Abstract
A reading of the studies having been published by important sociological and criminological journals reveals a clear picture: for a variable to be considered dependent in a randomized experimental study (at least for those accepted and published by these journals), it has to be behavioral. The question asked in this article is, may only behavioral measures constitute dependent variables in highly qualified experimental studies? The answer is a distinct “no”, and attitudinal measures are also proposed as possible and legitimate dependent variables in randomized experimental studies. Here the factorial-survey approach, a relatively new survey technique, which combines the benefits of controlled, randomized experimental designs and conventional surveys, is suggested as a characteristic experimental technique in such studies. This article concludes that the factorial-survey approach may be considered an appropriate experimental technique in social science research—it produces findings that less developed methods are not able to examine.
Highlights
IntroductionWe may define a randomized experimental study as this whose internal validity is established by random allocation of the population of interest—or a sample of it—to different conditions, treatments, or programs
A review of the articles published in the leading criminological journals so far reveals that for a highly qualified experimental study in criminology—and criminal justice—to be published—at least in these journals, in most cases it needs to deal with a behavioral measure, which for the purposes of these studies will be considered the dependent variable
The purpose of the present study was to introduce the factorial-survey technique as an additional highly qualified experimental technique, which unlike the former situations may be applied in answering questions related to attitudinal issues in both criminology and criminal justice
Summary
We may define a randomized experimental study as this whose internal validity is established by random allocation of the population of interest—or a sample of it—to different conditions, treatments, or programs Their common aim is to isolate effects on the respondents, from other possible factors, that may contribute to group differences. Subsequent differences found in the dependent variables may be assumed, with a very high degree of certainty, to stem from the respondents’ exposures to the various options of the independent variables, and not from other confounding factors For this reason, internal validity is often maximized in experimental studies, which are generally considered the most appropriate research setting for questions and issues of causality and effect Internal validity is often maximized in experimental studies, which are generally considered the most appropriate research setting for questions and issues of causality and effect (see Lum & Yang, 2005: p. 192 [9])
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
