Those of you just joining, it looks like people are still trickling in. I'll give it another few seconds, and then we'll go ahead and kick it off. Alright, let me go ahead and share my screen, now that it looks like numbers are leveling off a bit. All right. Well, hey everyone, welcome back to the JSDSE Cause Webinar Series. Today, we're joined by Dr. Finley from the University of Illinois Urbana-Champaign, and Dr. Justice from Pacific Lutheran University, who'll be presenting their work, Why Swipe Right? Career Interests and Aspirations for Incoming Statistics Majors. Joining me in hosting and moderating the webinar today is Alex Reinhart from Carnegie Mellon University, who is also an associate editor with JSDSE, and I'd also like to give a special thank you to Andrew Ferguson, the cause webmaster who manages the cause website, the listserv, and handles the tech for these webinars. Before we turn it over to our speakers, we've got a couple of announcements to make, and at the end of the talk, you can put your questions in the Q&A, and we'll help share them and moderate the discussion. First, I want to highlight just a couple of recent articles from the journal. Now. There's never enough time, as you'll hear me say at all of these webinars, to discuss all the cool work that's published in JSDSC. So, as usual, I've tried to select just a couple of the most recent papers, which cover a variety of the types of articles that get published in the journal, as Ifia Bednarovska-Mikhail, and Emma Uprichard have an article on bringing interdisciplinary data science education challenges into the classroom. Nicholas Busberg and Laura Taylor have a paper on student perceptions of group work and formation strategies. Bodong Chen and co-authors have a paper on seeing our world through data, 6th graders integrating data investigations and Collaborative Knowledge Building. And Laura DeLuca and co-authors, including my co-host today, Alex Reinhardt, have an article about developing student statistical expertise through writing in the age of AI. Now, this last paper that I mentioned here is also going to be the topic of a webinar in the fall, so if you're interested, stay tuned for that. Next, a couple of cause announcements. U.s. Cuts will be happening this year. Most of the deadlines for that have passed, but registration is still open, and if you'd like to do a Birds of a Feather, the deadline for that is June 20th. And the next JSDSE cause webinar is going to be on Tuesday, June 10th at 1pm Eastern Time. Please note the change from the usual time slot, and that's going to be on the design and implementation of a Bayesian data analysis lesson. Registration for that webinar is going to be available shortly on the CAUS website. Alright, on to our wonderful speakers. Dr. Finley is a teaching associate professor in the Statistics Department at the University of Illinois Urbana-Champaign. He primarily conducts qualitative research, seeking to build theories regarding students' intuition about statistical concepts and students' disciplinary perspectives about statistics and data science. And Dr. Justice has a passion to help students develop into skillful and ethical data storytellers. She has authored and co-authored several papers related to the teaching and learning of statistics and community, and papers exploring students' perceptions of the discipline of statistics. She's the 2024 winner of the Mu Sigma Rho Early Career Undergraduate Impact Award, and was recently awarded tenure and promotion to the rank of Associate Professor at Politico Pacific Lutheran University. Um, and not teaching or writing, she likes to geek out on board games or get outside with her family, hiking, exploring, and throwing rocks in water. Dr. Finley and Dr. Justice, welcome, thank you so much for sharing your work, and we're really excited for your presentation. Thank you so much! Um, so let me… share my screen, and get started from here. Um, so first we just want to say thank you to two of our co-authors, uh, Chris and Florian. Um, so they were also co-authors on the paper, and they were part of the Kind of data analysis and discussions, um, that we had. So, um, the work we're sharing is also work that they were creative authors on as well. Um, and also to our participating students, um, that we gather data from. So, um, we were motivated by, um, our… our study here based on just some work that Nicola and I had independently been doing on… students' perspectives as statistics. Um, there's some literature from the 2000s on this, and then Nikla and I and Florian each, uh, published some papers, um, kind of around a similar time. Trying to add on to some of this literature, but to keep it brief, let's just say that students' perspectives of statistics can usually be, um, kind of described on the spectrum from statistics as tests and procedures to statistics is real-world meaning-making, with a few different categories and possible other dimensions as well. Um, however, most of this research is based on cross-sectional data, and usually focusing on the perspectives of undergraduate students who are taking service courses, kind of like a one-time introduction to statistics, but not necessarily students who are planning to continue in working with data or majoring in statistics. So, Nicola and I ended up discussing together, and we were kind of curious about the perspectives of students who were actually majoring in statistics, and maybe it'd be worthwhile to do some research, um, with that population. And also, just wanting to