Two Experimental Designs Applied in the Management Coronary Artery Disease - Research Paper Example

Problem ment Over the of 18 months, will develop, implement, and evaluate a disease management program for coronary artery disease patients recently discharged from a hospital. Two sub-problems will be investigated: 1. Does the gender of the patient play a role in adhering to the strategy of a health coach? 2. Does a health coaching course reduce readmissions for patients with coronary artery disease? Abstract This design paper deals with the two experimental designs to be applied in the management Coronary Artery Disease. Out of seven designs suggested for the experiment, Solomon Four Group Design and Static Group Comparison Design have been discussed. While Solomon Four Group Design has all salient features of an experimental design, the Static Group Design is found to be less suitable for the study proposed. Solomon Four-Group Design This is one of the most robust designs for quantitative research that can be used in Coronary Artery Disease management. It is one of the three main designs recommended for use in ‘true experimental’ research. It can also be used in quasi-experimental studies. Though there are some obstacles in using this design, advantages that accrue far outweigh the obstacles. The design combines the pretest-posttest control group design and the posttest only design. The combination gives the added advantage of testing and control for instrument reactivity. The researcher can examine both the outcomes of testing and interaction testing and treatment. The researcher can also evaluate the combined effect of maturation and history with the comparison of ‘posttest only control group’ and ‘pretest control group’. The subjects are randomly divided into four groups. While two of them will be receiving actual treatment (for intervention), the other two will not. (for control) All the four groups are posttested while one of them will be only pretested. A modified version of this will have only one control group given both pretest and posttest. (McGahee and Tingen S, 2009)See Table 1 below for schema of the design. Table 1: Solomon Four-Group Design (McGahee and Tingen S, 2009) Group Pretest Treatment Posttest 1 O1 X O2 2 O3   O4 3   X O5 4     O6 O=Outcome Measure (observation) . (McGahee and Tingen S, 2009) The above experimental design enables assessment of presence of pretest sensitization. In this case, outcome of posttest is not only influenced by intervention i.e treatment but also the pretest. (McGahee and Tingen S, 2009) Key (1997) says this design is perhaps the most powerful experiment as it is an extension of pretest and posttest control group and intended to minimize the pretest effects. See Table 2 below for comparison of Solomon Four Group Design with other two. True Experimental Design - greater control and refinement, greater control of validity Aim of the Research Name of the Design Notation Paradigm Comments To study the effect of an influence on a carefully controlled sample Pretest-posttest control group R - - [ O » X » O         [ O » - » O This design has been called "the old workhorse of traditional experimentation." If effectively carried out, this design controls for eight threats of internal validity. Data are analyzed by analysis of covariance on posttest scores with the pretest the covariate. To minimize the effect of pretesting Solomon four-group design R - - [ O » X » O         [ O » - » O         [- » X » O         [ - » - » O This is an extension of the pretest-posttest control group design and probably the most powerful experimental approach. Data are analyzed by analysis of variance on posttest scores. To evaluate a situation that cannot be pretested Posttest only control group R - - [  X » O         [ - » O An adaptation of the last two groups in the Solomon four-group design. Randomness is critical. Probably, the simplest and best test for significance in this design is the t-test. Leedy, P.D. (1997). As in the problem statement above, patients who have been already discharged and monitored for their life style adaptations can be given questionnaire for relevant queries and their responses can be subjected to the above Solomon Four Groups Experiment for ascertaining their health status vis-à-vis CAD after 18 months of their discharge. The questionnaire will also include the two queries relating to the role of health coach in mitigating the impact of CAD and to gender response. Static-Group Comparison Design This design has two groups of experimental group receiving treatment and control group that does not receive treatment. The experimental group’s performance on ‘posttest’ will be compared with that of the control group. It would appear as follows. X O …………….. O The dotted line indicates that the participants have not been randomly selected. The two main threats to the validity are (1) differential selection and (2) experimental mortality. Differential selection arises due to the groups having divergent characteristics initially. Experimental mortality refers to likelihood of participants dropping out. Hence it is highly essential to collect maximum possible information on the group members’ background. (Mertens, 2004 p137) The design can be depicted as follows Where X denotes the treatment group and blank space beneath X indicates control group, the O’s represent the posttest. This design has the problem of validity in that there is no empirical evidence to show that the participants are of identical characteristics. They can be however made comparable by the strategies such random assignment, matching the groups on extraneous variables, and using them as blocking factors or covariates. The following are the likely threats to the validity of this design. (Friel M) Potential Threats to Validity in a Static-Group Comparison Design Potential Threats to Validity Effect On The Design Internal Validity History + Maturation ? Testing + Instrumentation + Regression + Selection  Mortality  Interaction: selection & maturation  External Validity Interaction: testing & X NA Interaction: selection & X  Reactive arrangements NA Multiple –X interference NA (Friel M) This static group comparison design has some limitations for the study in the problem stated above. In the first place, non-identical pattern of respondents may not be relevant as all of them are CAD patients. But they may not be of equal health status each having a different problem both before and after their discharge. However the strategies suggested above for harmonization cannot be applied in the case of problem statement above. Conclusion The above discussion would show that Solomon Four Groups Design is better suited for the study of the problem statement as it has been validated as a reliable one for comparison of the outcomes after 18 months of the study to be undertaken. References Friel M Charles, Assessing the Goodness of a Research Study, Retrieved 25 April 2009 Key P James (1997) Module R13, Experimental Research and Design, Research Design in Occupational Education, Retrieved 25 April 2009 Leedy, P.D. (1997). Practical research: Planning and design (6th ed.). Upper Saddle River, NJ: Prentice-Hall, Inc., p. 232-233.cited in Key P James (1997) Module R13, Experimental Research and Design, Research Design in Occupational Education, Retrieved 25 April 2009 McGahee Thayer and Tingen S Martha, 2009, Qualitative Methods, The Use Of The Solomon Four-Group Design In Nursing Research, Southern Online Journal of Nursing Research, Volume 9 (1) Mertens M Donna (2004) Research and evaluation in education and psychology: integrating diversity with quantitative, qualitative, and mixed methods, Sage, Edn 2, p 137 Read More