• Syllabus

General honor code: You may discuss the problems with each other in general terms, but you must write your own solution. All sources, including friends and colleagues, must be cited. It is important to get used to a stringent code of conduct in scientific writing. On the other hand, use commonsense and attribute where honesty requires it. Two points worth special mention:
*** If you received an extension for a homework, do not consult posted solutions.
*** An offense with severe consequences anytime would be consulting solutions of homeworks from previous years.

• Homework 1: R practice; see the "Introduction to R" below.

• Homework 2: linear algebra and latex practice; edit the LaTex source and submit a PDF file by email.
  If you have never used LaTex, you can first install some free software:
  • MikTex translator,
  • LEd LaTex editor,
  • Manual for Latex.
  In the manual, pay special attention to Section 1.3.2 (special characters) and Chapter 3 for math typesetting (math symbols: Section 3.10). To produce PDF from LaTex, the LEd environment requires you to click the green and blue right arrows in the tool bar. Feel free to check out other free software and other documents. If you find something particularly useful, please, let me know.

• Homework 3: R practice, string manipulations and analysis.

• Homework 4: Linear algebra and linear models; edit the LaTex source and submit a PDF file by email.

• Homework 5: Q-R decompositions and Least Squares computations in R.

• Homework 6: Writing exercise, Chapter 5 in "Style".

• Homework 7 (data, template): real estate project.

• Homework 8: Writing exercise, Chapter 6 in "Style".
  Also, redo Homework 6 by downloading a new copy of the blank file above. Make sure you are solving the proper problems.

• Homework 9: Linear models for ANOVA and tests for lack-of-fit diagnostics

• TA: Yuzhou Liu --- Office hour: Thursdays, 2-3pm, JMHH 440
  Instructor's office hours: Monday, 4:30 after class

• Unless instructed otherwise, homeworks should be e-mailed in attachments to stat541.at.wharton[at-sign]gmail.com. The format should be .txt or .pdf or .doc depending on the assignment.
  Your checked and graded solutions are returned in e-mail attachments. Search '#AB' to find comments. A score such as 8/10 at the end means '8 out of 10 points'. A deduction of 2 points does not mean you got two questions wrong; it is only a relative measure of how much below optimal your solutions are.

• Lecture 20 (2009/11/18)

• Lecture 19 (2009/11/16)

• Lecture 18 (2009/11/11)

• Lecture 17 (2009/11/09)

• Lecture 16 (2009/11/04)

• Lecture 15 (2009/11/02)

• Lecture 14 (2009/10/28)

• Lecture 13 (2009/10/26)

• Lecture 12 (2009/10/21)

• Lecture 11 (2009/10/14)

• Lecture 10 (2009/10/12)

• Lecture 9 (2009/10/7)

• Lecture 8 (2009/10/5)

• Lecture 7 (2009/09/30)

• Lecture 6 (2009/09/28)

• Lecture 5 (2009/09/23)
  Here is R code to illustrate the LS geometry; you can run it directly by executing this in an R interpreter:
  source("http://www-stat.wharton.upenn.edu/~buja/STAT-541/LS-geometry.R")

• Lecture 4 (2009/09/21)

• Lectures 1-3 (2009/09/17)

• Introduction to R

• Crib sheet for R

• Readme file for Emacs' ESS macros

• A small book
• Spelling dictionary
• Speech fragment (3.3 mB!)
• Boston housing data with a description of the variables
  Geographical names are in this file.
• Pima Indians diabetes data with a description of the variables
• Laser data with a description of the variables
• Titanic survival data
• Marketing data
• Tips data; analysis
• Detergent data
• Places Rated data with a description
  In a form suitable for xgobi or ggobi: data, column labels, row labels.
  Say 'xgobi places_ggobi' or 'ggobi places_ggobi', depending on which you're using.
• Accounting-Market Rate data (Myers, p.16ff)
• Odd regression data
• Fabric failure data (Myers, p.329f)
• Vaso-restriction data (Myers, p.331f)
• FedEx data, reduced for elasticity demo
• Blocks data, reduced for fixed/variable cost demo
• Algal bloom data; some background is in the README file
• Webserver data
• Wine displayspace data
• Car Models 2003-4
• Body Fat data, variable names, README file,
• FTSE Data 1991-05-13 through 2006-05-11

