The Cause and Effect Rule for Percentaging Tables: An Overdue Statistical Correction for “Stacking” Studies

Click name to view affiliation

Wilbert M. Leonard II Illinois State University

Search for other papers by Wilbert M. Leonard II in
Current site
Google Scholar
PubMed
Close
and
John Phillips University of the Pacific

Search for other papers by John Phillips in
Current site
Google Scholar
PubMed
Close
Restricted access

“Stacking” is one of the oldest and most thoroughly studied phenomena in the sociology of sport. Because of this tradition, the literature is replete with tabular demonstrations of the stacking phenomenon. Many of these data arrangements violate an important convention in table presentation: Percents should be computed in the direction of the causal factor. This procedure allows one to contrast the distribution of the dependent variable between/among categories of the independent variable and enables determining what differences, if any, exist between/among categories of the independent variable. The consequences of this violation for stacking studies is that, technically, position appears to affect race whereas, logically, race affects position played. Because so many competent researchers have published tables that run the “wrong way,” it is appropriate to examine the rationale behind the cause and effect rule for percentaging tables and instances in which this “rule” may be broken.

Wilbert M. Leonard, II is with the Department of Sociology at Illinois State University, Normal, IL 61761. John Phillips is with the Department of Sociology at the University of the Pacific, Stockton, CA 95211. This paper was presented at the annual meeting of the North American Society for the Sociology of Sport, Birmingham, AL, November, 13-16, 1996.

  • Collapse
  • Expand
All Time Past Year Past 30 Days
Abstract Views 1067 32 1
Full Text Views 19 3 0
PDF Downloads 5 3 0