Vol 6, Issue 3, 2013 ISSN - 0974-2441

Review Article

OVERVIEW OF RANDOMIZED CONTROLLED TRIALS

DR. RATHAI RAJAGOPALAN1, DR. PRIYADARSHINI M.DEODURG2, DR. SRIKANTH*2
1Department of Pharmacology, M.S.Ramaiah medical college, MSR Nagar, MSRIT post, Bangalore, 560054, India, 2Department of
Pharmacology, Khaja Banda Nawaz institute of medical sciences, Gulbarga, 585104, India.Email: pharmacsrikanth@gmail.com
Received:19 May 2013 , Revised and Accepted:16 June 2013
ABSTRACT
Randomized controlled trials are considered to be the gold standard in clinical studies to establish level of evidence in medical research. But, they
are not easy to conduct and various other aspects have to be looked into. Randomization offers each enrolled subject equal chance of being allocated
to the intervention and the control groups. Randomized control trial (RCT) is most powerful tool in clinical research. In this, subjects are assigned
to different groups of interventions by chance for comparison. RCT is only study design which can help us evaluate a new treatment. By assigning
participants to different intervention groups by chance, comparison between the interventions groups is made. Purpose of randomization is to
make the treatment groups comparable, eliminates the source of and it ensures that the difference in groups is only due to trial treatments. In this
article, we review randomized control trial with special emphasis on various types of randomized controlled trials, their characteristics, the process
of randomization, and advantages and drawbacks of randomized controlled trials.
Keywords: Randmized controlled trials, study design, randomization, clinical research
INTRODUCTION
Randomized controlled trial is defined as “An epidemiological
experiment in which subjects in a population are randomly allocated Intervention
Outcome

into groups, usually called study and control groups, to receive or group No outcome

not receive an experimental preventive or therapeutic procedure,

maneuver, or intervention. The results are assessed by rigorous STUDY
POUPULATION
comparison of rates of disease, death, recovery, or other appropriate Control
Outcome

outcome in the study and control groups” [1]. group

No outcome

The terms "Randomized Control Trial" and “randomized trial” are

often used synonymously, but some authors distinguish between Direction of enquiry
"Randomized Control Trial" which compare treatment groups with
control groups not receiving treatment (as in a placebo-controlled
study), and "randomized trials" which can compare multiple
treatment groups with each other [2]. Fig. 3: Outline of an intervention trial [7]

First published RCT in medicine is credited to Sir A. Bradford Hill Nonrandomized controlled
[3], an epidemiologist for England’s Medical Research Council.
Randomization as a basic principle of experimental design in the A study where participants have been assigned to the treatment,
1920s was developed by RA Fisher who presented randomization as procedure, or intervention alternatives by a method that is not
an essential ingredient of his approach to the design and analysis of random. The investigator defines and manages the alternatives. This
experiments, validating significance tests predominantly in is an experimental study in which people are allocated to different
agricultural research [4]. interventions using methods that are not random. In these studies,
allocation to different groups is done arbitrarily. This kind of study
RCTs are now recognized as optimal method for “rational
design may sometimes overestimate the advantages of one
therapeutics” in medicine [5]. To improve the reporting of RCTs in
treatment over other [8].
the medical journals, Consolidated Standards of Reporting Trials
Non-randomized trials are a type of quasi-experimental design. Non-
(CONSORT) Statements were published regularly, the last being
randomized clinical trials are sometimes referred to as “quasi-
published in 2010 by an international group of scientists and editors
experimental” clinical trials or “non-equivalent control group”
which have become widely accepted to improve the reporting of
designs because the characteristics of subjects in non-randomized
RCTs [6].
groups will tend to be non-equivalent. The estimation of
Intervention trials (controlled trials) intervention effects in non-randomized clinical trials may be biased
if group differences in subject characteristics are not controlled for
The term “intervention” refers to treatment and in its much wider in the data analysis
sense includes prevention strategies, screening programs, diagnostic
tests, interventional procedures, educational models and the setting When is it appropriate to use a non-randomized trial design?
in which health care is provided. In a intervention trial primary
exposure under study is applied by the investigator. These are the  When the act of random allocation may reduce the
only experimental form of epidemiologic studies, though they are effectiveness of the intervention (Occurs when the
also observational in that subjects remain in their ordinary habitats. effectiveness of the intervention depends on the
In an intervention trial, the investigator decides which subjects are participant’s active participation which is influenced by their
to be exposed and which are not. beliefs and preferences)
 When it would be unethical to do random allocation
 Dr. Srikanth et al.
Asian J Pharm Clin Res, Vol 6, Issue 3, 2013, 32-38

