Microsoft Word research method fm doc

c) Case-control studies:
Group of subjects with the disease (cases) and group of 
subjects without the disease (controls) are identified. Information, about previous exposures 
are obtained for cases and controls, and frequency of exposure compared for the two groups. 
 
Strengths and limitations of the case-control study design
 
Strengths: 
ƒ
Is relatively quick and inexpensive 
ƒ
Is optimal for the evaluation of rare diseases. 
ƒ
Can examine multiple etiologic factors for a single disease. 
 
Limitations: 
ƒ
Is inefficient for the evaluation of rare exposures 
ƒ
Cannot directly compute incidence rates of disease in exposed and non- exposed 
individuals. 
ƒ
Is particularly prone to bias compared with other analytic designs, in particular, 
selection and recall bias. 

---

Research methodology 
31
Intervention studies 
In intervention studies, the researcher manipulates a situation and measures the effects of 
this manipulation. Usually (but not always) two groups are compared, one group in which the 
intervention takes place (e.g. treatment with a certain drug) and another group that remains 
‘untouched’ (e.g. treatment with a placebo). 
The two categories of intervention studies are: 
• 
experimental studies and
• 
quasi-experimental studies
1. Experimental studies 
An experimental design is a study design that gives the most reliable proof for causation. In 
an experimental study, individuals are randomly allocated to at least two groups. One group 
is subject to an intervention, or experiment, while the other group(s) is not. The outcome of 
the intervention (effect of the intervention on the dependent variable/problem) is obtained by 
comparing the two groups. A number of experimental study designs have been developed. 
These are widely used in laboratory settings and in clinical settings. For ethical reasons, the 
opportunities for experiments involving human subjects are restricted. However, randomised 
control trials of new drugs are common. 
At community level, where health research is frequently undertaken, we experience not only 
ethical but also practical problems in carrying out experimental studies. In real life settings, it 
is often impossible to assign persons at random to two groups, or to maintain a control group. 
Therefore, experimental research designs may have to be replaced by quasi-experimental 
designs.