How to write a research proposal for observational studies
1. HOW TO WRITE A RESEARCH
PROPOSAL FOR
OBSERVATIONAL STUDIES?
WORKSHOP
2.
3. Objective
To illustrate a guide to writing a research
proposal, outlining the important elements of a
research proposal for observational studies.
5. Elements of research proposal
1. WHY?
Introduction and rationale
Literature review of previous studies on the topic
Burden of illness
Biological rationale of intervention/exposure
Statement of the problem and its importance to
public health
What is the purpose of the study? (research
question)
6. Elements of research proposal
1. WHY?
Study Objectives
Primary objective
(sample size depends on this)
Secondary objectives
Hypothesis
7. Example of Introduction
1. The Intro begins
broadly…..
2a. More specific….
Lung cancer is the leading cause of cancer death, and
is associated with low 5 year survival rates if
diagnosis late. In 2005, the age-standardised
incidence rate of female lung cancer in France was
12.6, with a 5.1% annual increase [1]. While
incidence is still higher among men,……….……
burden of the diseases
Early epidemiologic studies demonstrated that
cigarette smoking is a major cause of lung cancer.
Tobacco smoking using the traditional forms of
tobacco (waterpipe , arguileh, hookah and shisha) is
an older form of tobacco consumption in the eastern
Mediterranean region [2]….……..rationale of
exposure
8. Example of Introduction
2b. Even more so.... Data from low quality studies showed that
waterpipe tobacco smoking is possibly associated
with a number of deleterious health outcomes
including lung cancer [3] …….. ….cite
landmark research/reviews here to
make key points
However, there is paucity of high-quality studies to
identify the strength of association between shisha
smoking and risk for developing lung cancer
.........cite research gap/need for
study ….. problem
statement/importance of issue
9. Example of Introduction
3. Until you introduce
your study…..
In this study, we examine the association between
shisha smoking and lung cancer in a large prospective
study……..include study’s unique
contribution
here/objectives/research question
10. Example of Objectives
Primary objective: To examine the association
between Shisha (or equivalents) smoking and risk of
developing lung cancer
Secondary objectives:
To estimate the magnitude of association relative to
intensity, total duration of Shisha /equivalents smoking,
times-week; after adjusting for all potential confounders.
To estimate the magnitude of association relative to the
type of smoke used; after adjusting for all potential
confounders.
11. Example of Hypothesis
We hypothesize that shisha smoking is associated
with increased risk of developing lung cancer.
OR
We hypothesize that the risk of lung cancer
increases with increased intensity (or duration) of
shisha/equivalents smoking.
12. Methods
“The methods or procedures section is really the
heart of the research proposal. The activities
should be described with as much detail as
possible, and the continuity between them
should be apparent”
(Wiersma, 1995, p. 409).
13. Methods
HOW?
1. Study Design
“Describe the research methods that could be used for the best
achievement of the study objectives and testing your
hypothesis”
Study area
Type of study
Design architecture (flow-chart)
Instruments for data collection (questionnaire, observation
recording form, etc.) Include in appendix
Endpoint (in prospective studies)
Outline of study procedure (in observational studies)
14. Outline of study procedure Template
Activity Time
Visit 1 Visit 2 Visit 3 Visit 4 Visit 5
Activity Time
Visit 1 Visit 2 Visit 3 Visit 4 Visit 5
Consent
Blood test X
CT chest
Pulmonary function
Example
15. Methods
HOW?
2. Participant Selection (sampling)
“Mention the sampling technique that will be used in order
to obtain a representative sample for your target
population”
Recruitment and Enrolment (multicentre, single
centre....etc)
Study population (including sampling technique)
Study participants
Case definition
Inclusion/Exclusion Criteria for cases
Inclusion/Exclusion Criteria for controls
16. Methods
WHAT?
Conduct of Study
What is the exposure
What is/are the outcome(s)
Key variables
Detailed study procedure
What variables are to be measured
Development of lung
cancer
17. Methods
WHAT?
Evaluation of the outcomes
Tools (lab, radiology,.......etc)
Management of Patient Care (in prospective studies)
Protocol deviation and subject withdrawal (in
prospective studies)
18. Methods
HOW MANY?
Biostatistical Considerations and Data analysis
Sample Size Determination and pow
Outcome Analysis (statistical tests used)
Statistical package(s) used
Interim analysis (in prospective studies)
19. Work plan
Timelines
starting time
duration of the study
duration for each participant
Task Month
1 2 3 4 5 6 7 8
Progress report
20. Utilization and dissemination of
the results
SO WHAT?
What will this study add to the existing knowledge?
‘how this research will refine, revise, or extend existing
knowledge in the area to be investigated’
Will the study results be generalized?
21. Adds on
STUDY MONITORING (in prospective studies)
ETICAL CONSIDERATIONS (consents, invitation letters)
BUDJECT AND RESOURCES
Personnel
Equipments
Supplies
Patients costs
Training
22. Adds on
LIMITATIONS
‘Indicate any potential weakness in the study, analysis,
your instruments, the sample’
REFERENCES
‘Mention recent articles relevant to the study subject and
enumerated according to their order of appearance in
the text’
APPENDIXES
[1] Cigarette smoking and lung cancer in women: Results of the French ICAREcase–control study. Lung Cancer 74 (2011) 369– 377[2] The effects of waterpipe tobacco smoking onhealth outcomes: a systematic review.International Journal of Epidemiology 2010;39:834–857[3] Int J Epidemiol. 2010 Jun;39(3):834-57.The effects of waterpipe tobacco smoking on health outcomes: a systematic review.
State your study design, and describe your data source(s) and data collection methods;
Define your study sample – inclusions, exclusions;Sampling is critical to external validity—the extent to which findings of a study can be generalized to people or situations other than those observed in the study.
Define your key nting and key explanatory variable(s); briefly mention confounders and covariates
After presenting the outline for study procedure, and someone had a CT-scan suggestive of lung cancer………. How will the outcome be measured and what tool will be used to measure it….(ie lung biopsy in our case).