Anna McGaughey (Conference Committee)

Anna’s JRA project focuses on the interplay between mental health and R studio. By conducting twelve, 1 hour, 1 to 1 interviews, her research found that there is an interplay between mental health and R, whether that is through engagement, dread, empowerment or things we can do to improve the learning and teaching of R. Another important finding from her research is the idea that social networks can help to improve the process of learning R due to bonding over the love/hate of R. Or hinder the process with the pressure of supporting peers. 

To find out more about her project, you may check out her poster and additional insights here!

Magdalene Ho (Mag) (Blog Editor & Conference Committee)

Mag’s JRA project focuses on the interactive influence of statistics attitudes and career goals. With a quantitative survey based on the expectancy value theory, in combination with a content analysis of qualitative responses, her research found an interaction effect between valuing and expecting to do well in statistics, on the extent to which students planned to use statistics in their future careers. Further exploratory analysis also revealed a potential reciprocal relationship between statistics attitudes and career goals. To find out more about her project, you may check out her poster here, along with her supplementary website with deeper insights!

At first, I never really knew what to think about statistics in psychology - it seemed like this big, technical thing that could be quite intimidating. I was never really a massive fan of maths but when thinking about why you do statistics it really makes sense. To see the really cool results that you have produced! 

Although I had the added benefit of enjoying maths before pursuing higher education, I surprisingly didn’t enjoy it and found it quite intimidating! That was before my degree though, where I was taught in a very traditional way (i.e. to understand concepts through hand calculation, but to simply interpret results when using statistical software) for my Psychology diploma. So statistics remained a mystifying practice, and was simply for me to ‘prove’ something rather than to unpack nuance. I held onto this impression for years, even in my previous job doing research and programme evaluation for a charity!

The way it was taught completely changed my feelings towards statistics. The constant reassurance, regular testing, and fun animations made it so much more engaging than I expected. I actually started to enjoy it because the teaching made it feel approachable and interactive. Also being exposed to Jenny’s student-as-partners approach really helped me enjoy it as I could be involved in all these really cool projects. 

It made statistics make sense, and played a huge role in ‘fine-tuning’ my confidence in conducting research. I had already done research, but due to my previous impression of statistics, I felt like I hadn’t really properly done it. Having unclear concepts clarified, learning how to engage with my data more deeply, to choose the best test and cutoff values rather than just the standard, etc., the undergraduate curriculum showed me exactly how cool and enjoyable it would be to apply what I have learnt into research.

I was fascinated by the extreme differences in how students felt about statistics - either loving or hating it, unlike other areas of psychology. This curiosity drove me to research what shaped these contrasting experiences in statistics education.

Because it seemed like everywhere I go, at every educational/professional stage of my life, there would be a significant amount of people around me that hated statistics, so I wanted to break that down and explore why. These observations aligned quite well with research gaps, where there hadn’t yet been any investigation into how career goals could affect statistics attitudes. Especially at my previous workplace, where for many of my colleagues, a significant enough reason as to why they steered away from research and further education was because of this hatred.

It will be a combination of things and those things will be different for everyone, of course. Psychology students are often deterred by a) a preference for learning about the applications of psychology, rather than the scientific nature of it and b) an aversion to statistics, usually derived from negative past experiences with mathematics. On the flip side, we often see students who give it a chance, surprise themselves by how well they do which improves their confidence, and then they fall a little bit in love with it (like Hanna’s own example, below!).

The statistics modules were really helpful for understanding quantitative research, but my project focused on qualitative methods, which weren’t explored as much during the Psychology Undergraduate degree. Because of that, I needed a lot of extra support to navigate the research process. As there are so many areas of thematic analysis to think about! 

The taught content built such a solid foundation for my research project, even the qualitative bits! The emphasis on using code to transparently display your analysis made me want to meticulously cover every possible process, from reliability, to accounting for missing data, versus just itching to get to the main bits. Key differences I noticed were that a) real data is messy, so much more than practice datasets, and b) it gave me the opportunity to learn more statistical tests and concepts, which really just highlights how valuable research experience is!

One of the biggest challenges was working with qualitative data, which required a different approach than the structured, number-driven analysis I was used to in the statistics modules. Unlike assessments with clear right or wrong answers, I had to think more critically about interpretation and context.

Similar to what Anna said, working with qualitative data was incredibly insightful but challenging. I never knew of a more systematic way to ‘quantify’ qualitative data beyond thematic analysis, until Jenny introduced me to content analysis! It was so satisfying to be able to use this ‘quantification’ to support my hypotheses (of course, not forgetting nuance), especially at an exploratory stage, it really strengthened the importance of the topic. At the same time, you could really go on for forever and code the data in a million ways, so finding balance (and not driving my co-coder Hanna mad) was difficult.

My research underscored the link between mental health and learning, showing how anxiety and confidence impact engagement with statistics. These insights can help instructors, advisors, and mental health professionals better support students in their studies.

Because students don’t value statistics (quantitative, i.e. importance of doing well, enjoying statistics, and usefulness, which holds true regardless of self-efficacy), and/or having career goals that weren’t statistics-inclusive (i.e. believing that their desired careers would not require much statistics) caused them to disengage! The qualitative and quantitative findings speak to each other, emphasising the potential of teaching strategies that integrate a wide range of career applications. I can’t make this all negative though, because my qualitative findings revealed persistence regardless of students' goals/attitudes, so I think educators have already made huge strides in fostering an appreciation for statistics!

Working with student researchers is probably my favourite part of my job. Their enthusiasm is contagious and I always learn so much! The projects really benefit from their insights as well - they are part of the population we are researching, so they have invaluable knowledge about what, who, and how to research that can steer things in ways I’d have not have thought of otherwise.

