Course objective: to develop data analysis skills by working with some of the most important statistical and graphical techniques, implementing all techniques and analyses in the SAS programming language/platform. This course is about statistical modelling, computing and data analysis using SAS. Prerequisite: Stat 400 is the only listed prerequisite: the concepts but not so much the problem solution techniques of that course are important. We will do some algebraic manipulations in making sense of various statistical models, and familiarity with elementary linear algebra and matrix notation will be helpful in dealing with (multiple) regression topics.
Course requirements and Grading: Most of the work for the course will consist of 8--10 graded Problem Sets. These will involve writing and running small SAS programs and interpreting the sequence of data-analysis operations and outputs. While you will be permitted to share hints and infor- mation concerning SAS programming, the reasoning behind analyses, sum- maries of them, interpretation of results, and edited handed-in copies must be exclusively your own work.
In addition, there will be an in-class test toward the end of October, on basics of the SAS language and concepts underlying data-display and statistics in categorical data, two-sample comparisons, and simple linear regression. Finally, there will be a slightly more ambitious data-analysis term project in place of a Final Exam (due Friday, May 15, by 5pm). The course grade will be based on a weighted average, with 50% weight on Homework scores and 25% for the Test and 25% for the Term Project.
After the first couple of problem sets in which you develop basic SAS sysntax skills, your homework will be graded not only on the correct calculations in your SAS programs but also on the explanations you give of what you computed and why, and what it shows. So I will strongly discourage handing in voluminous or unedited outputs, and I will impose page limits on each submited Homework.
Text: Applied Statistics and the SAS Programming Language,
5th ed., by R. Cody and J. Smith.
Recommended: Make sure you have access to a Stat 400-401 level introductory
statistics textbook. For linear regression topics, an excellent general
reference is: Applied Regression Analysis, 3rd
ed., by N. Draper and H. Smith. Wiley, 2001. Earlier editions
would also be OK.
The sections covered in the main part of the text are:
Chapter 1: Basics of SAS syntax, all sections, with some reference to material in Chapters 12, 13.
Chapter 2: Data display and graphics, all sections.
Chapter 3: Categorical data, esp. sections A, C-E, G, I-L, N-Q
Chapter 5: all
Chapter 6: all
Chapter 7: sections A-E
Chapter 9: sections A-E, G-H
In addition, we discuss under several headings the notions of statistical simulation and permutational significance levels. The later chapters of the book (primarily, parts of Chapters 12-15) will serve throughout as a SAS reference and source of mini-program templates.