Experimental vs. Quasi-Experimental Research Evaluating

Experimental vs. quasi-Experimental research

Evaluating Client Profile

There are a number of differences between experimental and quasi-experimental research. For experimental research, there are a few basic things that one would need. First of all, a hypothesis for a causal relationship is needed as well as a control group and a treatment group. The next thing needed is a way to eradication confounding variables that could have the potential to ruin the experiment and stop them from illustrating the causal relationship. Larger groups are also important and they should have a carefully sorted constituency -- preferably randomized so that accidental differences will not ruin the experiment.

Trochim (2006) notes that experimental designs are the most rigorous of all the research design methods and all other methods are judged in comparison to the experimental design. If one can implement an experimental design well, and, Trochim (2006) emphasizes the word "if," the experiment has the potential to be the strongest design in regards to internal validity (2006). He states, basically: "If X, then Y" (2006) -- or to put it in much simpler terms: "If the program is given, then the outcome occurs" (2006). Yet, this is still not enough. To really show a causal relationship, one has to address (simultaneously) these two propositions: "If X, then Y" and "If not X, then not Y" (2006). More basic again: "If the program is given, then the outcome occurs" and "If the program is not given, then the outcome does not occur" (2006).

When one or more of these elements is missing, the experiment is not a true experiment, but rather it is considered a quasi-experiment. Quasi-experiments want to find a causal relationship, however, the researcher may not have the ability to control all of the factors that could potentially affect the outcome of the experiment. Trochim (2006) states that a quasi-experimental design is one that looks a bit like an experimental design but lacks the key ingredient -- random assignment. He notes that his mentor [Don Campbell] used to refer to quasi-experiments as "queasy" (2006) experiments because they give the experimental purists a queasy feeling.

With respect to internal validity, they often appear to be inferior to randomized experiments. But there is something compelling about these designs; taken as a group, they are easily more frequently implemented than their randomized cousins (Trochim 2006).

The most important part of both experimental and quasi-experimental research is the measure of the dependent variable, which it allows for comparison. Some types of data are very straightforward, but there are other measures, but there are other types of data that are completely subjective. In cases where the data is highly subjective, the quasi-experiment will have to have various strategies to compare subjectivity.