Randomization introduces a deliberate element of chance into the
assignment of treatments to participants in a clinical trial. It
tends to produce treatment groups in which the distributions of
prognostic factors, known and unknown, are similar. In combination
with blinding, randomization helps to avoid possible bias in the
selection and allocation of participants arising from the predictability
of treatment assignments. It also provides a strong statistical
basis for the quantitative evaluation of the evidence relating to
The method of
allocation generation should be specified in the protocol, such
as a random-number table or a computerized random-number generator.
The sequence may be generated by the process of simple randomization
or restricted randomization. Simple randomization is based on a
single sequence of random assignments and is particularly suited
to large trials. It is possible that by chance alone the groups
might be imbalanced in important prognostic factors. Restricted
randomization describes procedures used to control the randomization
to achieve balance between groups in size or characteristics. Examples
of restricted randomization include: blocking; stratification; minimization.
This has greater potential benefit in small trials.
trials the randomization procedures should be organized centrally.
This can entail, for example, generation of separate random schemes
for each centre or provision of telephone randomization where the
collaborating centers phone up the co-ordinating office for the
cannot allocate individuals to treatments, but must allocate a group
(‘cluster’) of subjects together in a cluster randomized
trial. The procedures for randomizing clusters to trial interventions
are identical to those described above.
to knowing the methods used, it is also important to state how the
random sequence will be implemented: specifically, who will generate
the allocation sequence, who will enroll participants, and who will
assign participants to trial groups. Whatever the methodological
quality of the randomization process, failure to separate the creation
of the allocation sequence from assignment to study group may introduce
Back to top
to consider when writing a protocol
the methods used to generate the random allocation sequence.
the factors used for any restricted .randomization
who will generate the allocation sequence.
- Explain who
will enroll participants.
- Explain who
will assign participants to their groups.
Illustrative example - Example 1
‘In this trial all units (hospitals) enters the study at the
same time, and all prognostic variable are known in advance. In
this situation a computer algorithm can choose by random one allocation
sequence among a set of sequences that minimizes the imbalance between
groups. Such algorithm will be used to allocate hospitals in this
There are four
hospital characteristics that were selected as important prognostic
variables. These are the variables that will be included in the
minimization algorithm to assure balance between groups.
hospital with residents (Yes-No).
size (less than 2000 – 2000 or more deliveries per year).
- Region (Montevideo,
Salto/Paisandu, Rosario, Buenos Aires).
algorithm will minimize the imbalance between groups, assigning
more priority to variables 1 and 2.
After the baseline
data collection period the dataset will be analyzed by RTI. RTI
will then apply the inclusion criteria to assess the eligibility
of preselected hospital according to the baseline rate of episiotomy
and active management. The statistician at CLAP will elaborate a
computer program implementing the minimization algorithm. The source
code of the algorithm will be made available in advance to RTI and
UNC-CH for audit and testing. This computer program will be used
by the statistician at RTI to allocate eligible hospitals to either
intervention or control without participation of others. The assignment
will then be communicated to CLAP. Thus, there will be a clear separation
between the generator of the intervention assignment and the CLAP
study coordination. (CLAP Trial - go to protocol )
Illustrative example - Example 2
Simple randomization will be conducted independently for each study
site by the Development and Research Training in Human Reproduction
(HRP) of the Department of Reproductive Health and Research (RHR)
statistical unit at WHO headquarters and provided to the pharmaceutical
The random allocation
sequence will be generated using computer-generated random numbers.
Randomization will be to the two arms of the trial and stratified
by country. Blocking with randomly varying groups of 6-8 will be
used to restrict randomization within the strata (country) (SAS
Software, CopyrightÆÉ 1989, 1994 SAS Institute, Inc.,
technique consists of allocating consecutively numbered treatment
boxes for each woman, including in each box seven independent bottles,
each of them with tablets for four weeks of treatment. Each bottle
contains 100 tablets. Therefore each subject will have seven bottles
with the same randomization number. Treatment boxes will be kept
at the clinic. Bottles will be provided consecutively as needed
every month after randomization. When the woman comes for antenatal
care, she will return the used bottle from the previous month and
will be given the next month's bottle from her box. She will return
the bottle after 4 weeks, regardless of whether she finished the
tablets or not. Each bottle is numbered from 1 to 7 within the box
and should be used sequentially. (WHO Multicentre Randomized Trial
of Calcium Supplementation for the Prevention of Pre-eclampsia -
go to protocol)
example - Example 3
Hospitals with access to the 24-hour telephone randomization service
Women are entered
into the trial by means of a telephone call to the 24-hour randomization
service in Oxford. During this telephone call brief baseline details
from the Trial Entry page in the Women’s Booklet (Appendix
3) are requested, and recorded on a computer, before the treatment
allocation can be given. At the end of the call a two-digit pack
number (and the four digit number of the box from which it should
be taken) is issued, and this number should be recorded immediately.
Once this pack number is allocated, the woman is irrevocably entered
into the trial, irrespective of whether the treatment pack is opened.
Randomization is balanced for major prognostic variables; severity
of pre-eclampsia, gestational age at randomization, whether delivered,
whether given anticonvulsants drugs before trial entry, whether
a multiple pregnancy and country.
a local pack system
is only for hospitals that do not have access to the 24-hour telephone
randomization service. When a woman has given consent to participate
in the trial the clinician completes the Trial Entry page in the
Women’s Booklet (Appendix 4). This page must be completed
BEFORE the treatment pack is opened, it records brief baseline details
about the woman and the number of the next treatment pack. The treatment
packs MUST be used in the order in which they are removed through
the slot in the box, which is lowest number first. Once the Trial
Entry page has been completed the woman is entered into the trial,
irrespective of whether the treatment pack is opened. (Magpie trial
- go to protocol )
Checklist for randomization
This checklist has been contributed by Dave Sackett, who prepared
it for the forthcoming 3rd edition of Clinical Epidemiology; A Basic
Science for Answering Questions about Health Care, to be published
by Lippincott, Williams & Wilkins in 2004.
- Make it
easy for collaborating clinicians – they are busy people.
- Be realistic
and practical (no good planning telephone randomisation if participating
centres have no reliable access to phone systems).
- Make sure
you consider: where participants will be recruited; who will randomize
the participants; when randomisation will take place.
the most appropriate randomisation systems for the project (consider
the options below) central/local; phone/fax/email; treatment box;
- Ensure that
participant details are recorded before treatment allocation is
- Ensure that
the treatment allocation is adequately concealed.
This is an example of a random number table (as a pdf).
by using a pre-packed, sequentially numbered trial case
This is presentation has been contributed by Zhengming Chen and
illustrates randomization by using a pre-packed, sequentially numbered
trial case instead of 24-h telephone or fax system.
of randomization software and services
This is a directory
of randomization software and services for clinical trials, including
both simple do-it-yourself software and 24 hour telephone randomization
services. It is intended to help people planning and seeking funding
for clinical trials.
on randomization in clinical trials
are part of a guide to planning a research project for researchers
in health care. It is written for applicants for NHS R&D funding,
but will be useful for everyone trying to set up healthcare research
There are services available that provide 24-hour automated telephone
randomization. However, these services are not free so you must
agree their involvement before applying for your grant. These can
be found by searching the Internet.
- Pocock SJ.
(1983) Clinical Trials: A Practical Approach. John Wiley and Sons,
DG, Bland JM. How to randomize. BMJ
1999; 319: 703-704 .