 When it is impractical to do random allocation (e.g. cost or Randomized Controlled Clinical Trial
convenience factors)
Includes Diagnostic, Therapeutic, Prophylactic, Devices, Procedures,
 When there are legal or political obstacles to random
Regimens, Protocols. Concerned with evaluating therapeutic agent,
allocation
mainly drugs e.g. Evaluation of nitrates in reducing cardiovascular
mortalityA simplified diagram of a Randomized Controlled Clinical
Randomized controlled trial
Trial is depicted in figure 1, and the flow chart according to
CONSORT statement for reporting a RCT is depicted in figure 2.
Randomized controlled trials (RCTs) are considered the “gold
standard” in medical research since they offer the best answers
about the effectiveness of different therapies or interventions. The
Study population
important aspect of this study design is that the patients are
randomly assigned to the study all groups that help in avoiding bias Inclusion/exclusion
in patient allocation-to-treatment that a physician might be subject criteria
to. It also increases the probability that the differences between the Randomized to two or
groups can be attributed only to the treatment(s) under study [8]. more groups

Types of Randomized Controlled Trials

Intervention
 Randomized Controlled Clinical Trial: Diagnostic, group
Control group

Therapeutic, Prophylactic, Devices, Procedures, Regimens,

Protocols
 Randomized Controlled Field Trial outcome outcome
 Preventive Trial
 Risk Factor Trial
 Cessation experiments
 Trial of etiologic agents
Fig. 1- Example of a Randomized Controlled Clinical Trial [7]
 Evaluation of health system

Fig. 2: Flow diagram of the progress through the phases of a parallel randomized trial of two groups [6]

standard. As they are usually conducted in the community, the term

Randomized Controlled Field Trial: It is similar to an Randomized used is Randomized Controlled Field Trial.
Controlled Clinical Trial except that the intervention is preventive
and not therapeutic. These are usually preventive trials in which the Preventive Trials: Trial of primary preventive measures e.g.
efficacy of a preventive intervention such as a new vaccine is tested Vaccines. Analysis of preventive trials must result in clear statement
in one study group and the other group receives a placebo or about benefits to community, risk involved and cost to health

