To plan any analysis, it is first important to understand the available data. The IDI links up a broad set of administrative and survey datasets, and navigating the datasets and available variables can be complicated, especially when you do not have access to the IDI yet. This post hopes to signpost several useful tools to make it easier to plan before you have been given Datalab access.

Te rourou IDI search app

As a first step, we recommend the super useful Te rourou IDI search app that has been developed by Elliott, et al. since December 2022. The app enables anyone online to directly search what collections, datasets and variables are available in the IDI, without physically having to enter the Datalab. In some cases, the search app also has metadata about these variables. The app combines information of variable listings and data dictionaries, which are both provided to the developer team by StatsNZ and are updated every refresh.

Statistics New Zealand

StatsNZ welcomes researchers to book pre-application meetings, and they can email out most data dictionaries. Please contact access2microdata@stats.govt.nz.

The StatsNZ website also gives a high-level overview of data in the IDI. There is a link to a useful chart which sets out the timelines of data coverage for some of the main datasets, and this gets updated with every refresh.

Integrated Data Commons

Stats NZ ID Commons is an online forum of researchers and Datalab users, launched in early 2023. Invitations have currently been sent to Datalab users, but it is expected to then be made available more broadly. See https://idcommons.discourse.group. The platform allows you to ask questions, follow discussions, share tips, and learn more about the IDI. There are spaces for discussions and questions on metadata and analytical approaches, and code sharing.

Figure 1: ID Commons Home Page

Virtual Health Information Network

The VHIN has published a set of guides with important information for researchers about commonly used datasets in the IDI. Some of these may be helpful for planning your analysis.

Another useful space for asking questions has been the VHIN Facebook group. You can ask to join the group and post questions to other IDI users. Questions can also be posted to the VHIN at vhin@auckland.ac.nz.

Data providers

After searching online, you may still have questions about the datasets and variables you want to use in the IDI. Other researchers, colleagues and StatsNZ can direct you to the relevant data providers for advice about data collection, variables, and other helpful contextual information. This is common and an important step in ensuring the quality and validity of your research.

In the Datalab

Once you have established access and visited the Datalab, you can navigate the SQL database and access data dictionaries in the Wiki. There is more information on these steps in the VHIN Guide: Getting Started Using the IDI.

Summary

Recent developments have made it much easier to plan IDI research, before applying to get access to the Datalab. Tools outside the Datalab have made this possible.

By Andrea Teng & Frederieke Sanne Petrović-van der Deen

Originally published 12 April 2023

This work is licensed under a Creative Commons Attribution 4.0 International Licence