TRIAL DESIGN SETUP: Doctors, Nurses, and Researchers work together with statisticians, trial manager and representatives from Pharmaceutical companies, if relevant, to design the best possible trial[5,6].

Who is going to be recruited in the trials: Eligibility- Inclusion and Exclusion Criteria?

Typical inclusion Criteria:
*  Subject/Participants must have disease of Interest.
*  Subject must have a certain amount of disease.
*  Subject must understand study and agree to participate.

Typical Exclusion Criteria:
*  Subject must not be on active treatment.
*  Subject must not be allergic to intervention.
*  Pregnancy, Breastfeeding, Child.

Study procedure:
*  Divide your study patients in to groups.
* Administer the study and control interventions to the respective groups.
*  Measure the Outcome.


[1]. Descriptive trials: Hypothesis generation.

[2]. Analytical or Observational trial:Relate associations between causes and diseases.

[3]. Experimental trials:  Demonstrate efficacy and Safety.

Descriptive trials:  Useful in generating hypothesis, simple and inexpensive. Describe and document Characteristics of Human disease, Personal experience, unexplained phenomena, and innovative treatments[2,6,7].

Hypothesis:  The hypothesis is a clear statement of what is intended to be investigated. It should be specified before research is conducted and openly started in reporting the results. This allows identifying the research objectives / its relation to both the problem statement and literature review.

Types of hypothesis
[1] Null hypothesis—Designated by HO or HN

[2] Alternative hypothesis-- Designated by H1

Null hypothesis:Represents a theory that has been put forward, either because it is be-lived to be true or because it is to be used as a basis for argument, but hasn’t been proved.

Alternative hypothesis: The alternative hypothesis is a statement of what a hypothesis is test is set up to establish. Opposite of  Null. Only reached if HO is rejected.

Let’s see – In a Clinical trial of a new drug, the null hypothesis might be that the new dug is no better, on average, than the current drug.

We would write HO: There is no difference between the two drugs on average.

We would write H1: The new drug has a different effect, on average, compared to that of the current drug.

Case series studies: It is an uncontrolled retrospective review of a group of patients. It is a cross sectional in nature as treatment and outcome are determined simultaneously at a single point of time. These studies are relatively in expensive. Results can be obtained quickly. It is most hypothesis generator.

Analytical Trial: Seek causes, etiologies, predictions, better diagnosis, assess therapy. The Investigator is observing nature rather than controlling treatment allocation[6,7].

* Case control study – Looking backward.
* Cross sectional  Study– At present
* Cohort study – Looking forward

Case control study: Begins with cases (People with the disease). Go retrospectively from the disease to the risk factor. Select controls from the same population. Further data are then collected on those individuals and then groups are compared to find out if other characteristics are also different between groups. Determine the presence or absence of risk factors in two populations. Association determined by the odd ratio ([>1).

Cross sectional Study: Begins with a study population. Classify the population in terms of the presence or absence of the outcome, determining the prevalence of the abnormality (e.g community survey of asymptomatic bacteria). Determine what risk factors are present in two groups[13,14]

Advantages—Efficacy, with all information collected at the same time often from immediately available sources.

Prevalence: Measures how much of some disease or condition there is in a population at a particular point of time. Prevalence is calculated by dividing the number of persons with the disease or condition at a particular time by the number of individuals examined.

Incidence: Measures the rate of occurrence of new cases of disease or condition[11,12]. Incidence is calculated as the number of new cases of a disease or conditions in a specified time period(Usually a yr) divided by the size of population under consideration who are initially disease free.

Cohort study:  A cohort study is a group of people who share a common characteristics or experience within a defined period (e.g are born, are exposed to a drug/vaccine). Go prospectively from risk factors to the outcome. Measures of outcome often requires years of follow up. More expensive than case control studies. Association determined by the relative risk (>1).

Experimental trials /Randomized Clinical Trials (RCT): Randomization assurance that subject populations are similar in test and control groups is best attained by randomly dividing a single sample population in to groups that receive the test or control treatments. Randomization avoids systematic difference between groups with respect to know or unknown base line variables that could affect outcome. Participants allocated randomly to either receive a specific intervention. Randomization and blinding are the two techniques usually used to minimize the chance of such bias and to ensure that the treatment and control groups are similar at the start of the study and are treated similarly in the course of the study.

Bias:  The systematic tendency of any aspects of the design, conduct, analysis and interpretation of the results of the clinical trials to make the estimate of a treatment effect deviates from its true value.

Compare outcomes (etiology, Cause, efficacy) or trial group and control group following an intervention. Most powerful tool assess efficacy. Controlled, randomized, double-blind trails are the ‘’GOLD STANDARD’’ in clinical research.



Based on



Type of intervention

Therapeutics; Preventive


Unit of Randomization

Individual ; community



Parallel; Cross Over; Factorial


Sample size

Fixed; Sequential



Fixed; Adaptive



Single; Double; Triple blinding

There are three basic ways to generate a randomization scheme for an RCT.

1.      Simple randomization

2.      Block randomization

3.      Stratified blocks

Simple randomization: The simple randomization, which is equivalent to tossing a coin for each subject that, enters a trial. The heads get the experimental treatment while the tails receive the placebo. A computerized or tabulated random number generator is generally used. It is simple and easy to implement and treatment assignment is completely unpredictable[15].

Block randomization: It is very popular and balanced within each block. For a trial of n treatments, the total number patients are divided into m blocks of size 2n. Then, each of the m blocks is randomized such that n patients are allocated to each of the treatments. One can then choose the blocks randomly. The INVEST study followed this scheme of block randomization[16].

Stratified blocks:  A third approach to randomization involves “stratified blocks.” Because a trial may not be considered valid if it is not well balanced across the prognostic factors, stratification of patients is done to produce comparable groups with regard to certain characteristics (e.g., gender, age, race, disease severity). This approach produces valid statistical tests in all stratified subgroups (e.g., high-risk subgroups in the ALLHAT trial)[17,18]



Subscribe to Pharmatutor Alerts by Email