Вы находитесь на странице: 1из 7

AMS 315

Data Analysis
Fall Semester, 2016
Class: Tuesday, Thursday, 4:00-5:20, Frey Hall 100
Instructor: Stephen Finch
Office Hours: Wednesday: 3:30 pm to 4:30 pm, Thursday: 2:30 pm to 3:30 pm, and by
appointment. There will be extra office hours the week before each examination. These
will be announced on the class blackboard. My office is in the Mathematics Tower,
Room 1-113, phone: 631-632-8369. My e-mail is Stephen.Finch@stonybrook.edu.
Text: Ott, R.L., Longnecker, M. (2016). Statistical Methods and Data Analysis, latest
edition. Pacific Grove, CA: Duxbury. You will not suffer much of a loss if you get an
older edition or even a different text.
Scientific papers will be posted on the class blackboard. These papers provide case
studies and more detailed discussion and illustration of the application of statistical
techniques than your text or I can give. They are an important supplement to your studies.
You should study them to enhance your understanding of the applicability of the material
in the course.
The prerequisite for this course is AMS 310 or equivalent. For example, a student
who has completed AMS 102, AMS 110 or PSY 201 and received a grade of B or better
should be reasonably well prepared for this course. Specifically, you should have some
knowledge of probability theory, a basic understanding of the central limit theorem, an
introduction to the single sample t-test, and an understanding of the concepts of testing
hypotheses and confidence intervals. I do expect that you have some familiarity with
computing and that you wish to expand your expertise to being able to work with
statistical computing packages.
Past examination problems are in the study guides for each chapter that are posted on the
class blackboard. Past examinations may be posted as well. These may not have a
complete set of answers. There are no homework assignments. You may turn in your
solutions for comments from the TAs and me. The TAs will read your solutions and offer
suggestions and instruction. They are instructed not to solve the problem for you.
Because of the rampant sharing of homework solutions, homeworks will not be graded or
included in the grading process.

Data Analysis Projects

Each student will be assigned at random to a group of three students. Each group will be
given two sets of problems that require the use of statistical computation programs. The
data in each project will be generated synthetically according to a model that differs for
each group. The models are selected because they occur commonly, as noted in the
scientific papers posted on the class blackboard. The first project will be to analyze two
different sets of synthetic data using single predictor linear regression. One part of this
problem will require students to merge two data files; this part focuses on data processing
issues. The second project will be to analyze synthetic data with multiple predictors and
to report the model that was used to generate the data. The model generating the data may
include non-linear predictors and two variable interactions of predictors. Each group will
submit a report in scientific paper format that is the basis of the evaluation of the group.
Each student in the group will earn the same number of points, provided that the other
students in the group include the student. The grade of a student who does not submit
computer projects will be severely impacted.
There will be two in-class examinations (the first on Thursday, October 20 and the
second on Thursday, November 17) and a final examination on Monday, December 19,
from 2:15 pm until 5:00 pm in a room that will be announced later. Each examination
will be comprehensive. The second examination, however, will focus on Chapters 8, 11,
and 12. Example problems for examinations are in your chapter study guides posted on
the class blackboard. Old examinations will also be posted.
You may use an approved calculator in the examination provided that you permit
the proctor to inspect it and reset the memory during the examination. Your calculator
may not have wireless communication capability. For example, the Texas Instruments TI84 is permitted provided that its memory is cleared. The TI-89 and later versions are not
allowed. If your device has an operating system, I will consider it to be a computer, and
you may not use it in the examination. You may have one page of notes using standard
paper size (8.5 by 11 inches). You may write on the front and back, and the sheet must
have your name on it. There may not be any xeroxed material on this sheet. You must
turn it in with your examination. It will be returned to you with your graded examination
paper. The statistical tables and graphs that are needed to solve examination problems
will be provided with the examination. You should not write on the tables and graphs and
must return them at the end of the examination. You may not use or give any other
assistance during the examination.
Professor Arkin, the undergraduate program director in the Applied Mathematics
Department, is the only person who can authorize an incomplete grade for an upper
division AMS course. If Professor Arkin has not authorized an incomplete, absence from
the final may result in failure of this class. Once again, the dates of the examinations and
the anticipated coverages are:

