- Observational Study
- Experimental or Interventional Study
1. Observational Study
Observational Study is a study in which the researcher only observes what is happening or what has happened in the past and tries to draw conclusion based on these observations. In observational studies, researchers don’t assign choices; they simply observe choices and their results. Observational studies can be retrospective (study things that happened in the past) or prospective (identify subjects in advance and collect data as events unfold)
Types of Observational Study Design:
- Descriptive Study Designs
- Case Report: Single Case
- Case Series: Collection of similar cases
- Cross-sectional (descriptive): Single sample from a larger population – there is no comparison
- Analytical Study Designs
- Cross-sectional (analytical): Single sample from larger population- compares two or more groups in the sample
- Case-control: Compares risk factors between diseased (cases) and non-diseased (controls) groups
- Cohort: Compares outcomes between groups exposed and non-exposed to risk factors for a disease
- Ecological Study: correlational study design with populations as the unit of study
Experimental studies are the studies designed to assess the effect of particular variables on a phenomenon by keeping the other variable constant or control. The researcher has control over the exposure; he/she not only just observes the situation and records it; but also manipulates the situation and measures the effect of manipulation.
- As per control: Randomized Control Trial/Non-randomized Control Trial
- As per Blinding: Single/Double/Triple Blind
- As per Area:
- Field: study carried out into different groups and the intervention is performed on the individual basis.
- Community trial: study is conducted into different groups and intervention is performed on community basis; unit of analysis is entire communities such as VDCs, districts, etc.
- Clinical: Investigator allots the subjects to different groups – intervention versus non-intervention; Randomized Control Trial
- Lab: studies conducted in lab settings
- Differences between Observational and Experimental Studies
Cross-sectional study is generally an observational study in which both exposure and outcomes are measured at the same time, information is obtained from the study subjects only once no follow up is required; provides a snap shot of the health problem of the population at a particular point of time. The data of cross-sectional study can be used to assess the prevalence of acute or chronic conditions in a population. Usually, cross-sectional studies are descriptive by nature, only sometime (rarely) analytic.
Types of cross-sectional study:
- Descriptive cross-sectional
- Analytical cross-sectional
Case control studies, often called “retrospective studies” are a common first approach to test causal hypothesis. This design is generally used to find out the cause/exposure for rare diseases. There are three distinct features of this study design:
- Both exposure (cause) and outcome (disease) have occurred before the start of the study
- The study proceeds backward from effect to cause
- It uses a control or comparison group to support or refute an inference
Cohort study is an observational analytic study, where enrolments of subjects in to the study are based on their exposure characteristics or membership in a group or healthy population, where disease, death or other health-related outcomes are ascertained and then compared. A group of disease free population or at risk population is followed over time-period to find out the relationship or an association between risk factors/cause and disease/effect based on their current exposure status. This design is generally used to find out the disease/effect for rare cause/exposure.
The distinguishing features of cohort studies are:
- Cohorts are identified prior to the appearance of the disease under investigation
- The study groups, so defined, are observed over a period of time to determine the frequency of disease among them
- The study proceeds forward from cause and effect
D. Randomized Controlled Trial (RCT)
RCT is a systematic study on investigating agent (drug/vaccine) in a human subject in order to discover or verify the effects or to find out the adverse effect of the investigating agent in order to determine the efficacy and safety. It is a prospective experimental study using primary data generated in the clinical and controlled environment following strict protocol.
Basic steps in conducting RCT:
- Drawing up a protocol
- Selecting reference and experimental populations
- Randomization
- Manipulation or intervention
- Follow-up
- Assessment of outcome
Figure: Design of Randomized Controlled Trial (RCT)
Concept of Blinding
The potential for bias is an important issue in experimental studies. The protection against these forms of bias is best achieved by use of blinding. Blinding is a process of assigning treatment to participants in such a way so that actual treatment assignment is not known to certain persons. Blinding can be done in three ways:
1. Single Blinding: The trial is so planned that the participant is not aware of whether he/she belongs to the study group or control group.
2. Double Blinding: The trial is so planned that neither the doctor nor the participant is aware of the group allocation and the treatment received.
3. Triple Blinding: The participant, the investigator and the person analyzing the data are all blind.