understand the experiences that seem to shape their perspectives, and maybe their sense of belonging, so really kind of getting a bit more of a longitudinal perspective on these students. So, we kind of formulated this study with this motivation of what is attracting and retaining students and statistics programs. So the recruitment idea, just asking, is statistics attractive to these students? What is kind of getting them to, as we might say, swipe right on statistics? If we think about statistics as kind of being like a profile on a dating app. Where students are choosing majors. Um, why are students attracted to the profile that statistics is putting out? Um, and then secondly, what about the retention? Um, our students' initial perceptions of statistics actually accurate? To what statistics is really like. Do they find what they're expecting, or do they find something that ends up being a bit different? And are there any early experiences that really solidify or perhaps shake students' sense of belonging? In statistics programs All right, so, um, this study is part of an ongoing longitudinal research study that's been going for about 4 years. We've had a total of 9 incoming statistics majors, and they were all from a large Midwestern university in the United States. Uh, the Y-swipe Right paper is based on these 9 students' first-year interviews. The interviews were semi-structured so that we could probe further into what they were thinking. They were conducted via Zoom, and we had one to two interviewers per interviewee. We're still, spoiler alert, we're still following 6 of the students, and, um, some have graduated and started careers, and we'll share a little bit of our insights based on the interviews after as well. So, to recruit participants, we sent an email to all the incoming statistics majors at the university, and from that, next slide, we had three participants, um, two female and one male, um, who are interested in participating, and they became our first cohort. Um, so the next slide shows the timeline, sort of. We interviewed them in the fall and spring of their first year, and then every subsequent spring after that. And this spring, we've, so far, we've only interviewed one. But we have great relationships with the other two, and we expect to interview them later this year as well. So then we did it again, um, sent the email out to all the incoming statistics majors the next year, and we had 6 students respond. And they became our second cohort, and those students we interviewed in fall and spring of their first year, and every subsequent spring, but as you can see by the kind of grayed-out students, that some of them stopped interviewing with us, and so we're still interviewing 3 of those students, and that became our second cohort. Um, some of the students have graduated, so you can see the little graduation hats there. Um, representing when they've graduated, and that's been really great to continue to follow them into, kind of, their careers. And the Why Swipe Right paper is based on the first year interviews, um, for both groups. So, um, you can see they're highlighted by the yellow box. The paper is primarily based on these interviews. So, for our interview questions in the start of year one, we first kind of asked them to imagine if statistics were a person, and Based on their personification of statistics, to think about and tell us about who that person would be, and also to draw a picture, which many of them were very uncomfortable with, drawing a picture of their, you know, personified statistics. Um, and then we would probe into things about, what do you think are the skills and character traits that are needed to be successful as a statistician? And then we asked what drew them into a statistics major, and we also asked if they had any experiences working with data that they could tell us about. And then at the end of year one, we asked, to what extent their views were the same or had changed, and then, um, also we asked them to reflect on any projects as well. Alright, so then our refined research questions for year one, um, so just kind of motivated by, um, our starting, uh, place, and then, um, kind of, as is usually done with qualitative research, you let the research questions kind of get refined and emerge as you start engaging with the data. So, for this year one data, we ended up, uh, uh, stating three different research questions. The first being what aspects of statistics do incoming first-year statistics majors find attractive or unattractive, and why? What are the common characteristics, perspectives, or experiences of students who choose to major in statistics? And what future do these students see for themselves in statistics? And we also, uh, chose a framing that we kind of teased with the title of the paper, Why Swipe Right? Um, that we kind of naturally started thinking about the way that students were talking about choosing statistics a little bit like the way you might talk about, uh, swiping right on someone on a dating app like Tinder or something else like that. And so, we decided to kind of look a little bit at literature on attraction theory to see if there would be any inspiration for our research in this question. And, uh, two kind of prevailing theories when you read about, um, attraction theory is, number one, complementarity theory. And that's this idea that people are going to be attracted to others who have characteristics that they aspire to have more of themselves. So when you think about people saying opposites