The first part of creating a quasi-experimental design is to identify the variables. The
quasi-independent variable is the variable that is manipulated in order to affect a dependent variable. In a time series analysis, the dependent variable is observed over time for any changes that may take place. One or more
covariates are usually included in analyses, ideally variables that predict both group membership and the outcome. These are additional variables that are often used to address
confounding, for example, by means of statistical adjustment or matching on an influential covariate. Once the variables have been identified and defined, experimental and control treatment procedures should then be implemented (assuming researchers are not studying nonmanipulable events like natural disasters) and group differences should be assessed. In an
experiment with random assignment, study units would have approximately the same probability of being assigned to the treatment and control conditions. As such, an aim of random assignment is to make the experimental and control groups as equivalent as possible by distributing known and unknown confounds evenly across treatments. In contrast, in a quasi-experimental design, assignment to a given treatment condition is based on something
other than random assignment. Depending on the type of quasi-experimental design, the researcher might have control over assignment to the treatment condition but use some criteria other than random assignment (e.g., a cutoff score on a reading test) to determine which participants are placed in the treatment and control conditions. Factors such as cost, feasibility, political concerns, or convenience may influence how or if participants are assigned to a given treatment conditions. Consequently, quasi-experiments, compared to true experiments, are subject to more concerns regarding internal validity. Many quasi-experiments use the "pre-post testing". This means that participants are assessed before they are exposed to the treatment and control conditions. And they are tested after the treatment and control conditions have been implemented. Pre-testing helps researchers identify confounds such as members of one group being heavier than the another in a diet study. If there are group differences on an important covariariate measured (e.g., weight, BMI) at the pre-test stage, the researcher can statistically control for that covariate after the post-test data have been collected. There are several types of quasi-experimental designs, each with different strengths, weaknesses and applications. These designs include (but are not limited to): they can be useful in areas where it is not feasible or desirable to conduct an experiment or randomized control trial. Such instances include evaluating the impact of public policy changes, educational interventions or large scale health interventions. The primary drawback of quasi-experimental designs is that they cannot eliminate the possibility of confounding bias, which can hinder one's ability to draw causal inferences. This drawback is often used as an excuse to discount quasi-experimental results. However, such bias can be controlled for by using various statistical techniques such as multiple regression, if one can identify and measure the confounding variable(s). Such techniques can be used to model and partial out the effects of confounding variables techniques, thereby improving the accuracy of the results obtained from quasi-experiments. Moreover, the developing use of
propensity score matching to match participants on variables important to the treatment selection process can also improve the accuracy of quasi-experimental results. In fact, data derived from quasi-experimental analyses has been shown to closely match experimental data in certain cases, even when different criteria were used. In sum, quasi-experiments are a valuable tool, especially for the applied researcher. On their own, quasi-experimental designs do not allow one to make definitive causal inferences; however, they provide necessary and valuable information that cannot be obtained by experimental methods alone. Shadish et al. (2002) suggested that researchers, especially those interested in investigating applied research questions, move beyond the traditional experimental design and avail themselves of the possibilities inherent in quasi-experimental designs. == Ethics ==