33
 Dr. Srikanth et al.
Asian J Pharm Clin Res, Vol 6, Issue 3, 2013, 32-38

Risk Factor Trials: Investigator intervenes to interrupt the usual • Provides strongest evidence for causality in relation to
sequence in the development of disease for those individuals who temporality and control for unknown "confounders"
have risk factor for developing the disease • Allows comparison of multiple outcomes
• Similar distribution of baseline characteristics in
e.g. Primary prevention of CHD using simvastatin to lower serum comparison groups
cholesterol • Fulfills the basic assumption of statistical hypothesis tests
Cessation Experiment: An attempt is made to evaluate the • Protection against confounders, both known and
termination of a habit which is considered to be causally related to unknown
disease • Similar distribution of baseline characteristics in
comparison groups
e.g. Cigarette smoking and lung cancer
Weaknesses of RCT
Trials of Etiological Agents: To confirm or refute an etiological
hypothesis • Subjects are often a highly selected group (selected for
willingness to comply with treatment regimen, level of
Evaluation of Health Services: Domiciliary treatment of primary health, etc.) and volunteers may differ from population of
pulmonary tuberculosis was as effective as more costlier hospital or interest (i.e., generalizability may suffer).
sanatorium treatment • Not suitable for rare outcomes
• Not suitable for outcomes requiring long or extensive
Controls in Randomized Controlled Clinical Trial
follow-up
FDA classifies clinical trial control groups into six types [9]. • Adherence/withdrawal issues
• Limitations of external validity
Placebo Concurrent Control • Narrowing of the studied question Sometimes impossible
or impractical to conduct
In a placebo-controlled trial, subjects are randomly assigned to a test
• Complex, Expensive, time consuming, sometimes ethically
treatment or to an identical-appearing treatment that does not
questionable.
contain the test drug
Examples of Experimental Studies
No-treatment Concurrent Control
 Lewis EJ, Hunsicker LG, Clarke WR, et al: Renoprotective
In a no treatment-controlled trial, subjects are randomly assigned to
effect of the angiotensinreceptor antagonist irbesartan in
test treatment or to no (i.e., absence of) study treatment. The
patients with nephropathy due to type 2 diabetes. N Engl J
principal difference between this design and a placebo-controlled
trial is that subjects and investigators are not blind to treatment Med 345:851-860, 2001
assignment.  Brenner BM, Cooper ME, de Zeeuw D, et al: Effects of
losartan on renal and cardiovascular outcomes in patients
Dose-response Concurrent Control with type 2 diabetes and nephropathy. N Engl J Med
345:861-869, 2001
In a randomized, fixed-dose, dose-response trial, subjects are
randomized to one of several fixed dose groups. Subjects may either Different types of randomized studies as follows [10-12]
be placed on their fixed dose initially or be raised to that dose
gradually, but the intended comparison is between the groups on
their final dose Randomized Controlled Trials Classified According to the
Active (Positive) Concurrent Control Different Aspects of Interventions Evaluated (Based on outcome
of interest)
In an active control (or positive control) trial, subjects are randomly
assigned to the test treatment or to an active control treatment. • Explanatory or pragmatic trials - Explanatory trials are
designed to know whether new interventions work and if
External Control (Including Historical Control) it works how it works. Pragmatic trials on the other hand,
are designed not only to determine whether the
An externally controlled trial compares a group of subjects receiving intervention works but also to describe all the
the test treatment with a group of patients external to the study, consequences of the intervention and its use under
rather than to an internal control group consisting of patients from circumstances corresponding to clinical practice [13].
the same population assigned to a different treatment. The external • Efficacy or effectiveness trials - Efficacy refers to
control can be a group of patients treated at an earlier time whether an intervention works in people who receive it,
(historical control) or a group treated during the same time period whereas effectiveness refers to whether an intervention
but in another setting works in people to whom it has been offered [14].
Multiple Control Groups • Phase 1, 2, 3, and 4 trials

It is often possible and advantageous to use more than one kind of Based on hypothesis
control in a single study, e.g., use of both an active control and • Superiority trials- Here one intervention is hypothesized
placebo. Similarly, trials can use several doses of test drug and to be superior to another in a statistically significant way.
several doses of an active control, with or without placebo. This • Non-inferiority trials –They determine whether a new
design may be useful for active drug comparisons where the relative treatment is not worse than a reference treatment.
potency of the two drugs is not well established, or where the • Equivalence trials –They investigate whether two
purpose of the trial is to establish relative potency. interventions are indistinguishable from each other.
Strengths of RCT According to the number of participants
• Most like an experiment • N-of-one trials- Randomized controlled trials with only
• The only effective method known to control selection bias one participant are called “n-of-one trials” or “individual
• Able to directly estimate risk patient trials”. They provide individual results and not
• Controls confounding bias without adjustment generalized results[15].
• Permits the use of probability theory to express the
likelihood that any difference in outcome between • Mega Trial- Mega trial is randomized clinical trial with a
treatment groups merely indicates chance simple design which includes thousands of patients from
multiple centers and from different countries; and limited

