Statistics 103: Summer (I) 2007
  Probability and Statistical Inference

Syllabus, grading policies, office hours, and general information

Course Objectives

Logistics

Prerequisites

Students must have completed and passed Math 31, or have the equivalent background in differential and integral calculus.  Students should be able to take derivatives and integrals of standard functions (exponentials, polynomials, logarithms) and must understand the basic applications of calculus (finding areas under curves, maximizing/minimizing functions, etc.).  No previous statistical knowledge or background is assumed.

Comparisons with Statistics 101

Statistics 101 covers some of the same topics as Stat 103, but at a lower mathematical level (there are fewer equations in Stat 101).  Statistics 101 does not cover random variables, probability distributions, the rules of expectations and variances, the law of iterated expectations, and point estimation (bias, efficiency, consistency) in the depth covered in Stat 103.  These topics are assumed known in econometrics and finance courses at Duke.  The data analyses in Stat 103 focus more heavily on economics applications than those in Stat 101 do. 

Students who know basic differential and integral calculus and want a general overview of statistics should take Stat 103.  Students who do not know calculus and want a general overview of statistics should take Stat 101.  Economics majors are better served taking Stat 103 than Stat 101, because econometrics relies on methods covered in Stat 103 but not covered in Stat 101.

Readings

The primary text is:

Wonnacott, T. H. and Wonnacott, R. J.  (1990). Introductory Statistics: Fifth Edition.  John Wiley & Sons, Inc.

This text book does not provide details on continuous distributions and supplemental material will be needed. Supplementary material will be suppied as needed.

Computing

We will use the statistical software package JMP-IN (Version 6) in labs and for the final project.  You can download JMP-IN for free from the Duke OIT web site.  It is also available on the PCs in 01 Old Chemistry Building and in several other public PC lab clusters.

Calculator

You need a basic calculator or access to one on a computer.  You don't need to purchase a calculator that can do graphing or has statistical functions.

Graded work

Graded work for the course will consist of problem sets, lab work, a project, two midterms, and a final exam. Your final grade will be determined as follows:
 
Final exam 20 %
Midterm exam 1 15 %
Midterm exam 2 15 %
Homework problems
15 %
In-class problems
 20 %
Labs
 10 %
Project
  5 %

There are no make-ups for exams, in-class or homework problems, or labs except for a medical or familial emergency or previous approval of the instructor.  See the instructor in advance of relevant due dates to discuss possible alternatives.

Cumulative numerical averages of 90 - 100 are guaranteed at least an A-.   Cumulative numerical averages of 80 - 89 are guaranteed at least a B-.   Cumulative numerical averages of 70 - 79 are guaranteed at least a C-.   Cumulative numerical averages of 60 - 69 are guaranteed at least a D-.  These ranges may be lowered, but they will not be raised (e.g., if everyone has averages in the 90s, everyone gets at least an A-).

Descriptions of graded work

Homework problems

Homework problems will be posted on the Stat 103 course web site on Blackboard.   You submit answers to Blackboard, which grades your responses.  You do not have to turn in any papers.  Answers are due before the beginning of the specified class.  After that class starts, the problems will not be graded and count as zeros.  You are permitted to work with others on the problems.  

The homework problems include questions on material covered in previous lectures.  These usually are problems from the text book or problems composed by the instructor.  They also may include questions on the readings assigned for the upcoming class.  These questions have two primary functions: 1) they allow you to practice essential statistical skills; and, 2) they reward you with grading points for keeping your reading current.  Keeping your reading current is essential for getting the most out of lectures, because we use material from the assigned pages when discussing examples and concepts.  The instructor will present lectures assuming that you have read the material for that class.

When you submit your answers, Blackboard will confirm that you have submitted them but not reveal answers.  Solution sheets will be posted after the class ends, so that you can check your results. 

I suggest that you keep paper copies of your work.  That way, you can show your work to the professor or TAs to review and correct any mistakes that you may have made.  Additionally, the copies will be useful for studying for exams.

In-class problems:

You will receive one or two problems to complete in class, covering material from previous lectures.  The problems are similar in spirit to the problems in the text and the problems provided by the instructor.  The dates of all in-class problems are announced at least one week ahead of time.   Roughly, you can expect one problem set per week.   If you miss an in-class problem set because you were not in class, it counts as a zero, unless you have a pre-approved excuse from the instructor.  All requests for excuses must be received by the instructor before the class begins; requests received after class begins will not be granted.

