Given Hapunda

104 causal-and-effect related questions. Examples of such designs are; pretest-posttest control-group design, and Solomon four-group design. Advantages of these are that they are stronger than the other designs in terms of establishing causality. They are also better than other designs at eliminating majority of the threats to external and internal validity. Some disadvantages though are that they are not always feasible or practical since they are not easy to set up and execute as they require random assignment of subjects to groups (experimental and control groups). The other main group of evaluation designs discussed in this chapter are the quasi-experimental designs. These are intervention studies employed to establish the causal relationship or impact of the intervention on the beneficiaries or target population without random assignment of subjects to treatment or control group. They are used when random assignment of subjects to groups is not feasible or practical. Examples of these are: Time series evaluation designs as well as pretest-posttest comparison-group design. One advantage of these is that they are more feasible and practical to set up than the true experimental designs. However, one disadvantage is that quasi-experimental designs lack random assignment of research participants to the intervention and control groups, hence are much weaker than the experimental in inferring causality. The last main category on the other hand are the non-experimental designs. These are basically used to describe and analyse the subjects and the situation in which they are found without any manipulation or intervention. Examples of non-experimental designs include, longitudinal study designs, cross-sectional study designs, case study designs, descriptive study designs, and explorative study designs. Hence, from the aforementioned, each design has advantages and disadvantages and each have suitable scenarios in which they can be used depending on the questions being answered. However, among the evaluation designs, the experimental designs are the strongest in terms of ascertaining causality as they have the least threats to external and internal validity. References Anich, K.V.,Witt, D.M.,Delate, T.,Shanahan, R.L.,Patel, R.J. (2005). A Descriptive Evaluation of Routine Complete Blood Count Monitoring in Patients Receiving Anticoagulation Therapy. Journal Thrombosis Thrombolysis ; 20(3):183-8. Doi: 10.1007/s11239-005-3842-8. Bryman, A. (2008). Social Research Methods. 3 rd edition, Oxford: Oxford University Press. Campbell, D.T. & Stanley, J.C. (1963). Experimental and quasi-experimental designs for research. Chicago: R. McNally. Coolican, H. (2014). Research methods and statistics in psychology. 6 th edition, East Susex: Psychology Press.