will be able to analyze many kinds of data in which one variable
of interest is thought to depend on, or at least be related to, several other measured
quantities, and some kinds of data collected over time or in some other serial manner.
Topics include: least squares estimation; inference for regression coefficients and
prediction; residual analysis, multicollinearity, autocorrelation, heteroskedasticity, time
series regression, decomposition methods, exponential smoothing, arima models (BoxJenkins Methodology), model identification, model diagnostics and validation,
forecasting.
Instructor: Gustavo Cepparo
Office: 13.148
E-mail: [email protected]
Lectures:
MW at 3:30 - 5:00 p.m.
Phone: 232-6189
WAG 201
Office hours:
MW 10:05 - 11:35 a.m. in RLM 13.148
Textbook:
Forecasting, Time Series, and Regression, by Bowerman (Duxbury, 2005).
Prerequisites:
A semester long introductory (elementary) statistics class such as M316 or 358K,
BIO 318M, STA 309, etc. I will assume that you are familiar with Chapter 2.
Homework:
Homework will be assigned regularly. There will be quite a lot of homework, and
most of it involves computer work. I will not grade any disorganized or difficult-to-read
assignments. Your homework is your best piece of work. I will not accept homework in
loose sheets of paper. No late assignments will be accepted.
Format: Must be stapled and no ripped pages from a notebook will be accepted. Write
your name at the top of each page. The first page should state the class, section number,
instructor’s name, and book sections included in the homework assignment. Label each
question clearly, specifying the section and exercise number (i.e. 4.1 #32). Should be
organized, clean, and easy to read.
Grading: 5 assignments 10% each
Final Project 14% and 3 Tests 12% each.
Note: This course carries the Quantitative Reasoning flag. Quantitative Reasoning
courses are designed to equip you with skills that are necessary for understanding the
types of quantitative arguments you will regularly encounter in your adult and
professional life. You should therefore expect a substantial portion of your grade to come
from your use of quantitative skills to analyze real-world problems.
Grading. A: 90-100;
B: 80-89;
C: 70-79;
D: 60-69;
F: below 60
(N.B) I will not bump.
Approximate Lecture Schedule
The following schedule is only approximate. I may rearrange the order of some
topics and sometimes I will cover the material more or less quickly than I expected.
Week 1. Review CLT (Central Limit Theorem). t -Confidence Intervals and Hypothesis
Testing. Randomization Tests. Type I and II errors. Simple linear regression: Scatter
plots, correlation (Pearson), End of Review.
(N.B) The review topics will be cover in the first and second lecture within the context of
Linear Regression, I will provide handouts with review problems with answers from
Moore’s Elementary Statistics.
Week 2. The linear regression model, least squares, predicted (fitted) values and
residuals. Hypothesis test and Confidence interval for coefficients, confidence intervals
for the mean value of y and prediction interval for an individual value of y. Interpretation
of coefficients. Log-linear model, log-log model.
Week 3. Is my model useful?(an adequate predictor), Coefficient of determination,
residual analysis: non-normality, heteroskedasticity, outliers, and influential observations.
Let’s look at square root of MSE.
Week 4. Multiple Linear Regression: Estimation, Inference, Testing hypotheses about a
single population parameter, Testing hypotheses about a single linear combination of
parameters (Covariance Matrix), Testing multiple linear restrictions. The Partial F-Test
(restricted model versus unrestricted model). A “Partialling Out” Interpretation of
Multiple Regression.
Week 5. continue… (Test 1 Weeks 1, 2, 3 material)
Week 6. Analysis with Qualitative Information: Binary (or Dummy) Variables,
Incorporating Ordinal Information by using Dummy Variables. Interaction modeling.
Week 7. Heteroskedasticity. Consequences of using OLS under heteroskedasticity. How
to detect heteroskedasticity. How to fix it. Chapter 5
Week 8. Collinearity. Consequences of using OLS under collineatity. How to detect
multicolinearity. How to fix it. Chapter 5, continue.
Week 9. Autocorrelation. Consequences of using OLS under autocorrelation. How to
detect autocorrelation. How to fix it.
Week 10. Time Series Regression. Modeling autocorrelated errors.
Week 11. Can you predict the future by looking at the past? Autoregressive and Moving
Average models. Identification. (Test 2 Weeks 4, 5, 6, 7, 8 material)
Week 12. Estimation. Diagnostic Checking, and Forecasting for Nonseasonal Arima
Models.
Week 13. Arima Seasonal Modeling.
Week 14. Intervention Models. Building a Transfer Function Model.
Week 15. Arima Equivalence with Exponential Smoothing Models. Multivariate
Autoregressive Models. State Space Models. (Final Weeks 9, 10, 11, 12, 13 material)
Computer Work. In this class we will be using SAS, R. I will distribute some material
that will help you get started with SAS and R. Data will be imported to SAS from Excel.
Data will be imported to R from notepad.
"The University of Austin provides upon request appropriate academic
accommodations for qualified students with disabilities. For more
information, contact the Office of the Dean of Students at 471-6259,
471-6441 TTY."
Emergency Evacuation Policy
Every member of the university community shall be familiar with the
Emergency Evacuation Policy and understand his or her role in these
emergency situations.
In the event of a fire or other emergency, it may be necessary to
evacuate a building rapidly. Upon the activation of a fire alarm or
the announcement of an emergency in a university building, all
occupants of the building are required to evacuate and assemble
outside. Once evacuated, no one may re-enter the building without
instruction to do so from the Austin Fire Department, University of
Texas at Austin Police Department, or Fire Prevention Services office.
University faculty members are responsible for pointing out their
classrooms' building emergency evacuation routes and emergency
procedures to students at the beginning of each semester.
Furthermore, faculty, staff, and students should familiarize
themselves with all the exit doors of each room and building they
occupy at the university, and should remember that the nearest exit
routes may not be the same as the way they typically enter buildings.
Students requiring assistance in evacuation shall inform their
instructors in writing during the first week of class. Faculty
members must then provide this information to the Fire Prevention
Services office by fax (512-232-2759), with "Attn. Mr. Roosevelt
Easley" written in the subject line.
Faculty members should be prepared to give appropriate instructions
in the event of an evacuation. Students should follow the
instructions of faculty members and class instructors during
emergency evacuations.
We can most effectively prepare for and cope with emergencies by
working together. Thus, everyone has a duty to ensure other
occupants of university buildings are aware of emergencies, and to
aid anyone requiring assistance in evacuation. People should only
provide this aid to the best of their abilities, however, and no one
is expected to endanger themselves in order to assist with the
evacuation of others.
Information regarding emergency evacuation routes and emergency
procedures can be found
at <http://www.utexas.edu/emergency>www.utexas.edu/emergency.
Classroom Instruction and Recommended Syllabus Information
To implement this policy and reinforce building evacuation
procedures, each faculty member shall provide the following
information and instructions to students:
Occupants of buildings on The University of Texas at Austin campus
are required to evacuate buildings when a fire alarm is activated.
Alarm activation or announcement requires exiting and assembling
outside.
Familiarize yourself with all exit doors of each classroom and
building you may occupy. Remember that the nearest exit door may not
be the one you used when entering the building.
Students requiring assistance in evacuation shall inform their
instructor in writing during the first week of class.
In the event of an evacuation, follow the instruction of faculty or
class instructors.
Do not re-enter a building unless given instructions by the
following: Austin Fire Department, The University of Texas at Austin
Police Department, or Fire Prevention Services office.
Behavior Concerns Advice Line
BCAL: 232-5050