The in-class problems provide a measuring stick for what you know and do not know before the exams.  They reward you for doing lots of problems and for understanding the material.  I suggest doing as many problems as possible from the text and from the additional problems posted by the instructor.  This practice will help you learn the material and ensure that you earn high grades on the in-class problems.

Lab assignments:

Each week, there are weekly data analysis problems completed in lab.  Labs provide hands on experience analyzing data under the guidance of the TAs.  The labs teach you how to apply the skills discussed in lectures and readings.

You are graded on lab reports that must be turned in by the end of the assigned lab period.   Late lab reports will be accepted up to one day late (by Friday at 2 PM) if you made a good faith effort in the lab period but just couldn't finish in time.  Labs turned in after Friday at 2 PM, but before the end of class on Monday, will be penalized by 50% of the maximum score for the lab assignment.  Labs turned in after class on Monday count as a zero.  Missed lab assignments cannot be made up without penalty unless pre-approved by the instructor (not the TAs).  Labs should be completed in your assigned lab section, unless you are given permission by the instructor or TAs to complete the lab in another section.  This is necessary because space in the labs is at a premium.  You are permitted to begin the lab before it is due.  If you do so, I suggest that you come to lab period with any questions that you want to ask the TA.  Traditionally, students who attend lab sections do better on the labs than those who do not attend, because the TAs are available to give advice and help you think about the data analysis.  You are permitted to work with others on the lab, but each person must write up their own lab report.

Final Project:

Web link to instructions for the data analysis project to be presented in poster sessions at the end of the semester in lab sections.

Exams:
Information for exams will be provided before the exams. There will be two midterms and a final exam.


Some advice for success in Statistics 103

DO AS MANY PROBLEMS FROM THE TEXT BOOK AND PROBLEMS POSTED ON BLACKBOARD AS POSSIBLE!!!

The best way to learn statistics, or any quantitative subject, is to work problems on a consistent schedule.  The homeworks and in-class problems provide a structured mechanism for doing so.  I recommend starting the problems at least two days before they are due, so that you have sufficient time to come to office hours with questions.  For particularly difficult concepts, I recommend working problems beyond those assigned, so that you get additional practice.  Then, visit your instructor and TAs to review answers.

Most sections in the text are followed by a set of exercises.  I recommend working two or three of these problems as you are reading.  This allows you to gauge what you did and did not understand on first reading. so that you can re-read if necessary.  After reading, go back and do a good chunk of the remaining exercises.  There are review problems at the end of most chapters.  I recommend working a few problems each week from previous review exercises to maintain and solidify your understanding. 

It is crucial to do the additional problems posted on Blackboard, especially for probability and topics not covered in the text.  These problems are challenging and hence will help you learn statistics effectively.  They also tend to show up on in-class problems.

To maximize your chances of success in Statistics 103, I recommend spending at least 6 hours of work per week outside of the classroom working problems.  I recommend setting up a realistic study schedule in which you spread your work over the week.  Leaving all your statistics work to one night is a sub-optimal strategy, because you won't spend enough time to develop a thorough understanding of the material.    There is a very useful handout describing strategies for studying for quantitative courses on the web site for Duke's Academic Skills Instructional Program (at the site, select "General Academic Skills handouts" and then "Problem-solving courses").   It's packed with good tips, especially for those who don't have much experience studying for quantitative courses at Duke.

I strongly encourage you to form a study group and work problems together.  Evidence shows that 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 Harvard University).

Finally, visit the TAs and instructor when you get stuck or even when you figure something out and want to share your victory.  Almost everyone who does well in this course asks for help at some point in the semester.  Think of us as allies in your efforts to learn statistics.  Nothing makes us happier than you understanding all the material!  

Academic honesty

You are expected to abide by Duke's Community Standard for all work for this course.  Violations of the Standard will result in a failing final grade for this course and will be reported to the Dean of Students for adjudication.  Ignorance of what constitutes academic dishonesty is not a justifiable excuse for violations.

For the homework problems, you may work with a study group with others but must submit your own answers on Blackboard.  For in-class problems and exams, 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 independently and turn in his or her own written report.    On the final project, you work and submit results in groups.

Procedures if you suspect your work has been graded incorrectly

Every effort will be made to mark your work accurately.    You should be credited with all the points you've worked hard to earn!   However, sometimes grading mistakes happen.  If you believe that an error has been made on an in-class problem or exam, return the paper to the instructor immediately, 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 .333);
(iv)  your answer to a free response question is essentially correct but stated slightly differently than the grader's interpretation.

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 takes up valuable time and resources that TAs and the instructor would rather spend helping you understand material.  Please be considerate and only bring claims of type (i), (ii), (iii), or (iv) to our attention.