Methods - Summary

Dr. Raghupathy Anchala

MD (Chest Medicine), MPH (USA), PhD (Cambridge, UK)
Associate Professor, Department of Epidemiology
PHFI - IIPH, Hyderabad
 Writing up Methods section…..

Photo courtesy: Prof S. Kadam, IIPHB

 Break up
• Study design
• Setting
• Study sample
• Variables
• Instruments
• Analysis plan
• Statistics
• Ethical clearance
 Importance of methods section
• Explains how you are going to tackle the main
problem of the project.

• Written description of the plan, or strategy you will

take to answer your research questions.

• Describe the techniques to allow the reader to judge

whether the project will achieve the stated
objectives.
These need to be given a second
look
 CONSORT guidelines
• Title and abstract
– How participants were allocated to interventions (eg, “random allocation,”
“randomized,” or “randomly assigned”).
• Introduction
– Background : Scientific background and explanation of rationale
• Methods
– Participants : Eligibility criteria for participants and the settings
and locations where the data were collected
– Interventions : Precise details of the interventions intended for
each group and how and when they were actually administered.
– Objectives : Specific objectives and hypotheses
– Outcomes : Clearly defined primary and secondary outcome
measures and, when applicable, any methods used to enhance
the quality of measurements (eg, multiple observations, training
of assessors)
– Sample size : How sample size was determined and,
explanation of any interim analyses and stopping rules
Adapted from
Moher D, Schulz KF, Altman D, for the CONSORT Group. The CONSORT statement: revised recommendations for improving the quality of reports of parallel-group randomized trials. JAMA.
2001;285(15):1987-1991.
 CONSORT guidelines
• Randomization

– Sequence generation : Method used to generate the random allocation

sequence, including details of any restriction (eg, blocking, stratification).
– Allocation concealment : Method used to implement the random allocation
sequence
– Implementation: Who generated the allocation sequence, who enrolled
participants, and who assigned participants to their groups

• Blinding (masking) : Whether or not participants, those administering the

interventions, and those assessing the outcomes were blinded to group
assignment. If done, how the success of blinding was evaluated.

• Statistical methods: methods used to compare groups for primary

outcome(s); methods for additional analyses, such as subgroup analyses
and adjusted analyses.

Adapted from Moher D, Schulz KF, Altman D, for the CONSORT Group. The CONSORT statement: revised recommendations for improving the quality of reports of parallel-group randomized trials.
JAMA. 2001;285(15):1987-1991.
 Strobe statement
• Study design (descriptive, case-control, cohort)
• Setting – general and study site
• Participants
• Sample size calculation (if needed)
• Data variables to be collected (outcome variables,
data collection instrument and data validation)
• Sources of data
• Analysis and statistics
• Ethics approval
 Three recent publications

Paper 1 : Development and validation of an

intervention

Paper 2: Systematic review & Meta analysis (Quant)

Paper 3: Cluster randomised trial

Step by step…all elements…MUST

come out in Methods
Summative…most helpful
Paper 1 - Methods
Where is DSS taken from?

Have we involved
stakeholders?

Where have we done?

Where is DSS taken from?

Paper 1 - Methods
We have used OPEN
source

Validity

We have used OPEN

source

What domains tested in our

system…piloting
Paper 1 - Methods

Clarity on what items

we are validating

Very detailed…should be
replicable and valid
 Have we covered all elements?
• Study design (descriptive, case-control, cohort)

• Setting – general and study site

• Participants

• Sample size calculation (if needed)

• Data variables to be collected (outcome variables, data

collection instrument and data validation)

• Sources of data

• Analysis and statistics

• Ethics approval
Paper 2 - Methods

When and what we

have searched

Selection criterion :
define upright
Paper 2 - Methods

How data was

selected and
extracted?

High importance
since we are pooling
Paper 2 - Methods

Procedures?

Weightage?

What have you finally

reported?
Paper 3
Paper 3 - Methods

Submitted – under review

We used
validated /
pilot tested

One primary end point…question, aim, methods

&sample size should reflect and speak same
 Paper 3 - Sample size calculations

Submitted – under review

Effect size Power based Design effect
 Paper 3 - methods

Submitted – under review

Study map, population size, what areas have you
covered and WHY
 Paper 3 - Methods

Submitted – under review

How we have stratified?
Line listing
Random
Matching
Who did this randomisation? Was it blinded?
Very important – your way of choosing

Method of

Submitted – under review

randomisation

Blinded to
whom?

Numbers
randomised,
received treatment
& analysed
Paper 3 - Methods

Submitted – under review

Very detailed so that
others can replicate

Pay attention
to
questionnaire
Paper 3 - Methods

Submitted – under review

Don’t forget
secondary
end points
 Paper 3 - Methods

Submitted – under review

Papers 3 - Methods

End points and what

have you do to

Submitted – under review

answer hypothesis
and primary end
points
Essential elements under methods
section

• Proposed experiments or investigations

• Materials and techniques that you will use

• Statistical techniques - ho would analyze the

data
 Design: Setting

– Describe the type of study you are conducting

– Study setting
– Time frame
– If you are using original data, describe how you
will protect the identity of your sources
– If you are using record based data, describe how
you accessed the records
 Participants
• Describe your data sources- (if participants, describe their
demographic characteristics: age, sex).

• Any inducements for participation you plan to use

• Sample-
Sample size, what are your sources?
• Where did you find them?
• What criteria did you use to include, or exclude data
sources?
• Address any issues regarding validity
• Address any issues regarding reliability
• Address any issues regarding permissions you obtained
to use data, and include copies of such in appendices
 Variables
– Description of all the variables being examined in
your study

– Description of how your variables are to be

combined

– Description of the points of measurement and

manipulation in the design.
 Instruments
• Include details about specific instruments
used to conduct research.
• Explain why you have chosen these specific
instruments
– Reliability and validity of instruments.
– Reference indicating where instruments can be
obtained
• Variables measured by instruments.
 Procedure

• The reader should know exactly what you

intend to do after reading this description

• Data collection steps

• A detailed step-by-step description of how the

study will be executed.
 Analysis plan, statistics
– Dummy tables
– Program you will use
– Assistance you received to interpret the data
– Missing data, loss to follow up
– significance levels
– If conducting a review-type thesis, how did you
store your data?
– How did you go through material
– synthesize, analyze, categorize findings?
 Ethical clearance
• This study was approved by….
• Usually include
– Patient information sheet and patient consent
form
– Protocol submissions
– Check on guidelines mentioned and be clear on
• Exemption
• Expedited
• Full Institutional Ethics Committee (IEC) review
 Summary
• Study design
• Setting
• Study sample
• Variables
• Instruments
• Analysis plan
• Statistics
• Ethical clearance