34
 Dr. Srikanth et al.
Asian J Pharm Clin Res, Vol 6, Issue 3, 2013, 32-38

data collection [16]. These helps in obtaining increased

statistical power and generalized results
• Sequential trials- A sequential trial is a study with
parallel design in which the number of participants is not Treatment A
specified by the investigators beforehand. Instead, the Study
Randomize
Evaluation of
investigators continue recruiting participants until a clear population outcomes

benefit of one of the interventions is observed or until Treatment B or

control
they become convinced that there are no important
differences between the interventions .
• Fixed trials- Alternatively, in a fixed trial, the
investigators establish deductively the number of
participants (sample size) that will be studied. This
number can be decided arbitrarily or can be calculated
using statistical methods.
Fig. 4: Parallel design [8]

According to level of blinding Crossover

The purpose of blinding is to reduce the risk of ascertainment and In these types of studies each patient serves as his own control. Each
observation bias. An RCT may be blinded (also called "masked"), by patient gets both drugs; the order in which the patient gets each
"procedures that prevent study data collector, participants, or data drug is randomized [Figure 5]. Generally, it requires a smaller
observers from knowing which intervention was received"[12]. sample size. As each participant acts as his or her own control in
crossover trials, they can produce statistically and clinically valid
Blinded RCTs have been classified as "single-blind", "double-blind" results with fewer participants [18].
or "triple-blind".
• Open RCT: In open RCT, everybody involved in the trial
knows which intervention is given to each participant
• Single-blind: Patient or evaluator is blinded as to Treatment A
Treatment B
treatment, but not both
• Double-blind design: Neither patient nor outcome Study population Washout period
evaluator knows to which treatment patient was
assigned
Treatment B Treatment A
• Triple-blind: Patient, Physician, and Data analyst are
blinded as to treatment identity

Randomized Controlled Trials Classified According to

Participants’ Exposure and Response to the Intervention ( RCTs
based on study design) Fig. 5: Cross over design [8]

These include parallel, crossover, cluster and factorial designs Factorial

Parallel Studies involving two or more factors while randomizing are called
factorial designs [Figure 6]. Factorial design permits researchers to
In parallel studies, treatment and controls are allocated to different investigate the joint effect of two or more factors on a dependent
individuals. This is unlike a crossover study where at first one group variable (e.g. weight). The factorial design also facilitates the study
receives treatment A, followed by treatment B later, while the other of interactions, illuminating the effects of different conditions of the
group receives treatment B followed by treatment A [Figure 4]. As experiment on identifiable subgroups of subjects participating in the
each participant is given only one study intervention, they do not experiment
produce statistically and clinically valid results when there are only
few participants in the trial [17]. Using these studies, comparison of
relative or absolute efficacy can be obtained in a short period.
However, these studies generally require large number of patients
for the analysis Treatment A Treatment A + B

Study
population

Treatment B No Treatment

Fig. 6: Factorial design [8]

Table: difference between factorial and cross over design

35
 Dr. Srikanth et al.
Asian J Pharm Clin Res, Vol 6, Issue 3, 2013, 32-38

Factorial Cross over

Groups assigned different treatments each patient receives both treatment
Shorter duration longer duration
Large sample size small sample size
No carryover effect carryover effect
Robust to problems like less variability and greater sensitivity
missing data, missed visits

