2025
Nationwide census scrapped, Science Media Centre and other media comments
2025-06-18
🏷 media; news; radio; interview; recording available;
On 18 June, Statistics Minister Dr Shane Reti announced a new approach for the census and administrative data in Aotearoa New Zealand.
I was asked for a comment by the Science Media Centre, which you can find here, among excellent comments from Lara Greaves, Tahu Kukutai and other experts I would recommend following in this area.
This comment was picked up in a 📃 1News article (very nice of them to give me the ‘last word’) and resulted in an interview with Joel Armstrong on 95bFM (📻 audio link + 📃associated write up) and Joel Maxwell for Stuff ( 📃 article link).
🤔 That’s questionable: Designing and deploying effective models for generating multiple versions of auto-marked questions, New Zealand Statistical Association (NZSA) 2024 Conference
2024-12-02
🏷 academic; conference; stats ed; presentation; slides;
This is joint work with Anna Fergusson, Lars Thomsen, Charlotte Jones-Todd.
Abstract
Creating automatically marked question banks with a number of versions is popular for both supporting academic integrity and for providing low-stakes assessment opportunities with instant feedback. Short quizzes can engage students in checking their understanding throughout a course and support their preparation for higher-stakes assessments. While auto-marking can help reduce teaching team workload, the creation and maintenance of high-quality and fair question banks can be very demanding. To support this, a range of computational tools exist for creating auto-marked questions and deploying them to assessment platforms (e.g., the R package exams, Grün & Zeileis, 2009). However, while there is guidance for the practical implementation of these tools (e.g., Zeileis et al., 2014), there is very little documentation that explains the design process for developing models that can generate tens or even hundreds of versions of questions. This talk has three aims: 1) to explore design principles that support pedagogy-first approaches to creating question-generating models, 2) to share considerations and opportunities with respect to having students analyse data (with iNZight Lite) to answer quiz questions, and 3) to report on how students are actually using quizzes with multiple versions in a large introductory statistics course, including findings based on data about quiz attempts, as well as reflections from the teaching team.
Slides
Direct link: https://lizabolton.github.io/2024-12-02_NZSA-Wellington/#/title-slide
2024
Maternal Depression and Antidepressant Use, Smooth Brain Society (co-host)
2024-09-16
🏷 media; podcast; recording available;
It was a real delight to be invited back to the Smooth Brain Society by Sahir as a co-host for this fascinating episode with my friend and COMPASS colleague, Steph.
One of my (selfishly) favourite parts, lightly editted for the written word:
Liza: If you were going to talk to that front row psych student in a first year course. What kind of advice would you give them, and why does it take more statistics?
Steph: Ooh, you’re putting me on the spot, Liza. One thing I actually ask my policy students to do is to think about how statistics could help address policy problems. What is something that they’re really passionate about, what is something they are interested in, what is something that they want to make a difference in, right? And to be able to make a difference you need to have evidence and that evidence can come from all perspectives as I see it. One thing with statistics is that you can make these generalizations and inferences if you’ve got good data. So if there is something that’s important to address in the population or in a community that you care about, it’s really important to have that kind of representative, generalizable evidence. And that’s where statistics can come into play and help you. If you’re wanting to advocate to the people at the top to make a difference, you need to have evidence there to show where the difference is needed and the impact is needed.
Description
There is often a tendency to focus on physical rather than mental health during pregnancy. While rates can vary by country, research suggests that about 10 - 20% of pregnant women experience depression during pregnancy. This is higher than the average rate of 6% seen in the general population. The changes during pregnancy can also make it hard for mood disorders to be detected and treated. Dr. Stephanie D’Souza, PhD of The University of Auckland was on the podcast discussing her research into maternal depression and antidepressant use. Dr. Liza Bolton joins as co-host as we go through some of the key things to be aware of around maternal mental health and why research in this area is hard to undertake.
Watch or listen [1:17:50]
This way or data-way: A survival guide for a world of data, Raising the Bar Auckland
2024-08-27
🏷 public; presentation; recording available;
Blurb: What do motivational posts on LinkedIn have in common with the supposedly small feet of Victorians? Join Dr Liza Bolton as she explores the habits of statistical thinking that can make our day-to-day lives better – from picking a restaurant like a statistician, to why you shouldn’t necessarily believe a bus stop advertisement when it tells you your hometown is one of New Zealand’s most monogamous. There are no mathematics prerequisites here – number lovers and loathers alike are invited on a romp through the good, the bad and the ugly from a world full of data and decisions.
Recorded at Norma Taps, Auckland.
You can find the annotated bibliography for this talk on my blog.
Listen [54:07]
Listen on SoundCloud or Spotify.
Ready Steady Learn, 95bFM
2024-08-20
🏷 media; radio; interview; recording available;
I dropped into the studio for a quick Ready Steady Learn chat with host Jonny in the lead up to the Raising the Bar on August 27.
Listen [9:30]
Direct link: https://95bfm.com/bcast/ready-steady-learn-w-liza-bolton-august-20-2024
Lies, Damned Lies and Statistics, Smooth Brain Society
2024-05-16
🏷 media; podcast; interview; recording available;
Host: Dr Sahir Hussain
Cohost: Alex Marinkovich-Josey
Description
The use of stats and throwing around numbers in conversation is incredibly common, yet statistics itself is poorly understood. Dr. Liza Bolton from @universityofauckland discusses the dark art that is statistics. Using examples, she takes us through some misconceptions and dispels the notion that numbers don’t lie. We cover how to identify the best ice cream store, how to not be fooled when stats are mischaracterized in media and politics, why we worship the nat 20 dice roll and is the 27 club for musicians a real thing?