attract, they're probably talking about complementarity theory. But it's not just the idea of, oh, you're opposite of me, but it's specifically, you have a characteristic or an attribute that I want more of. Maybe I tend to be more shy. And you're a little bit more spontaneous, and I want to be a little bit more spontaneous, so I… I find that attractive in you. But there's also similarity theory, and that just says that relationship seekers often find more stability with people that have characteristics and values that are in common with them, and give them feelings of safety. Um, so you have to have at least some level of similarity, um, to usually have a long-term stability in the relationship. So, thus, choosing a romantic partner is usually going to be some balance of similarity and complementarity. So, enough similarity that you can kind of stay together, and it can kind of work But enough differences that you find idealistic that kind of keep things interesting. And we definitely saw this theme reflected in a lot of what students were saying about statistics. This theme of balance came up a lot, um, for literally all of the 9 students in some way. Um, so, some examples of what similar kind of came out to be. Students a lot of times talked about statistics as being the safe choice. That it mirrored a lot of their own perceived strengths. Um, 8 out of 9 students identified as being good at math, and that being related to why they chose statistics. Students oftentimes talked about being more analytical. Or they talked about having a good experience in their AP statistics score. So that was what we kind of thought about as the similar side of why statistics felt like a good choice. But there was definitely some complementarity here as well. Um, so statistics was attractive because it offered exciting and far-reaching opportunities that wouldn't leave them feeling stuck. Um, students frequently talked about statistics as being something you could apply to almost anything. That I can find data for something I'm interested in, and I can do statistics in that area. Or there's always new tools and methods for me to learn, and students also talked about some of them feeling a little bit more introverted or shy, but feeling like statistics was a space Where they would be working in some community, not too much, um, intermingling, but at least some community that they liked the idea of. So, on this theme of balance, we identified 3 different, kind of. Sub-themes here that talk about what… how this balance manifested, and this first theme is Society of Balancing Individual Work with Collaborative Opportunities Um, and this came through in a couple different ways. So, so Lobos, for example, talked about being a connected workplace contributor. She said that I always want a job, or I want a job where I don't always have to rely on others. But my purpose is to communicate with others. And I think it's really cool how data's becoming a big form of communicating information and helping businesses grow. Um, so she wasn't necessarily wanting to do a lot of, like, you know, really integrated work. But she liked the idea that her work was somehow connected to what other people were doing. There'd be some communication between different different people. Um, there's also some discussion of consulting, so Hansen had a good quote about this. He described statistics as meeting with a client to understand their needs, applying your expertise, and then building something that might fulfill that need. Um, rather than kind of represented this more researcher-academic perspective, where she liked to, uh, she loved this idea of spreading knowledge. Um, she talked about people who do statistics love to help people get into the community and just be more in it, so she had the idea that she would be maybe a professor one day. She was interested in doing research. And just her experience so far with other professors or with other researchers was that it was just this big community that you're sharing knowledge, and she loved that idea. We also saw some of this reflected in students' pictures, so 6 of those pictures are down below. Um, but as a reminder to what Nikola was talking about, we asked them to first describe if statistics were a person, what would they look like. What would they do on the weekend? Who would they be friends with? And a few other kind of questions related to that. And so we got them all to kind of talk about that first, and then we had them draw a picture that kind of represented who they were talking about. Um, but a big theme that kind of came from these pictures relates to this idea of individual work and collaborative opportunities And that these students really tended to think of statistics as being a little bit more introverted themselves, but was kind of the connector of people. Um, so Clara said they're social on the weekend, but more low-key. They wouldn't go to big parties. Robin talked about statistics being attracted to people who are kind of the opposite of them. Maybe a little bit more loud and extroverted, but they'd kind of find comfort in relating to people who were a bit different from them. Hansen said they hang out with people of all kinds of interest, not just this person might be interested in numbers, but also people interested in other kinds of fields. And he also talked about statistics as being kind of the glue of the group. And we saw some of these discussions as perhaps being aspirational for the students. They wanted themselves to kind of fill that role, or they saw