|
6:30-8:00 p.m. Instructor: William Jacoby |
 |
6:30-8:00 p.m.
July 25-28, 2011
Monday-Thursday
Lecture Room 1, MLBInstructor: William Jacoby
102 Helen Newberry
Phone: (734) 763-6281
E-mail: jacoby@msu.edu
These lectures will cover methods for obtaining visual displays of quantitative information. We will discuss ways to, quite literally, look at your data. This is important because graphical representations avoid some of the restrictive assumptions and simplistic models that are often encountered in empirical analyses.These methods are particularly useful in the social sciences, where the robustness characteristics of traditional statistical techniques often are pushed to their limits.
The first lecture will provide the motivation for graphical displays in data analysis, and discuss the properties of good (and bad) graphs. The second lecture will focus primarily on graphical displays for univariate data. We will then move on, in the third and fourth sessions, to graphs for bivariate and/or multivariate data. Regardless of the specific analytic context, the objective is generally the same: To construct a pictorial abstraction that highlights the salient aspects of the data without distorting any features or imposing undue assumptions.
The lectures will cover a wide variety of specific graphical displays, along with their respective strengths and weaknesses. If time permits, we will also discuss some of the software considerations that are necessarily involved in graphical methodologies. These lectures should be useful for people at varying levels of technical sophistication. Virtually everybody who is exposed to these ideas seems to agree with a variant of the old cliché: "A picture is worth a thousand numbers."