About | HeinOnline Law Journal Library | HeinOnline Law Journal Library | HeinOnline
LOG IN
LOG IN

62 Soc. F. 800 (1983-1984)
Multicollinearity in a Study of Regional Variations in Homicide Rates: A Comment on Smith and Parker

handle is hein.journals/josf62 and id is 820 raw text is: Multicollinearity in a Study of Regional Variations in Homicide Rates: A Comment on Smith and Parker* STEPHEN C. LIGHT, State University of New York, Albany In a 1980 article, Smith and Parker examine homicide data from the 48 continental U.S. states in an effort to determine the relative explanatory power of a cultural versus a structural perspective. The authors note that previous studies have consistently shown a higher homicide rate in southern states, but that explanations of the phenomenon have been far more elusive (136). In an attempt to shed some light on this problem, the authors draw on their previous work (Parker and Smith) and divide homicide into two types: primary homicide, generally occurring between family, friends, and acquaintances, and non-primary homicide, generally occurring be- tween strangers. By focusing on the victim-offender relationship, they hope to avoid some of the inconsistency evident in previous research in this area, where an implicit assumption has been that the dependent variable, homicide rates, reflects a homogeneous phenomenon (Smith and Parker, 139). Multiple regression is then used to estimate the effect on total homicide, primary homicide, and non-primary homicide of structural variables and an indicator of the culture of the South. Although the authors deserve to be commended for their attempt at clarifying an important issue, their analysis contains a potentially serious flaw-the high degree of multicollinearity present among the independent variables in the multiple regression equations. An examination of the zero- order correlation matrix of the independent variables reveals the presence of six intercorrelations which are at, or in excess of, .70-structural poverty index with percent nonwhite (.89), 'structural poverty index with Gini coefficient (.81), structural poverty index with non-South (-.77), percent nonwhite with non-South (-.75), percent nonwhite with Gini coefficient *We acknowledge the expert assistance of Steve Greenstein (formerly of the suNY-Albany Computing Center) in FORTRAN computer programming. Address correspondence to the author, Department of Sociology, State University of New York, Albany, NY 12222. 0 1984 The University of North Carolina Press 800

What Is HeinOnline?

HeinOnline is a subscription-based resource containing thousands of academic and legal journals from inception; complete coverage of government documents such as U.S. Statutes at Large, U.S. Code, Federal Register, Code of Federal Regulations, U.S. Reports, and much more. Documents are image-based, fully searchable PDFs with the authority of print combined with the accessibility of a user-friendly and powerful database. For more information, request a quote or trial for your organization below.



Short-term subscription options include 24 hours, 48 hours, or 1 week to HeinOnline.

Purchase Access

Contact us for annual subscription options:

Contact Us

Already a HeinOnline Subscriber?

Log In

profiles profiles most