SAGE Journal Articles
Click on the following links. Please note these will open in a new window.
(13.1). This is an example of a nonequivalent comparison-group design. Remember: Quasi-experimental designs do not have random assignment to the groups.
Journal Article 1: Peterson, K., Sharps, P., & Banyard, V. (2018). An evaluation of two dating violence prevention programs on a college campus. Journal of Interpersonal Violence 2018, 33, 3630–3655. https://doi.org/10.1177/0886260516636069
Abstract: Dating violence is a serious and prevalent public health problem that is associated with numerous negative physical and psychological health outcomes, and yet there has been limited evaluation of prevention programs on college campuses. A recent innovation in campus prevention focuses on mobilizing bystanders to take action. To date, bystander programs have mainly been compared with no treatment control groups raising questions about what value is added to dating violence prevention by focusing on bystanders. This study compared a single 90-min bystander education program for dating violence prevention with a traditional awareness education program, as well as with a no education control group. Using a quasi-experimental pretest/posttest design with follow-up at 2 months, a sample of predominately freshmen college students was randomized to either the bystander (n = 369) or traditional awareness (n = 376) dating violence education program. A non-randomized control group of freshmen students who did not receive any education were also surveyed (n = 224). Students completed measures of attitudes, including rape myth acceptance, bystander efficacy, and intent to help as well as behavioral measures related to bystander action and victimization. Results showed that the bystander education program was more effective at changing attitudes, beliefs, efficacy, intentions, and self-reported behaviors compared with the traditional awareness education program. Both programs were significantly more effective than no education. The findings of this study have important implications for future dating violence prevention educational programming, emphasizing the value of bystander education programs for primary dating violence prevention among college students.
(13.2). This is an example of a study that used an interrupted time-series design.
Journal Article 2: Fraser, K., Wallis, M., & St. John, W. (2004). Improving children's problem eating and mealtime behaviours: An evaluative study of a single session parent education programme. Health Education Journal, 63, 229–241.
Objective: To evaluate the effectiveness of a 'single session' group, early intervention, multidisciplinary, education programme (entitled the Fun not Fuss with Food group programme) designed to improve children's problem eating and mealtime behaviours.
Design: A quasi-experimental time-series design incorporating data collection, twice before and twice following the intervention.
Setting: A health district within the southeast region of Queensland, Australia.
Method: Data were collected using the Children's Eating and Mealtime Behaviour Inventory-Revised (CEBI-R) and the Family Demographic Questionnaire.
Results: Parents who attended the Fun not Fuss with Food group programme reported significant improvements in their child's problem eating and mealtime behaviours and reported reductions in parental concerns regarding their child's eating and mealtime behaviours.
Conclusion: A single session, early intervention, group education programme for families with children with problem eating and mealtime behaviours is appropriate and effective. Therefore, early intervention group education programmes should be considered as a strategy for this client group.
(13.3). This article include additional information on the regression-discontinuity design, including an example.
Abstract: This Methodological Brief introduces the reader to the regression discontinuity design (RDD), which is a method that when used correctly can yield estimates of research treatment effects that are equivalent to those obtained through randomized control trials and can therefore be used to infer causality. However, RDD does not require the random assignment of individuals to treatment and control groups, making it very attractive for applied researchers in educational settings. This Brief introduces the method, discusses applications and limitations, and illustrates an idealized example as well as some potential pitfalls and their relevance to the context of gifted education research.
(13.4). This is an example of a study that used a multiple-baseline design.
Abstract: This study evaluated the effects of visual performance feedback (VPF) on teacher use of behavior-specific praise. In addition to receiving individual VPF, teachers participated in group consultation focused on increasing competence in the use of behavior-specific praise. Three general education elementary teachers and six students participated in the study. Classroom peer composite data were also collected. Teacher and student behaviors were monitored across baseline and VPF conditions in a multiple baseline design. The results indicated that VPF resulted in an increase in behavior-specific praise for participating students across all teachers relative to baseline. Additionally, teachers increased their use of behavior-specific praise with classroom peers. The findings highlight the need for direct assessment of intervention implementation and for the collection of peer data to identify collateral intervention effects.