themselves maybe filling that role. Um, where they were a little bit more introverted. Um, but liked the idea of being connected to others. A second theme related to balance is balancing a safe career choice with room for the students' passions. So, a lot of the students talked about having other interests outside of math, um, and many of them were idealistic about the idea that maybe they could still work somehow in that field while doing statistics. Um, Lois said, I think there's just a lot of opportunity in the field, and I can apply it to, um, or I can apply it, because I have other interests as well, so I find it very easy to find, like, a company or a business where I can apply statistics to something I love. Eleanor talked about just wanting to join a research organization or institute that's working to tackle a big global problem, like climate change or poverty. I think statistics is like a bridge between the science-y careers and other careers. They're kind of in the middle. So for Eleanor, we kind of see that connection between science-y careers, math-y careers who are a little bit more safe, they're more dependable. But I can connect them to things that I'm passionate about. And then Pete was really interested in baseball. He said he loved math at an early age, and then at 12, That's when he kind of realized, oh, I can actually do this while also enjoying baseball. There's kind of this field of baseball analytics, and maybe that's a way for me to connect, kind of, my passion with my strength and In mathematical, um, uh, subjects. And then the third theme that we'll talk about is balancing the idea of math But not doing formal mathematics. So, basically none of the students were all that enthusiastic about majoring in mathematics. That was… that was a pretty consistent theme. Apollo even just said, I couldn't imagine only studying or hanging out with math for four years. I would want to try to do things that are more interesting. I think I'm good at math, but I think math is boring. And Alex kind of said something similar. She, um, or they had had some experience with Calculus and differential equations, um, for dual credit And they said, okay, I don't know if I want to do this as my major, I really like the stats aspect, and I know that that involves some calculus, so maybe that's a pretty easy way for me to kind of weigh those two options, is I can still Do some of the math, but I'm not just kind of committing completely to mathematics. I'm still doing something that's very applied and useful. Robin was one of the only… was the only one of the nine who really said that they didn't like math, so she just openly said it, I hate math. But I love statistics. But she understood that statistics involves a lot of math, and she said that she was working on liking math to become better at statistics. There's a little bit of a compromise for her, but she definitely wasn't interested in doing more math than she needed. But she was okay doing some. She felt like she was at least okay or good at doing math, she just didn't like doing math. All right, great, thanks. Um. So, I get to discuss some insights we've had, and questions that we're asking, both based on The first interviews, and we'll give some sneak peeks into what we're noticing after interviewing these students for 2-3 years after the first year. First of all, this balance between individual and collaborative that Kelly talked about. We're seeing this continue throughout the students' careers as statistics majors and into their jobs. So, um, oftentimes they'll have an internship that will have them share about a little bit, and one of the first things that they'll say is. I really liked the balance between collaboration and individual work that I had. Um, or in their job, same thing. We'll say, tell us about your job, and one of the first things they talk about is. How they like the collaboration and the individual work balance. So this is something that really seems to persist. Throughout their careers, um, throughout their careers as statistic majors and into the jobs market. Secondly, um, when Kelly talked about safety, one of the aspects of safety that we've seen come up is, um, a favorable job market Students really tend to believe that after they major and get their degree in statistics, that it will be easy enough for them to find work. And their families are also often supportive, um, for that reason. Now, at the time that we started this research, um, statistics and data science were number… Um, 4 and number 3 in the fastest growing occupations in the… according to the Bureau of Labor Statistics. And so, this has just come to have us wonder, what's gonna happen when statistics is not perceived as growing so quickly, and is maybe not such a favorable job market? Um, are the same kind of students still going to swipe right on statistics? Then, as for the math, but not mathematics. We're wondering, um, you know, students often talk about how they like certain aspects of math, such as Getting a definitive answer, and often, like, putting a box around the answer, maybe being able to prove something is right. Or am enjoying a procedural aspect of math. And so this has caused us to really wonder how students handle it. When in statistics they encounter answers that are not so certain, or when the practice becomes less procedural. Another major theme that we've seen is to do with the computing journey. So, many students have been blindsided by the role of computing in the discipline. They struggle with imposter syndrome