Watch or listen [1:10:19]
This episode is available where ever you get your podcasts.
- On the Smooth Brain Society website.
- Also available on Wellington Access Radio.
Dance like nobody’s watching🕺
Write like nobody’s reading? ✍️:
Low-stakes writing, academic reflection & graduate profile capabilities, Faculty of Science Early Career Research Group Workshop
2024-04-10
🏷 academic; presentation; slides;
The Early Career Research Group supports Research Fellows in the Faculty of Science. Many Research Fellows also teach and the team organises this workshop yearly to support people to engage with education research and effective practices.
Slides
Direct link: https://lizabolton.github.io/2024-Lowstakes-writing-ECR/#/title-slide
Are we a-head or not? Use and misuse of per capita measures, Science Media Centre
2024-03-20
🏷 media; news;
Read the comment on SCIMEX.
This is a short ‘expert reaction’ solicited by the Science Media Centre (NZ) on an published article about issues with, and an alternative to, reporting per capita measures. Thomas Lumley also commented, and his thoughts are always a good read!
Data Aotearoa workshop for data journos
2024-03-08
🏷 presentation; slides;
Direct link: https://lizabolton.github.io/data-aotearoa-2024/
2023
Data democratisation panel, Science Communicators Association of New Zealand
2023-11-17
🏷 conference; presentation; recording;
Facilitator: Dacia Herbulock
Panellists: Keith Ng, Karatiana Taiuru, Liza Bolton
2023 Science Communicators Association of New Zealand Conference: Techtopia: Navigating the power, potential and perils of technology in science communication in Te Whanganui-a-Tara Wellington, Aotearoa New Zealand
Watch the video on YouTube.
See post with resources and links here.
Warrantless searches: Ongoing racial bias evident, comments for a Sunday Star-Times piece by Eugene Bingham and Sapeer Mayron
2023-07-30
🏷 media; news; interview;
Eugene and Sapeer did some excellent work on data from an Official Information Act request on warrantless searches. Sapeer and I had a chat about missing data, measuring ethnicity and data collection procedures.
University of Auckland professional teaching fellow in statistics Liza Bolton says recording ethnicity accurately is a “well-known issue in New Zealand statistics”.
🔗 Link to article on thepost.co.nz
2022
learnr Interactives or: How I Learned to Stop Worrying and Turn my Students into Pixelated Farmers, Computation and Data Science Education Community of Practice
2022-02-04
🏷 academic; presentation; stats ed; slides;
See the blog post here for more
Slides
Direct link: https://lizabolton.github.io/pixel-farmers-2022/#1
2020
Panel on teaching data-focused topics, Toronto Data Workshop
2020-12-17
🏷 academic; presentation; stats ed; recording available;
Big thank you to Rohan Alexander for organising this panel on teaching data-focussed topics. This was one of my favourite talks I’ve ever done because I got to get creative with it. Unfortunately my use of music kept getting Rohan copyright stuck on YouTube. Sorry, Rohan!
My bit starts at 14:51 but I’d highly recommend the other speakers’ sections!
Fellow panellists:
2019
Everything you need to fall in love with Statistics, an interview with storyo.co
2019-07-11
🏷️ interview;
I met Liza (pronounced Lie-zuh, like Liza Minnelli) at the R-Ladies meetup in Auckland, New Zealand where she was giving a talk on colour palettes. If you ever meet Liza, you will see that it is absolutely impossible to not get a massive positive energy recharge after talking to her. Liza is currently doing her PhD in Statistics, running a consultancy called The Data Embassy, speaking at events, teaching, mentoring. It would be my absolute pleasure to learn more about Liza and share her wonderful story.
Don’t cha wish your ggplot had colours like me?, R Ladies Auckland
2019-06-12
🏷️ presentation; slides;
A lightning talk about using colour when plotting data with ggplot.
2018
Lotto…you’re doing it wrong!, an interview with The Project NZ
2018-09-21
🏷️ media; news; tv; interview;
After hearing that FORTY Kiwis won Lotto first division this week we thought… what are the chances of that?!
So we invited statistician, Liza Bolton, onto the show to tell us her top 5 tips for winning at Lotto AKA… you’re doing it wrong!
Watch on Facebook (~4 mins) Unfortunately this video disappeared with The Project NZ.
Doctoral spotlight, the University of Auckland
2018-05-11
🏷️ interview;
An interview about PhD life at the University of Auckland.
Liza is a statistician and entrepreneur. Find out about her research on mortality inequality in New Zealand, her side hustles and her advice to new candidates.
🔗 Link
The Cambridge Analytica fallout, an interview with RNZ
2018-03-21
🏷️ media; news; radio; interview; recording available;
Social media giant Facebook is having a rough week, it’s stocks plummeting and a “please explain” from congress following reports a political consulting firm kept data on millions of its users.
The Cambridge Analytica files have caused a huge fallout, its CEO now suspended, after a UK newspaper revealed the company used underhanded tricks to sway election campaigns.
It’s a complicated investigation so here to explain why it’s causing so much concern is Liza Bolton, from the Statistics department at the University of Auckland.