The Study
The study that is being described is a randomized factorial trial of fall prevention in elderly home-owners. It was designed to evaluate the efficacy of three fall prevention treatments (group exercise, home hazard management, and vision improvement) and explore how they interact with one another.
Two-Group Strategy
An experiment using both control and experimental groups is known as a two-group strategy. Contrary to the study group, the control group typically does not receive any treatment. Under such circumstances, the researcher usually seeks to know whether a treatment done has effects or not. On the other hand, a factorial research design is used when a researcher wants to have two or more factors with distinct possible outcome or values and takes all the possible combinations of the values in all the factors (Collins, Murphy & Strecher, 2007).
Factorial Design
Under experimental designs, a factorial design can be used for the establishment of the groups within the independent variables. For instance, a two-factor design can be used to categorize the independent variables alone (Collins, Murphy & Strecher, 2007). Based on the research conducted by Day and colleagues, the factorial design was used to assign respondents into eight groups that were classified according to the occurrence or absence of the three interventions (group-based exercise, home hazard management, and vision improvement). That case, the subjects are equally and randomly assigned to each of the possible categories (Day et al., 2002). Consequently, a null outcome can be realized if the result is the same regardless of the combination of values or levels. However, most experiments with factor design produce alternative outcome with one independent variable performing lower than the rest. On a different note, the research reveals that a two-group design was implemented using an "adaptive biased coin" technique to enable the balance of the numbers for each group (Day et al., 2002).
Variables in the Experiment
The independent variables that were used in the experiment include group-based exercise that entailed strength and balance, home hazards, and vision improvement. These variables were manipulated through in the seven categories of the subjects to give the measurable outcome. Secondly, the dependent variables are the factors that were measured as an outcome or the target risk factors upon the treatments in the experiment. For instance, change in levels of risk factors such as falls, increase in strength and balance, and improved flexibility (Day et al., 2002).
Effects and Interactions of Factorial Design
Interactions usually occur when one independent variable has no constant effect at the level of other independent variables. Thus, the conclusion that is normally arrived at does not fully elaborate the outcome of the whole factorial experiment (Collins, Murphy & Strecher, 2007). Based on the experiment conducted on the research, it is identified that there were no interactive effects of the interventions on fall outcome. However, the interventions implemented were additive. Nevertheless, a relative poor compliance with exercise sessions especially at home was indicated during the experiment which was not at the same constant level as other independent variables (Day et al., 2002).
Random Samples
Based on the experiment conducted, the researchers randomly assigned subjects using the "adaptive biased coin" in order to ensure balancing of numbers within the groups. Thus, random samples were recruited (Day et al., 2002). However, the various limitations that were noted include insufficient intensity for the used interventions which resulted in limited effects of interventions on falls outcome. Furthermore, such outcome was noted as a result of the small and wrong type of home hazard modifications. This was coupled with the low numbers of participants that received the vision impairment treatment and the improvement in visual acuity in the control group (Day et al., 2002).
References
Collins, L. M., Murphy, S. A., & Strecher, V. (2007). The multiphase optimization strategy (MOST) and the sequential multiple assignment randomized trial (SMART): new methods for more potent eHealth interventions. American journal of preventive medicine, 32(5), S112-S118.
Day, L., Fildes, B., Gordon, I., Fitzharris, M., Flamer, H., & Lord, S. (2002). The randomized factorial trial of falls prevention among older people living in their own homes. BMJ, 325(7356), 128.