and with a sense of loneliness, like, I'm the only one who doesn't know how to code, everybody else knows how to do this. Um, we noticed that some early coding experiences were critical for helping students stay engaged, and we're wondering, what are the characteristics of those coding experiences That really helped them stick with it, um, or that… what are the characteristics that they perceive were really standing out as important to helping them persist. Even through the coding struggles that they had. Some students took several years to come around to really enjoy coding. Um, so we call this… we've been talking about it being like a long on-ramp into coding. And that's really important, because for me, sometimes I'm, like, Miss Quick Fix It, and I think, like, oh, what if we made some… Modules that could just go after the AP exam that would expose students to decoding, it would solve all the problems. But now I'm less convinced that that would be an amazing idea, because I wonder if it would just scare students away and not really give them the time with that long on-ramp to come around to coding. Um, coding for the students who grew to love it really became, um, a sort of means of transportation. Um, where they could get where they needed to go. So, they really enjoyed this aspect of choosing the best route, or the flexibility with how to get there, and so coding kind of just became a vehicle by which they could enjoy statistics and enjoy the discipline. Some students just never grew to enjoy coding. Coding for them, as opposed to a vehicle, became a barrier to their participation. Um, oftentimes they got through it just with, like, grit. Um, and… but not really with fluency, and, um, transportation sort of became the journey. Um, so the… it became the goal was just to get there instead of really Seeing where they'd gotten and how it related to other things, and so it really became a barrier. And this has caused us to wonder, is there a place for students in the discipline who just don't love coding? Um, and I don't have an answer to that, but we wonder, is there a place for them, and if regardless of what the answer is, what are the implications for that, for the discipline? Another theme that we've looked at is how students grapple with subjectivity. Um, and I know that there may be some controversy about how much subjectivity there is in statistics, but I think most of us would agree that even within disciplinary conventions, when doing statistics, we often make decisions that affect the outcome, and that a different practitioner might make a different decision, and that will affect the conclusions. Um, that are made. So we're curious when and how students come to recognize this human influence in statistical practice. And how do they respond? Do they love it? Does it draw them in? Or does it make them really uncomfortable, and does it kind of deter them from the discipline? Um, we're also interested in what learning experience tend to promote this kind of grappling with subjectivity and with the human influence. Um, and then on the right, I have this image of the investigative cycle. This is just one depiction. There are many others that are more detailed and more thorough. But I have that there because we've sort of started to find that, um. Different aspects of the investigative cycle, um, for different aspects, students are more open to and aware of the human influence Um, and for other aspects, students are very resistant to the human influence. Maybe they make more excuses, or they're even sometimes in denial about the human influence for that aspect of the Of the investigative cycle. So it's really been fun to probe, um, that among our students. And if you want to know which is which, you can ask in the questions, but I'm not going to say anything now, because I want to give you a chance to think about which parts of the cycle you think would be more or less conducive to students thinking about the human influence and accepting it. Alright, all of our students who took AP Statistics had something great to say about it, but for different reasons, so we wanted to give a shout out to the AP Statistics teachers, um, and talk about that a little bit. So, Tony credits his choice to major in statistics to his AP experience. He talked about cool applets and simulations that the visual piece really drew him in. Robin didn't really like definitions and basics. Um, but when it got to real-world applications, Robin was really interested, and Robin talked about the Her teacher being very patient to discuss ideas further, point her to resources where she could attend webinars and learn more. Um, so the real-world applications really drew Robin in. And then Alex, for better or worse, really was into the procedures that made the process clear. And I just love to point out, I'd like to read the end of Alex's quote, I see this problem, I know how to approach this, I can go ahead and do yada yada yada and get an answer. And I just love that I got to quote Seinfeld In a research presentation, so thank you, Alex. All right, for future work, um, if you're planning to do any studies about this. Please learn from our mistakes. We wish that we had included other sources for triangulation, so… Journal entries would have been fantastic to ask students to complete, to kind of get more rich sources of data. We would have loved to have advisors and mentors complete surveys that we could kind of get a bigger picture of what their experience was like And we also would have liked to have access to