Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
443 views

Data Analysis Template 20131125 PDF

This document provides a template for a data analysis plan for an observational study. It includes sections for background information on the study, research questions and hypotheses, study design details, the proposed analytical strategy, and plans for interpreting and disseminating the results. The template requests information on the study population, inclusion/exclusion criteria, variables, analytical models, and approach to dealing with missing data. It also recommends including concept maps or directed acyclic graphs to visualize hypotheses and potential confounders.

Uploaded by

datadob
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
443 views

Data Analysis Template 20131125 PDF

This document provides a template for a data analysis plan for an observational study. It includes sections for background information on the study, research questions and hypotheses, study design details, the proposed analytical strategy, and plans for interpreting and disseminating the results. The template requests information on the study population, inclusion/exclusion criteria, variables, analytical models, and approach to dealing with missing data. It also recommends including concept maps or directed acyclic graphs to visualize hypotheses and potential confounders.

Uploaded by

datadob
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Example Data Analysis Plan

Template
For Observational Studies

Last updated 25 November 2013

Research School of Population


Health
ANU College of Medicine, Biology &
Environment

Example Data Analysis Template


Note: This data analysis template is a modified version of the template created by the
Master of Philosophy (Applied Epidemiology) teaching team at the Australian National
University.

DATA ANALYSIS PLAN


TEMPLATE
Reference No.
Date of plan
Person conducting
analysis

Study name
Chief investigator
Telephone
Mobile
Email

Analysis team
members

Background to the study and analysis


(Please use plain language)
Provide an overview of the necessary background for the study including evidence of what is
already known in the area of study and what the gaps are in the literature. Finish with a clear
stated aim of the project.

Number study
participants
Study research
question
Specific hypothesis
under study
Endpoints or
outcomes of interest

Duration of study

Data details
(Please complete all that apply)
Study type
Data sets used
Analysis package
Study population
Inclusion/exclusion criteria
for participants
Exposure variables
Outcome measures
Covariates
Sub-groups
Page 2 of 3

Approach to dealing with


missing data

Please outline proposed analytical strategy


Include:
Outline of main comparison groups
Frequency and cross-tabulations of main variables
Basic analysis model (usually age- and sex-adjusted)
Final analysis model (including adjustment for other confounders)

Analysis dissemination strategy


Outline the intended steps to be taken to disseminate the results of the study (i.e. will the
results be published, presented at a conference etc)

Interpretation
Detail how you will interpret the results in the context of your stated hypothesis. I.e. if the
results do/do not meet your hypothesis, what will you conclude? A concept map (see below)
may assist with this.

Concept map or directed acyclic graph


Drawing a diagram of the ways in which the exposure might be related to the outcome will
help to visualise your hypotheses as well as serving as a basis for clearly communicating
this to your collaborators. The diagram should include the possible confounders or mediators
of the relationship. This will require good knowledge of the background to the study.
Directed acyclic graphs are a type of causal graph. Further information about these graphs
can be found through a Google search and in the paper Causal Diagrams for Epidemiologic
Research by Sander Greenland, Judea Pearl, and James M. Robins (Epidemiology
1999;10:37-4)

Dummy tables & Charts


Dummy tables and charts are empty skeleton tables and charts which show how the results
will be presented but which do not contain any data/results.

Page 3 of 3

You might also like