U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Theory, Operationalization, Identification, and the Interpretation of Different Differences in Time Series Models

NCJ Number
193670
Journal
Journal of Quantitative Criminology Volume: 17 Issue: 4 Dated: December 2001 Pages: 359-375
Author(s)
Robert M. O'Brien
Editor(s)
David McDowall
Date Published
December 2001
Length
17 pages
Annotation
In this article, the author examined times series modeling and issues concerning operationalization and model specification and discussed the responsibility of theorists in defining how their theories should be tested.
Abstract
The author expressed the right of theorists to criticize those who test their theories in unreasonable manners. However, when theorists do not provide clear instructions for appropriate tests, the range of reasonableness is extended. Cantor and Land (1985) were said to have provided researchers with a reasonable description of how to test their theory. The author determined that the C-L theory should be tested with the first differenced crime rate as the dependent variable based on their discussion of fluctuation in crime rates. In referencing David Greenberg’s (1985) theory, the author was unsure on how researchers should test his theory. It was suggested that he outline the conditions necessary for an adequate test, such as the time period, level of analysis, and measures of crime to be used. An examination of the ongoing debate between the C-L and Greenberg models on the relationship between unemployment and the rate of crime created an analysis of time series modeling and issues regarding theory and operationalization, specification, identification with levels, lags, and first differences, differencing and interpretation of model parameters, and additional data and tests. The primary issue seen between C-L and Greenberg was the specification of the model, not the fit of the model. References

Downloads

No download available

Availability