Cluster • Design of the study: selection of patients, drugs and doses,

It is a type of randomized controlled trial wherein groups of assessment, withdrawals, data analysis, data discharge
participants (as opposed to individual participants) are randomized • Ethics: patient consent, adverse events
[Figure 7]. Cluster randomized controlled trials are also known as • Documentation
cluster randomized trials, group randomized trials, and place Select participants
randomized trials.
• Likely to benefit and not be harmed
Advantages of cluster randomized controlled trials over individually • Likely to adhere
randomized controlled trials include the ability to study • Should be representative of the population
interventions that cannot be directed toward selected individuals • Adequate sample size is key features of RCT
(e.g. a radio show about lifestyle changes) and the ability to control
for "contamination" across individuals (e.g. one individual's change Measure baseline variables
in behavior may influence another individual to do so too).
Randomize
Disadvantages compared with individually randomized controlled
trials include greater complexity in design and analysis and a • Eliminates baseline confounding
requirement for more participants to obtain the same statistical Blinding the intervention
power.
• As important as randomization
• Eliminates biased measurement of outcome
10 hospitals
Follow subjects
 Adherence to protocol
Cluster randomization  Lost to follow up
( 5×clusters of 2 )
 Minimal loss to follow up is key features of RCT
Measure outcome
Intervention Control
5 hospitals 5 hospitals • Positive results/Negative results
• Clinically important measures
• Adverse events
Total study population (N=500)
• Specific primary & secondary outcomes
Randomization Procedure
Intervention Control
(N=500) (N=500) Importance of Randomization in Randomized Controlled Trial
Randomization is the random allocation of treatment, which means
all participants have the same chance of being assigned to each of
the study groups. The allocation, therefore, is not determined by the
Fig. 7:Cluster randomization [19] investigators, the clinicians, or other study participants [20]. The
effects of the treatment would be indistinguishable from the
Traditional Designs for Clinical Trials influence of the imbalance of covariates, thereby requiring the
• Parallel-group design researcher to control for the covariates in the analysis to obtain an
• Crossover design unbiased result [21].
• Factorial design The basic benefits of randomization include
• Add-on design
• Randomized withdrawal design  Eliminates selection bias.
• Early-escape design /Fail
 Balances arms with respect to prognostic variables
Other designs (known and unknown).
• Add on trials  Forms basis for statistical tests, a basis for an assumption-
• Run in phase free statistical test of the equality of treatments
• Taper phase
• Adaptive design Criteria For Randomization
• Sequential design
The detailed explanation of the above designs is beyond the scope of Unpredictability
the article
• Each participant has the same chance of receiving any of
Steps in conducting a RCT the interventions.
The protocol • Allocation is carried out using a chance mechanism so that
• Rationale neither the participant nor the investigator will know in
• Aims and objectives, Research questions advance which will be assigned.

