If you do data analysis, you encounter missing data. Missing data upsets data analysis workflow because you have to make decisions on how to deal with it - do you impute the values? Remove them? These each have consequences! The data we often encounter does not always arrive with a research question in mind, so how do you understand why you have missing values? When I first encountered missing data I was incredibly frustrated at how hard it was to understand and explore it. This frustration led me to create two R packages to explore missing data, {naniar} and {visdat}. In this talk I will showcase how to use these tools to explore missing data, as well as new features that have not been presented, and planned advances.
Talk materials are available at https://github.com/rstudio/rstudio-conf/blob/master/2022/nicholastierney/The%20Future%20of%20NA%20Data.pdf.
Nick Tierney has an honours degree in Psychology, and a PhD in
Statistics and now work as a research software engineer with
[Nick Golding](https://www.telethonkids.org.au/contact-us/our-
people/g/nick-golding/) at the [Telethon Kids Institute](https://
www.telethonkids.org.au/), in Perth. Here, he maintains the [greta]
(https://greta-stats.org/) R package for statistical modelling,
and writes new software to perform analysis on diseases like
COVID19 and malaria. Previously, Nick worked at Monash University,
working with Di Cook, teaching ETC1010,
introduction to Data Analysis, and
developing the following R packages for exploratory data analysis:
(visdat) , [naniar]
(https://naniar.njtierney.com/), and [brolgar](https://
brolgar.njtierney.com/). Nick is a keen outdoorsman, and likes to hike
really far, run ultra marathons, brew coffee, take photographs, and
have long meandering conversations.
