The term experimental design has been used differently by different authors. A look at the literature on the subject reveals that the term experimental design has been used to convey mainly two different, though interrelated meanings. In the first category, are those who have used the term in general sense to include a wide range of basic activities for carrying out experiments, that is, everything from the formulation of a hypothesis to drawing conclusions (Pukelsheim, 2006). The second definition of the term is comparatively restricted. The term is used in the ‘Fisher definition’, that is, to state statistical principles underlying experimental designs and analysis, where an experimenter can schedule treatments and measurements for optimal statistical efficiency (Pukelsheim, 2006). It contains activities such as selection of factors and their levels of manipulation, identification of extraneous variables that need to be controlled, procedures for handling experimental units, selection of criterion measures, selection of specific design, and data analysis.
Though there are different objectives of designing an experiment, it may not be out of proportion to state that the most important function of experimental design is to control variance. According to (Ryan, 2006, p. 56), “experimental research design is the plan, structure, and strategy of investigation, conceived so as to obtain answers to research question to control and variance”. The first part of the statement emphasizes upon the objective, that is, to obtain answer to question. The most important function of design is the strategy to control variance.
In behavioral sciences, especially in education and social research, it is not always possible to exercise full control over the experimental situation. For example, the experimenter may not be at liberty of assigning subjects randomly to the treatment groups or the experimenter may not be in a position to apply the independent variable whenever or whoever he or she wishes. Collectively, such experimental situations form part of quasi experimental designs (Broota,1989). The other type of experimental design is single case experimental design. This type of design, observations or measurements is made on an individual subject. On the other hand, in experimental design, groups of subjects are observed and the experimenter has full control over the experimental situation (Broota,1989).
Included in this category are all those designs in which a large number of experimental units or subjects are studied, the subjects are assigned randomly to the treatment groups, independent variable is manipulated by the experimenter, and the experimenter has complete control over the scheduling of independent variables. There are three types of experimental designs namely between subjects design, within subjects design, and mixed design. In the between subjects design, each subject is observed only under one of the several treatment cognitions (Krauth, 2000). In the within subjects design or repeated measures design, each subject is observed under all the treatment conditions involved in the experiment (Krauth, 2000). Finally, in the mixed design, some factors are between subjects and some within some within subjects (Krauth, 2000).
Quasi Experimental Design
All such experiments in which experimenter does not have full control over the assignment of experimental units randomly to the treatment conditions or the treatment cannot be manipulated are collectively referred to as quasi experimental design (Krauth, 2000). For example, in an ex-post-facto study, the independent variable has already occurred and hence, the experimenter studies the effect after the occurrence of the variable.
Let us consider an example of a quasi experimental design. Suppose an investigator is interested in evaluating the efficacy of three methods of instruction on the achievement scores of 10th grade students. Suppose for the aforementioned problem, the investigator cannot draw a random sample of 10th grade students because the school administration cannot allow him to regroup the classes. Ideal conditions being unavailable, the experimenter finds three schools, following the same curriculum and each providing instructions using one of the three methods. He administers an achievement test to the subjects from the three schools and compares the outcome to evaluate the effect of each method of instruction on achievement scores. It is observed from the example that the investigator in the second condition did not have control over the selection of subjects and over the assignment of subjects to the treatments. Further, the investigator could not control the independent variable (providing instructions using the three methods) as the independent variable had already occurred. This experiment is a typical example of a quasi experiment. Random assignment of subjects to the treatment groups was not possible in the quasi experiment and it was, therefore, handicap in controlling secondary variables (Cresewell, 2011).
These investigations are as sound as experimental investigations, but are less useful in drawing causal relationships between independent and dependent variables. The statistical tests applied to data obtained from quasi experimental designs are same to the data acquired from experimental designs. It is possible to perform even analysis of covariance of data of such studies. However, conclusions cannot be made with as much confidence as from the studies employing experimental designs because some of the assumptions underlying the statistical test are violated in quasi experiments. Besides this, the experimenter has no control over the secondary variables. Though quasi experimental designs have various limitations, nevertheless these are advantageous in certain aspects. It is possible to seek answer to several kinds of problems about past situations and those situations which cannot be handled by using experimental designs (Cresewell, 2011).
Single Case Experimental Design
Single case experimental designs are an outgrowth of applied clinical research, especially in the area of behavior modification. In this type of design, repeated measurements are taken across time on one particular individual to note the subtle changes in behavior. Single subject or single case experimental designs are the extension of the before-after designs. The single case experimental designs do not lend themselves to clear statistical analysis and hypothesis testing and have not been formalized as in the case of experimental designs. The experimenter relies on the convincingness of the data. In these designs, the experimenter cannot control the order effects. Moreover, the designs do not provide a good basis for generalizations (Cresewell, 2011). However, single case experimental designs provide us with such information about human behavior that is not always obtainable in group designs (Cresewell, 2011).
This paper has noted that “experimental research design is the plan, structure, and strategy of investigation, conceived so as to obtain answers to research question to control and variance” (Ryan, 2006, p. 56). There are three types of experimental designs namely between subjects design, within subjects design, and mixed design. In addition, all such experiments in which the experimenter does not have full control over the assignment of experimental units randomly to the treatment conditions or the treatment cannot be manipulated are collectively referred to as quasi experimental design. In the other hand, repeated measurements are taken across time on one particular individual to note the subtle changes in behavior.
Broota, D. (1989). Experimental Design In Behavioural Research. New Delhi: New Age International.
Cresewell, J. (2011). Educational Research: Planning, Conducting, and evaluating quantitative and qualitative research. New York: Pearson.
Krauth, J. (2000). Experimental Design: A Handbook and Dictionary for Medical and Behavioral Research. Amsterdam: Elsevier.
Pukelsheim, F. (2006). Optimal Design of Experiments. Philadelphia: SIAM.
Ryan, P. (2006). Modern Experimental Design. New York: John Wiley & Sons.