Statistics 111/130
Probability and Statistical
Inference/Probability and Statistics for Engineers
syllabus, course policies, office hours, and general information
Basic Information
The course schedule is
posted on the website. The course will cover probability, up to
double integrals for bivariate densities. Inference includes
Bayesian and maximum likelihood estimates, and traditional and
bootstrap methods for confidence intervals. Hypothesis testing is
covered in multiple ways---parameter tests, goodness-of-fit, and
ANOVA, as well as power. Regression includes simple, multiple,
nonlinear and nonparametric regression. We cover two-way ANOVA
and fractional factorial designs. We also briefly discuss risk
analysis and decision theory.
The recommended, but
optional, text is
Probability and Statistics
(4th edition) by De Groot and Schervish, published by Addison-Wesley
(ISBN 10:0-321-50046-6, price $132.99).
Finding a good book is always a problem---none of the available
texts is fully satisfactory.
In general, this is a technically strong introductory book, but this course will
supplement its coverage at several points. The book is worth keeping
for reference in future courses and later life.
Course lectures will be posted on
the class website the day before the lecture. You are encouraged to
print these out and bring them to class---that way you can focus on the
material rather than taking notes. To save trees you can use some
special print options. For PCs, use (1) Print - ePrint; (2) Properties (just to
the right of the printer selector): a. "Print on both sides" b.
"Pages per sheet" (Four pages per sheet works well for the lecture
notes) c. OK; (3) OK/Print. For Macs, use (1) File - Print; (2) Click on
the box that says "Copies and Pages"; (3) Select "Layout";
(4) Select "Two-sided Printing" (long-edge is usually preferred); (5)
Properties - "Pages per sheet" (four pages per sheet works well).
Computing
We shall use the statistical
software package Stata during the economics labs and Matlab in the
engineering labs, and all students are welcome to use R, or any
other package they prefer. Stata is the only
package used by Duke's Economics Department, and since most students
in STA 111 are econ majors, this may be your most efficient
choice. Many econ majors purchase and install Stata on
their laptops, but it is available for free in OIT computer
clusters.
Calculator
For every lecture,
you will need a simple calculator for quizzes,
exams and homework. Graphical capability is not required, and questions
are worded so that advanced calculators confer no advantage.
Advice
for Success in Statistics 111
WORK MANY PROBLEMS!!!
The best way to learn statistics,
or any quantitative subject, is to work problems. Although you usually
won't have to turn in problems from the book, working these at home on a
regular schedule will significantly improve your understanding of the
material. Also, the homework and exams (discussed below) are based on the
concepts reviewed by the problems in the text, so a solid understanding of
these problems increases the chance that you will earn a high grade in the
course.
Most sections in the text are
followed by a set of exercises. I recommend working these as you
read. There are also review exercises at the end of most chapters; doing
these a few days after reading the chapter will consolidate your understanding.
JOIN A STUDY GROUP!!!
Students who work in groups in quantitative
courses learn more and enjoy the course more than those who work alone (see the
studies by Richard Light
at
PLAN YOUR TIME!!!
Students who succeed in
Statistics 111 typically put in at least 6 hours of work per week
outside of the classroom. You should set up a realistic study schedule in
which you spread your work over the week. It is a poor idea to rely upon
cramming the night before an exam.
Finally, please use us, the TAs
and instructor, for help when you get stuck. We are allies in your
assault upon statistics.
Graded
Work
Graded work for the course will
consist of quizzes, homework, lab work, and four exams. Your
final grade will be determined as follows:
Exams 1-4 |
20% on the best score, 15% on the second and third best, 10% on the worst |
Homework |
10% |
Quizzes |
20% |
Lab Work |
10% |
There will be no final exam for this class during Duke University's
exam period at the end of the semester.
Missed homework,
quizzes, or lab
reports can only be excused under exceptional circumstances. For
short-term illness, please send the instructor the standard Duke form.
Except in emergencies, all other absenteeism
must be approved in advance (e.g., an athlete who must miss class may be
excused by prior arrangement for specific days). For emergencies, email
notification is needed at the first reasonable
time.
If a student has
an excused absence from an exam, quiz, homework, or lab,
then the missing grade will be
imputed by the average of all other corresponding grades on exams, quizzes,
homeworks, or labs (without any dropped scores).
Each exam, quiz, homework, or lab
will receive a letter grade. An 'A+' corresponds to a score of 12, an 'A'
corresponds to 11, an 'A-' is a 10, a 'B+' is a 9, and so forth. The final
grade in the course is determined by the weighted average (as per the table
above) of these scores. Breakpoints for grades occur at the halfway points. For
example, the lowest possible average that gives an 'A-' for the semester is
9.5.
Descriptions
of Graded Work
Homework:
You will download homework assignments
from the class website. There will be a homework assignment for almost every
week, and it must be turned in at the beginning class on the date indicated. The homework
component of the final grade is found by dropping the lowest homework grade and
averaging the rest.
Lab assignments:
Almost every week, there are data
analysis problems to be completed in lab. Labs provide hands-on
experience in analyzing data under the guidance of the TAs. The labs
teach you how to apply the skills discussed in lectures and readings. You must
attend your scheduled lab except when given prior permission by the
instructor or a TA to complete the lab in another section. This is
necessary because space in the labs is very tight.
You are graded on lab reports
that must be turned in by the end of the assigned lab period. The lab
component of your final grade is found by dropping the lowest lab grade and
averaging the rest.
Quizzes:
There will be short in-class
quizzes in almost every lecture. The purpose of these is to help students
realize instantly what parts of the current material they have mastered and
what parts are unclear. Quizzes will focus on difficult material from
previous lectures, easy material from the current lecture, and the assigned
reading for the day. The quiz component
of your final grade is found by dropping the two lowest quiz grades and
averaging the rest.
Academic Honesty
You are expected to abide by
Duke's Community Standard for all work for this course. Violations will
be reported to the Dean of Students for adjudication; the minimum penalty for
cheating is failure in this course.
For homework, you are allowed to
discuss problems in general, but the final solution and write-up must be your
own. For in-class exams and quizzes, you are required to work alone and
for only the specified time period. For labs, you are allowed and
encouraged to help each other, but each person must complete the lab report on
their own.
Procedures
for Requesting a Regrade
Every effort will be made to mark
your work accurately. We are on your side, and want you to
receive every point you have worked to earn. However, sometimes
grading mistakes happen. If you believe that an error has been made,
return the paper to the instructor within two weeks, stating your claim in
writing.
The following claims will be
considered for re-grading:
(i)
points are not totaled correctly;
(ii) the grader did not see a correct answer that is on your paper;
(iii) your answer is the same as the correct answer, but in a different
form (e.g., you wrote a correct answer as 1/3 and the grader was looking for
0.333);
(iv) your answer to a free response question is essentially correct but
stated slightly differently than the grader's expectation.
The following claims will not
be considered for re-grading:
(v) arguments about
the number of points lost;
(vi) arguments about question wording.
Considering re-grades consumes
time and resources that TAs and the instructor would rather spend helping you
understand material. Please bring only claims of type (i), (ii), (iii),
or (iv) to our attention.