1. Thursday, October 20, with target coverage from Chapters 3, 4, 5, 6, 7, and 11.
2. Thursday, November 17, will be comprehensive and cover Chapters 3, 4, 5, 6, 7, 8,
11, and 12, but not Chapters 9 and 10.
3. Final: Monday, December 19, 2:15 pm-5:00 pm. It will be comprehensive and cover
Chapters 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12. The grading of this examination will not be
Make up examination
In the event that you miss one in-class examination, there will be one make up
examination given on Tuesday, December 13. It will be comprehensive. That is,
questions may come from Chapters 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12. The grading of
this examination will not be "curved." Students who miss both in-class examinations
are advised to withdraw from the class.
Since this class can be offered as part of the training requirements of the
Society of Actuaries, academic integrity issues are fundamental. Academic integrity
standards will be enforced to the best of our ability.
The target grade distribution is roughly 25% A, 30% B, and the remainder C or
lower. That is, the target course GPA is 2.75. Your final grade will be determined on the
basis of two components. One is your computer project component, which is the sum of
the scores received for the two projects. The second is the examination component, E,
which will be calculated by the formula E1 +E2 +EF. Each in-class examination will have
about 6 questions each worth about 40 points so that the examination is worth
approximately 240 points. The final examination will have about 13 problems and be
worth approximately 500 points. The final examination grade and make up examination
will not be "curved." That is, a score of about half of the available points will be a C
score. A performance with about two-thirds of the available points will be a B
performance. A performance with 88% of available points or more will be an A
If your group earns at least 50% of the maximum grade on both of your projects,
your performance on computer projects is satisfactory. If you have satisfactory work on
both computer reports, a strong performance on the final will be a major factor in my
final grading decision. That is, such a student who gets an A on the final gets an A on the
course; such a student who gets a B in the final gets at least a B in the course; and so on.
Lecture Schedule
This schedule is a rough guide to the pace of the lectures. In general, I will go through the
text as indicated. Please note that Chapters 11 and 12 are moved before Chapters 8 and 9
so that there is more time to work on the projects. Your standing assignment is to read the
material before lecture and identify difficulties that you want to have discussed further in
lecture and office hours. You also have a standing assignment to read a newspaper or

internet news source daily to identify stories that involve the use of statistics. If any class
is cancelled due to weather or other conditions, I will cover the material in the next
meeting. Examinations are fixed on the dates above. In the event of lost classes, you will
be responsible for all material covered in class up to the examination date.
There will be no review classes prior to the examinations. The class after each
in-class examination will be dedicated to explaining the solution to each problem on
the examination and the return of the examination. My advice to you is to place the
highest priority on attending these classes.
Tentative Lecture Schedule
Aug 30:
Sep 1:
Sep 6:
Sep 8:
Sep 13:
Sep 15:
Sep 20:
Sep 22:
Sep 27:
Sep 29:
Oct 4:
Oct 6:
Oct 11:
Oct 13:
Oct 18:

Chapter Three, Data Description

Chapter Four, Probability and Probability Distributions (simulation issues)
No class, Labor Day Break
Chapter Five, Inferences about Population Central Values
Chapter Five, Inferences about Population Central Values
Chapter Six, Inferences Comparing Two Population Central Values
Chapter Six, Inferences Comparing Two Population Central Values
Chapter Seven, Inferences about Population Variances
Chapter Eleven, Linear Regression and Correlation
Chapter Eleven, Linear Regression and Correlation
Chapter Eleven, Linear Regression and Correlation
Chapter Eleven, Linear Regression and Correlation
Chapter Eleven, Linear Regression and Correlation
Chapter Twelve, Multiple Regression and the General Linear Model
Chapter Twelve, Multiple Regression and the General Linear Model

Oct 20:

Examination One: Chapters 3-7 and Chapter 11

Oct 25:
Oct 27:
Nov 1:
Nov 3:

Nov 15:

Examination One returned and discussed

Chapter Twelve, Multiple Regression and the General Linear Model
Chapter Twelve, Multiple Regression and the General Linear Model
Chapter Eight, Inferences about More than Two Population Central
Chapter Eight, Inferences about More than Two Population Central
Chapter Eight, Inferences about More than Two Population Central
Chapter Nine, Multiple Comparisons

Nov 17:

Examination Two: Chapters 3-8, 11, and 12

Nov 22:
Nov 24:
Nov 29:
Dec 1:
Dec 6:
Dec 8:

Examination Two returned and discussed

Thanksgiving Recess, no class
Chapter Nine, Multiple Comparisons
Chapter Ten, Categorical Data
Chapter Ten, Categorical Data
Chapter Ten, Categorical Data

Dec 19:

2:15 pm-5:00 pm. Final examination: Chapters 3-12.

