OCA Data Sharing Practicals

Chapter 1 Introduction

This repository contains two training documents for the OCA Data Sharing Platform:

• Chapter 2: Data dictionaries covers the production of data dictionaries to accompany datasets that will be shared

• Chapter 3: Pseudonymization covers techniques for assessing and limiting disclosure risk when preparing datasets to be share

1.1 Setup

Before moving on to Chapter 2, setup a folder on your computer where you can store the datasets that accompany this practical. If you use R Studio we suggest setting up a new R Project, as described in The Epidemiologist R Handbook.

The datasets used in Chapters 2 and 3 can be downloaded from GitHub via the links below. Our example code chunks in Chapters 2 and 3 assume that these datasets will be stored within a folder called “data/”.

• mortality_survey_simple_kobo.xlsx
• mortality_survey_simple_data.xlsx
• mortality_survey_simple_dict_pre_pseudonym.xlsx

You will also need to install some R packages.

install.packages(c("remotes", "rio", "here"))
remotes::install_github("epicentre-msf/datadict")