• Initial tabulation of all variables of a dataframe
• "plot.plus()" and "pairs.plus()": wrappers around 'plot()' and 'pairs()' that jitter categorical variables and provide more space between the points and the borders and axes.
• Empirical two-sample quantile plot with inference
• Mosaic plots, double-decker plots (a competitor for R's mosaic plot function)
• Trimmed correlations, covariances and standard deviations
• Histograms with graphical bootstrap
• Tree-based regression for interpretation and datamining
• Diagnostics plot of linear models with smooth
• Box-Cox transformations
• Collinearity diagnostics with PCA
• Residual diagnostics with null comparisons
• Leverage plots with null comparison
• Utilities for k-means clustering
• Moving blocks bootstrap for time series

IMPORTANT: If a function in the class notes does not work or is not found in your R session, check whether the function is in one of the R code files below. If so, download and read the file into R one more time, even if you thought you had done so earlier. I allow myself to update the code all the time.

• The paper on tree-based regression and classification is in this PDF file.

• The paper on additive principal components is in this PDF file.

• For regression: Seber and Lee, "Linear Regression Analysis" (Wiley Series in Probability and Statistics)
• For linear algebra: Strang, "Linear Algebra and its Applications" (Academic Press)
  Strangely, the most fundamental material is tucked away in the Appendix: "Linear Transformations, Matrices, and Change of Basis." If you are not fluent at basis changes and associated coordinate transformations, study these 11 pages with great care!

• Instructor: Andreas Buja, stat541.at.wharton[at-sign]gmail.com
  Office hours: by appointment.
  Office: JMHH 471
  Class Room: JMHH F36

• The goal of the course is to prepare statistics Ph.D. students for independent research. Accordingly, the demands on conceptual thinking and quick uptake will be considerable as the course progresses.

• Homework will be extensive and approach the level of research problems. The weekly homeworks will be the heart of what you retain from this course.

• Grades will be computed from homeworks and class participation alone. There will be no midterm or final exams.

• Topics:
  • Linear Models and inference
  • Exploratory data analysis, data visualization
  • Statistical testing exemplified with permutation tests
  • Confidence intervals with bootstrap
  • Tree-based regression
  • ACE and additive models
  • Principal Components
  • Non-parametric curve fitting
  • Bias-variance trade-offs
  • Cross-validation for estimating prediction errors and selecting bandwidths and models
  • Writing for research, including style and clarity, typesetting, web publishing

• As the tool of choice for the execution of data analyses and simulations, we use the R programming language. R will be taught, but this is not an ``R class.''

• Prerequisites will include
  • a course in linear algebra (linear maps, inner product spaces, orthogonal projections, eigen decompositions);
  • statistical inference at the level of Stat 431 (including statistical tests, confidence intervals, linear models, estimation, sufficiency);
  • programming experience in some language (examples: R, Splus, Matlab, Perl, Python, Visual Basic; C, Fortran, ...).

• A word to undergraduate students contemplating this course: If you do not have a solid background in statistics already, you should not take this class or, at a minimum, not rely on credit from it for graduation. As mentioned above, the goal is to prepare students for statistics research, and there will be only one standard of performance for all students.

• Writing is of utmost importance for research. To get used to the standards of writing research papers in statistics, some homeworks will be required to be typeset in LaTex and submitted by e-mail as a PDF file.

• The only required texts are the following, one of which not about statistics but about writing:
  • Style --- Lessons in Clarity and Grace by Joseph M. Williams (ISBN 0-321-47935-1).
  • An Introduction to R by Venables and Smith (ISBN 0-9541617-4-2)

• Required web documents:
  • The Science of Scientific Writing
  • An Introduction to R [PDF] [HTML]
    This is the above required book in a free online version. While online is handy for searching, you should still have the book version for actual reading. It costs only about $20.

• If you need more reading about R, look up the numerous books about R or the numerous free web documents about R. Yet another way to find R introductions is to do a search for "Introduction to R". If you find something particularly useful, please, let me know.

• Recommended texts:
  • Venables and Ripley, "Modern Applied Statistics with S-Plus" (Springer) a recommended, terse book on a broad array of appl. stats. topics, based on the S/R language.
  • Becker, Chambers, Wilks, "The New S Language" the original S book, also called "the blue book"; even for R users still a good place to start.
  • Chambers, Hastie (eds.) "Statistical Models in S" on the statistical modeling language in S/R, also called "the white book"
  • R. L. Harris, "Information Graphics, an excellent overview of useful and common data visualizations.
  As we go along, special topics books will be recommended.