Nov 8:
Nov 10:

Methods of Student Evaluation

There will be three examinations with a total with between 25 and 30 questions.
Approximately seven will be theoretically oriented, such as proving that the expected
value of the sample variance using a random sample is equal to the variance of the
sampled random variable. The final examination will be cumulative and focused on the
material taught in the course beyond the content of AMS 310.
Course Objectives
1. Review topics from the prerequisite course (AMS 310 or any one semester
college level introduction to statistics.
a. Basic probability distributions; i.e., binomial, Poisson, normal, and
exponential distributions (Chapter Four of text).
b. Probability calculations; e.g., probability of an event for a random variable
following one of the basic distributions, use of Bayes Theorem, finding
expected value and variance of a random variable (Chapter Four of text).
c. Vocabulary of statistical procedures; e.g., confidence intervals, tests of
hypotheses, Type I and Type II error rates (Chapter Five of text).
d. One sample Student t procedures (Chapter Five of text).
2. Extend knowledge of probability theory.
a. Central chi-square and central F-distributions (Chapter Seven of text).
b. Bonferronis inequality applied to multiple test of hypotheses (Chapter
Nine of text).
c. Logic of multiple comparison procedures (Chapter Nine of text).
d. Decomposing chi-square sums of squares (Chapter Nine of text).
e. Expected value and variance of multiple linear combinations of random
variables (Chapter Eleven of text).
3. Learn intermediate level statistical procedures.
a. Two sample tests and confidence intervals (Chapter Six of text).
b. Tests and confidence intervals for the variance of a normally distributed
random variable (Chapter Seven of text).
c. Tests comparing the variances of two independent normal random
variables (Chapter Seven of text).
d. Tests and confidence intervals for the one way analysis of variance
(Chapters Eight and Nine of text).
e. Statistical procedures for multiple comparisons (Chapter Nine of text).
f. Categorical variable tests using the chi-squared distribution (Chapter Ten
of text).
g. One predictor linear regression (Chapter Eleven of text).
h. Multiple predictor linear regression (Chapters Twelve and Thirteen of
4. Review scientific studies that use the techniques of the course and introduce the
basic ethical principles governing scientific research.

a. Read papers posted on class blackboard.

b. Reference to papers as techniques studied in lecture.
5. Learn the statistical computing package of the students choice and apply it to
obtain the statistical model that generated a set of synthetic data.
a. One predictor linear regression group project using synthetic data that
requires students to merge separate files.
b. Multiple predictor linear regression group project using synthetic data to
recreate statistical model that generated the data. Model includes nonlinear predictors and interactions of two predictors.
Method of Evaluating Each Objective
1. Review of prerequisite material: three or four examination questions.
2. Extend knowledge of probability theory: approximately five examination
3. Learn intermediate statistical procedures: approximately 15 questions.
4. Review of scientific studies: no explicit evaluation.
5. Learn and use statistical computing package: two group reports.
Mandated University Statements
The following statements are mandatory in each undergraduate syllabus. In the
event that I have omitted a mandatory university statement, the requirements of that
statement will apply to this course.
Academic Integrity Syllabus Statement
The following paragraph must be included in the syllabus of any undergraduate course.
Each student must pursue his or her academic goals honestly and be personally
accountable for all submitted work. Representing another persons work as your own is
always wrong. Any suspected instance of academic dishonesty will be reported to the
appropriate academic review board. For more comprehensive information on academic
integrity, including categories of academic dishonesty, please refer to the academic
judiciary website at http://www.stonybrook.edu/uaa/academicjudiciary/

Students with Disabilities

The following statement is inserted in this syllabus as part of official University
If you have a physical, psychiatric/emotional, medical or learning disability that
may impact on your ability to carry out assigned course work, I would urge that you
contact the staff in the Disability Support Services office (DSS). Disability Support
Services is located in the Educational Computing Center (ECC) building, location D5 on
the campus map. Their phone number is 632-6748/9. DSS will review your concerns and
determine, with you, what accommodations are necessary and appropriate. All
information and documentation of disability is confidential.
I will follow DSS recommendations with regard to any students situation.
Critical Incident Management:

Stony Brook University expects students to respect the rights, privileges, and
property of other people. Faculty are required to report to the Office of Judicial Affairs
any disruptive behavior that interrupts their ability to teach, compromises the safety of
the learning environment, or inhibits students ability to learn.
Electronic Communication Statement
Email and especially email sent via Blackboard (http://blackboard.stonybrook.edu) are
ways the TAs and I officially communicate with you for this course. It is your
responsibility to make sure that you read your email in your official University email
account. For most students that is Google Apps for Education
(http://www.stonybrook.edu/mycloud), but you may verify your official Electronic Post
Office (EPO) address at http://it.stonybrook.edu/help/kb/checking-or-changing-yourmail-forwarding-address-in-the-epo. If you choose to forward your official University
email to another off-campus account, the TAs and I are not responsible for any
undeliverable messages to your alternative personal accounts. You can set up Google
Mail forwarding using these DoIT-provided instructions found
at http://it.stonybrook.edu/help/kb/setting-up-mail-forwarding-in-google-mail. If you
need technical assistance, please contact Client Support at (631) 6329800 orsupportteam@stonybrook.edu.
End of Syllabus for AMS 315, Fall Semester, 2016