36
 Dr. Srikanth et al.
Asian J Pharm Clin Res, Vol 6, Issue 3, 2013, 32-38

Balance (1) AABB, (2) BBAA, (3) ABAB, (4) BABA, (5) ABBA, (6) BAAB
• Treatment groups are of a similar size & constitution, Advantage
groups are alike in all important aspects and only differ in
the intervention each group receives Balance between the numbers of participants in each group is
guaranteed during course of randomization. Another advantage of
Simplicity blocking is that if the trial is terminated before enrollment is
completed, balance will exist in terms of number of participants
• Easy for investigator/staff to implement randomized to each group.
Methods of Randomization Disadvantage
The common types of randomization include (1) simple, (2) block, Analysis of data is more complicated than simple randomization.
(3) stratified and (4) unequal randomization. Some other methods Also with fixed blocks, people involved in the trial may be able to
such as biased coin, minimization and response-adaptive methods predict the group assignment of participants being randomized at
may be applied for specific purposes the last in the block.
Simple Randomization Unequal Randomization
Randomization based on a single sequence of random assignments is Most randomized trials allocate equal numbers of patients to
known as simple randomization [22]. The most common and basic experimental and control groups. This is the most statistically
method of simple randomization is flipping a coin. For example, with efficient randomization ratio as it maximizes statistical power for a
two treatment groups (placebo versus treatment), the side of the given total sample size. However, this may not be the most
coin (i.e., heads - control, tails - placebo) determines the assignment economically efficient or ethically/practically feasible. When two or
of each subject. A random number table found in a statistics book or more treatments under evaluation have a cost difference it may be
computer-generated random numbers can also be used for simple more economically efficient to randomize fewer patients to the
randomization of subjects expensive treatment and more to the cheaper one. The substantial
Advantage cost savings can be achieved by adopting a smaller randomization
ratio such as a ratio of 2:1, with only a modest loss in statistical
• simple and easy to implement power. When one arm of the treatment saves lives and the other
such as placebo/medical care only does not much to save them in
Disadvantage
the oncology trials. The subject survival time depends on which
• At any point in time, there may be an imbalance in the treatment they receive
number of subjects on each treatment
Covariate adaptive randomization
• Balance improves as the sample size n increases
• Thus desirable to restrict randomization to ensure Covariate adaptive randomization has been recommended as a valid
balance throughout the trial alternative randomization method for clinical research [28]. In
covariate adaptive randomization, a new participant is sequentially
Stratified Randomization
assigned to a particular treatment group by taking into account the
The stratified randomization method addresses the need to control specific covariates and previous assignments of participants [29].
and balance the influence of covariates. Stratified randomization is
Allocation Concealment
achieved by generating a separate block for each combination of
covariates, and subjects are assigned to the appropriate block of • Procedure for protecting randomization process so that
covariates. After all subjects have been identified and assigned into the treatment to be allocated is not known before the
blocks, simple randomization is performed within each block to patient is entered into the study
assign subjects to one of the groups. • Protects an assignment sequence before & until allocation
Prevents selection bias
Although stratified randomization is a relatively simple and useful
• Always possible to have allocation concealment
technique, especially for smaller clinical trials, it becomes
complicated to implement if many covariates must be controlled Effective Allocation Concealment
[23].
• Sequentially numbered opaque sealed envelopes
The block size should be relative small to maintain balance in small • Pharmacy controlled
strata. Increased number of stratification variables or increased • Serially arranged numbered containers (not labeled as A
number of levels within strata leads to fewer patients per stratum. or B when only two assignments)
Subjects should have baseline measurements taken before • Central randomization
randomization. Large clinical trials don’t use stratification. It is
unlikely to get imbalance in subject characteristics in a large Trial registration
randomized trial. When baseline characteristics of all subjects are In 2004, the International Committee of Medical Journal Editors
not available before assignment, using stratified randomization is (ICMJE) announced that all trials starting enrollment after July 1,
difficult [24]. 2005 must be registered prior to consideration for publication in
Block Randomization one of the 12 member journals of the Committee [30].

The block randomization method is designed to randomize subjects Consort guidelines for reporting an RCT should be followed. The
into groups that result in equal sample sizes. This method is used to final report should include all relevant details like development of
ensure a balance in sample size across groups over time. Blocks are the protocol, ethical committee approval, sample size calculations,
small and balanced with predetermined group assignments, which details of methodology with primary and secondary outcome
keeps the numbers of subjects in each group similar at all times [25, measures, procedures of randomization, allocation concealment,
26]. The block size is determined by the researcher and should be a blinding procedures, results and observations, analysis and
multiple of the number of groups (i.e., with two treatment groups, statistical tests applied.
block size of either 4, 6, or 8). Blocks are best used in smaller Conflict of interest: none
increments as researchers can more easily control balance [27].
REFERENCES
Example: Two treatments of A, B and Block size of 2 x 2= 4
1. Available from http://www.cebm.net/index.aspx?o=1116.
Possible treatment allocations within each block are [Last accessed on June 1st 2012 at 6.00pm].

