The design of a quasi-experiment constitutes a study in which one has limited control over the distribution of the treatments or factors being studied. The unique feature in this empirical study is that it is short of random task (Achen 66). In addition, it involves time series analysis. The main component of constituting a quasi-experimental design is to recognize the variables. To start with, quasi-independent variable are the x-variable, the variable that is manipulated to influence a dependent variable. In this situation, x-variables are normally a grouping variable of various levels. Grouping vattiables refers to two or more organized groups such as a treatment group and a placebo or control group. The expected outcome is always the dependent variable, which is the y-variable
First limitation of a quasi-experiment is that it lacks of proper randomization makes it statistically meaningless (Achen 67). For instance, a quasi-experimental design does not pay attention to any pre-existing factors or influences outside the experiment which can affect the results. Secondly, a quasi experiment designed to investigate the effects of various educational programs on two groups of pupils, for instance, may produce conflicting outcomes such as one program is more effective than the other. These results cannot stand up to thorough statistical analysis since the researcher willcontrolother factors that may have influenced the outcome. One group of children may have been slightly more intelligent or motivated. Without some form of pre-testing or random selection, it is hard to judge the influence of such factors.
In conclusion, despite immense limitation in quasi-experimental design, they can be useful particularly in conditions in which true experiment is irrelevant. They are important in obtaining a generalized overview which very significant in making a follow up with aquantitative research study which focuses on the fundamental reasons for the outcome got in a quasi-experiment.