Series:

Quantitative Applications in the Social Sciences

3 total works

Cover of Statistical Graphics for Visualizing Multivariate Data
Author William G. Jacoby explores a variety of graphical displays that are useful for visualizing multivariate data. The basic problem involves representing information that varies along several dimensions when the display medium (a computer screen or printed page) is inherently two-dimensional. In order to address this problem, Jacoby introduces the concepts of a "data space." He then explains several methods for coding information directly into the plotting symbols used to represent the observations. He next describes pictorial representations of three-dimensional space followed by a discussion of the scatterplot matrix as a way of "flattening out" the multiple dimensions of a multivariate data space. In addition, he examines conditioning plots (which are strategies for "looking into subregions" of the multidimensional data space), and presents the biplot as a technique for showing observations and variables together in a single display. He concludes with a discussion of some general ideas about data visualization. Statistical Graphics for Visualizing Multivariate Data will enable researchers to better explore the contents of a dataset, find the structure in their data, check the underlying assumptions of the statistical model they used, and better communicate the results of their analysis.

Cover of Statistical Graphics for Univariate and Bivariate Data

Author William G. Jacoby focuses on graphical displays that researchers can employ as an integral part of the data analysis process. Such visual depictions are frequently more revealing than traditional, numerical summary statistics. Accessibly written, this book contains chapters on univariate and bivariate methods. The former covers histograms, smoothed histograms, univariate scatterplots, quantile plots, box plots, and dot plots. The latter covers scatterplot construction guidelines, jittering for overplotted points, marginal box plots, scatterplot slicing, the Loess procedure for nonparametric scatterplot smoothing, and banking to 45 degrees for enhanced visual perception. This book provides strategies for examining data more effectively. The resultant insights help researchers avoid the problem of forcing an inaccurate model onto uncooperative data and guide analysts to model specifications that provide accurate representations of empirical information.


Cover of Data Theory and Dimensional Analysis
By examining some of the basic scaling questions, such as the importance of measurement levels, the kinds of variables needed for Likert or Guttman scales and when to use multidimensional scaling versus factor analysis, Jacoby introduces readers to the most appropriate scaling strategies for different research situations. He also explores data theory, the study of how real world observations can be transformed into something to be analyzed, in order to facilitate more effective use of scaling techniques.