Typically, postgraduate researchers are further along in their learning journeys so will be a bit more independent and their support needs will differ, but it really depends on the individual student and their background.

Statistics are just one part of a whole research system. Getting involved in a real research project brings that system to life by giving students lived experience of its components - it makes the abstract concrete. That usually translates into a deeper appreciation of where different types of data come from, what they look like, and how to manipulate and reason with them.

I think I’ve had a pretty tricky relationship with statistics overall. As someone who struggles with numeracy, I initially thought I would really hate the statistics courses, until I realised that learning R was a tool to make stats more accessible for me. This realization came to me pretty early on in my studies, and was one of the reasons why I even considered a research degree later on. Since then, I have been generally very enthusiastic about learning statistics, and working with different people as stats lead on their projects. However, I had more time to play around and find extra Rstats courses on the internet during my undergraduate course. I still want to learn more, but now as a PhDer, I am finding less time to work on random skills that I would like to learn or build on. So, I think I am in a constant state of wanting to learn more, but I am not finding the time/opportunity to do so.

I believe we’re only beginning to understand the connection between statistics education and mental health, and my JRA was just a first step. It highlighted the need for a more supportive curriculum that addresses empowerment, dread, confidence etc, making statistics more accessible and engaging for all students.

Both mine and Anna’s projects are pretty novel within the statistics education literature, so I feel like a change in perspective is positively inevitable (but isn’t most research!). My experience and findings shifted my personal experiences into an empirical reality, where it affirmed the possibility and importance of considering longer-term outcomes (not just academic achievement/goals) when researching into and delivering statistics education in the curriculum. So I went from “how do you even foster an appreciation for something so hated?!” to “ah, maybe we should expose students to the many wonderful ways stats can be used in their future careers”.

Using the Millennium Cohort Study for my dissertation has boosted my confidence in applying statistics to real-world data. It’s given me practical experience with complex variables and data interpretation, preparing me for more advanced analyses in future projects.

Massively helpful in many areas - Statistics wise, I'm more confident in dealing with messy data, organising analyses appropriately, making adaptations, and going beyond the curriculum in terms of methods and/or code. I actually just took a peek at my dissertation data and thought, had I not done the JRA, I would’ve been so stressed with the messy and incomplete responses I’m seeing. I wouldn’t even have thought to preview and practice analyses prior to the end of data collection. The confidence boost has also made me more excited to play around with variables and hypotheses beyond my main one!

Building a strong support network can make learning statistics easier, as connections with peers can boost confidence and motivation. However, it’s important to be mindful of the pressure that group dynamics can create, while collaboration can be helpful, comparing yourself to others may add unnecessary stress.

Keep asking questions, but most importantly, try to solve them by yourself and/or with your peers before you ask for an answer. This is such a cliché and I know how irritating it is to receive non-concrete advice, but this ‘framework’ has become such an unconscious but helpful practice in my academic and professional journey. If you’re struggling to understand a concept, break it down into its components and identify specific gaps in your understanding. If your code returns an error, don’t raise your hand yet, check and run each line to pinpoint where it went wrong! This is also how research gaps and cool ideas emerge 😎.

I do think that it enhances confidence and I suspect that is due to the increased experience and deeper understanding of research. However, it is usually students that already enjoy research and statistics that volunteer for research assistantships, so we rarely see a complete change in their attitudes. Rather, students tend to come away from the experience having decided whether or not research is something they want to do in their future careers.

It is like I said above - working with the people that are part of the population you are studying can benefit research massively and statistics education is no different. For example, I’ve had students suggest studying phenomena that I was completely unaware of, identify challenges or opportunities for recruiting participants I’d have missed, and pick up nuances in qualitative responses I wouldn’t have noticed. Every time, the research has been better off for their involvement.

Feeling frustrated is part of the research journey, and while it can be stressful at times, when you do get that ‘aha’ moment, it is the most satisfying part of the research journey. If you had mastered all the research skills before starting a PhD, then you probably wouldn't need to do a PhD. I’m also not alone in my journey, I have taken research methods training, I have my supervisors to help me, and my peers and I often help each other out. So, it is really just about building an encouraging environment, and feeling supported through your studies.

I really want to take as many opportunities that I can and improve the future research of statistics education! As they say, the statistics world is my oyster!

I’m working on publishing my JRA project! Though I’m not the greatest at balancing that with my current commitments, I really hope to see it in its full, academic paper glory. I may have departed from statistics education research for the timebeing, but the wider topic of meta-psychology and open science will always be an core part of my ‘research/academic philosophy’. Hence why I’m here at RoSE as a blog editor, and also why I’ve been organising a Decolonial Psychology interest group. One of my goals in the interest group is to delve into how the way we approach data could potentially obscure cultural, structural, and experiential differences. As a side hobby/project, I’ve also been building a personal and academic website using Quarto, I’m slowly reviving my tumblr/blogspot days.

My primary research strand centres around statistics anxiety - what it is and whether it differs from mathematics anxiety. There is still so much to be discovered before we can really answer that question, so I’ll be focussing on that for a while longer. I also undertake various other statistics education research side-quests and am especially keen on researching ways to support students to learn R and in helping statistics educators take their first steps in research and scholarship. Click here to check out what I’m working on.

We are currently organising a ‘Methods for Open and Reproducible SciencE’ interest group within our department. While we don’t quite discuss statistics education directly, these sessions are meant to collaboratively enhance research skills. It is a way to combat gatekeeping research skills, coding tips/tricks, and education more broadly. I have now tutored on all the undergraduate statistics modules in my department. It felt quite strange initially having taken all these modules as an undergraduate, to now be tutoring on those exact modules. I do think it has given me a unique perspective on tutoring on those modules, understanding what people struggle with, what people complain about most, as well as what people enjoy about the modules and what students want out of their education