37
 Dr. Srikanth et al.
Asian J Pharm Clin Res, Vol 6, Issue 3, 2013, 32-38

2. Ranjith G, Interferon-α-induced depression: when a 16. Woods KL., Mega-trials and management of acute
randomized trial is not a randomized controlled trial, myocardial infarction, Lancet 1995; 346:611-14.
Psychother Psychosom 2005;74(6):387. 17. Louis TA, Lavori PW, Bailar JC III, Polansky M., Crossover and
3. Streptomycin in Tuberculosis Trials Committee. self controlled designs in clinical research. In: Bailar JC III,
Streptomycin treatment of pulmonary tuberculosis. Br Med J Mosteller F, editors. Medical uses of statistics, 2nd ed.
1948;2:769–82. Boston, MA: New England Medical Journal
4. Peter Armitage. International Journal of Epidemiology Publications;1992. p. 83-104.
2003;32:925–28. 18. Greenland S, O’Rourke K. Meta-analysis. In:Rothman KJ,
5. Meldrum ML. A brief history of the randomized controlled Greenland S, Lash TL, editors. Modern Epidemiology, 3rd ed.
trial. From oranges and lemons to the gold standard. Philadelphia: Lippincott Williams & Wilkins;2008. p. 652-82.
Hematol Oncol Clin North Am 2000;14:745–60. 19. Donner A, Klar N: Design and Analysis of Cluster
6. Schulz KF, Altman DG, Moher D, CONSORT Group. CONSORT Randomization Trials in Health Research. London: Arnold;
2010 Statement: updated guidelines for reporting parallel 2000.
group randomised trials. BMJ 2010;340:c332. 20. Duffy SW. Interpretation of the breast screening trials: A
7. Anita S Acharya, Anupam Prakash, Aruna Nigam, Pikee commentary on the recent paper by Gotzsche and Olsen. The
Saxena. Scientific study designs for research: an overview. Breast 2001;20:209-12.
Indian journal of medical specialities 2012;3(2):191-94 21. Kalish LA, Begg GB. Treatment allocation methods in clinical
(modified). trials a review. Stat Med 1985;4:129-44.
8. Shraddha Parab, Supriya Bhalerao. Study designs. 22. Altaman DG, Bland JM. Statistics notes. Treatment allocation
International Journal of Ayurveda Research 2010;1(2):128- in controlled trails: Why randomize? BMJ 1999;318:1209.
31. 23. Weir CJ, Lees KR. Comparison of stratification and adaptive
9. 9)Available from methods for treatment allocation in an acute stroke clinical
http://www.fda.gov/downloads/regulatory trial. Stat Med 2003;22:705-26.
information/guidances/ucm125912. pdf. [Last accessed on 24. Lachin JM, Matis JP, Wei LJ. Randomizations in clinical trails,
20th march 2013 at 4 pm]. conclusions and recommendations. Control Clin Trails
10. Hopewell S, Dutton S, Yu LM, Chan AW, Altman DG. The 1988;9:365-74.
quality of reports of randomised trials in 2000 and 2006: 25. Frane JW. A method of biased coin randomization, its
Comparative study of articles indexed in PubMed. BMJ implementation and validation. Drug Inf J 1998;32:423-32.
2010;340:c723. 26. Altaman DG Bland JM. How to use randomize. BMJ
11. Stolberg HO, Norman G, Trop I. Randomized controlled 1999;319:703-4.
trials. Am J Roentgenol 2004;183:1539–44. 27. Lachin JM, Matis JP, Wei LJ. Randomizations in clinical trials,
12. Wood L, Egger M, Gluud LL, Schulz KF, Jüni P, Altman DG, et conclusions and recommendations. Control Clin Trails
al. Empirical evidence of bias in treatment effect estimates in 1988;9:365-74.
controlled trials with different interventions and outcomes: 28. Zalene M. Randomized consent designs for clinical trails: An
meta-epidemiological study. BMJ 2008;336:601–5. upadate. Stat Med 1990;9:645-56.
13. Sackett DL, Gent M., Controversy in counting and attributing 29. Kalish LA, Begg GB. Treatment allocation methods in clinical
events in clinical trials, N Engl J Med 1979;301:410-12. trials a review. Stat Med 1985;4:129-44.
14. Fletcher RH, Fletcher SW, Wagner EH., Clinical epidemiology: 30. De Angelis C, Drazen JM, Frizelle FA, Haug C, Hoey J, Horton
the essentials, 3rd ed. Baltimore, MD: Williams & R, et al. Clinical trial registration: a statement from the
Wilkins;1996. International Committee of Medical Journal Editors. New
15. Guyatt G, Sackett D, Taylor DW, Chong J, Roberts RS, Pugsley Engl J Med 2004;351:1250–1.
S. Determining optimal therapy-randomized trials in
individual patients, N Engl J Med 1986;314:889-92

38