Quasi-experimental study designs

The only study conducted in the UK (Forder et al, 1996) employed a retrospective, quasi-experimental design in which patients from an open-label study of sertraline were compared with age- and gender-matched patients prescribed TCAs in a primary care setting. The study found that sertraline was more effective than TCAs (87% versus 74%,... 

Recently, a quasi-experimental design was used to study British Columbia s reference pricing policy for five therapeutic classes of drugs to determine if a worsening of health outcomes could be detected after implementation of the reference pricing policy. The... 

These results need to be treated with some caution for four reasons. First, some data are purely correlational, indicating associations between variables, not necessarily causation or causal direction. Second, even longitudinal evaluation studies tend to be of a quasi-experimental nature because of inability to control the influence of many variables, which makes the interpretation of results difficult (Cox et al. 2000). Nevertheless, there are examples of well-designed studies (Jackson 1983). 

This study used a quasi-experimental design with quantitative data (Anderson, 2000 CresweU, 2003) that used two previously designed questionnaires to solicit information related to several affective factors from second-year college chemistry students who were involved in a problem-based learning (PEL) chemistry laboratory corrrse. In order to make comparisons in particular instances, information was also solicited from a group of students enrolled in a traditional laboratory course that involved carrying out specific laboratory activities based on instructions that were provided. With the small sample size and the likelihood of non-normal distribution, any differences between the treatment and comparison groups and between pre- and posttests were analyzed with nonparametric statistics. 

---