transcripts, not necessarily for grades, but we would love to know from the students that sort of stopped interviewing with us. What did they end up choosing for their major? We would really just love to know that. Um, we'd also be interested in a more geographically and racially diverse sample, and we'd also like to explore who swipes left, so to interview students who are entering in related fields, such as CS, economics, math, and business analytics, and just learn more, why did they choose that instead of statistics? All right, so here are our references, and I noticed that even one of the authors from these is attending today, um, so anyway, thanks for the work that you did. Um, uh, giving us a foundation to work from, but I'll leave that up for just a second so that you can take a screenshot if you'd like, but I know this webinar recording will be made available later if you… or you can email us if you would like. And then as we answer questions, we'll just go to the next slide. Oh, it's not there. Oh, that was… I thought it might be there, but it's not. That's okay. Which… which one are you thinking of? Um, I made a slide that had the students' pictures, and, um, but I must have done it on a different slide deck, um, but I can… maybe I can share my screen as we, um, answer questions, because it also had our Um, it also had our contact information. Sure. Ooh, okay, yeah, if you want to, go ahead. Okay. So, I'll stop there. Uh, slideshow… How's that? Can you all see it? Okay, great. All right, thanks, everybody. Yeah, we're ready for questions. Yeah. All right, thank you. So, I will lead in here. Uh, with a couple questions, and then anyone in the audience, if you have questions, there's a little Q&A button, feel free to jump in, type your questions. Um, I think we've got… we've got some time here to go through questions, so feel free to jump in, um, or press the raise hand button if you'd like to… you know, jump in verbally, and I'll… I'll look at the list, um, as we go through some questions. So to get us started. I had a thought, um… while you were talking about the role of math. Uh, so you mentioned there was this… or differences in how the students appreciated Um, the role of math and statistics, some of them thought, well, I'm good at math, but I don't want to just… just do math, so this seems like a good fit. You also had the one who said, I hate math. Um, and he talked a little bit also in your paper about how there's this trade-off between math detracting some students and being a barrier for others who aren't really into it. I was wondering if any of your students The role of math in statistics is particularly for, like, if you go into statistical theory, right? The more theory you do, the more… important that math is going to be. So I wonder if any of them talked about stat theory at all. It seemed like most of their justification, their reasoning was about, I can apply it to different things. I don't know if they were even sort of as freshmen, maybe aware of what statistics theory looks like, but that would also be interesting to know Yeah, I can start, and Nicola, please jump in too, but, um, so one thing that I'll mention is… Several of the students enjoy their mathematical statistics courses, several, not so much. One described it as, like, it's like the history of statistics, and she didn't really understand Why she needed to take it. She was just like, I guess this is a course we're all supposed to take, but it just feels like history. Um, several enjoyed it. But none of our students were on a trajectory to really do more theory work. Um, several were interested in doing masters, but usually on a more applied side, like, one's doing a master's in computer science, one's doing a master's in statistics, but much more interested in the applied, um. So, so even Alex, who was very mathematical, very, very procedure-driven. We had a theory that they would really like the mathematical stat piece, and maybe not so much the other pieces, but Alex really like the applied piece. Alex really fell in love with coding. They fell in love with more applied work, and we asked them about it, and they're like, yeah, I guess, you know, mathematical stats was fine, but I just care about what I can do with it now. Um, so I guess my first instinct to that… to that question is, um… That… that despite having a love of… of, you know, the mathematical procedures in some cases. It was more like something to get them in the door, but not something that long-term mattered as much for their retention. Nicola, do you have thoughts on this, too? I think also just another thing is that the individual versus collaborative Balance was really related to the math, but not math balance, and I think Due to… maybe imperfect perceptions of what it would like to be a statistical theory person, that it would be a very individual, like, they'd often say, like. I don't just want to sit at a desk and do problems all day, like, I want to talk to people, and so if you don't… And this is related to, I think, Rolka and Bollmer's work, too. They… there was, like, this, like, um… Uh, now I'm nervous to, like, misquote them, but it was kind of, like, this idea that maybe the mathematician just, like. Sits in an office all day, doesn't talk to anybody, and so that… I think that kind of misperception that in research and statistical theory that there's not a lot of collaboration. Um, might be trickling into that, like, I don't want to just do math all day, or I don't want to just do stat theory all day. Interesting, interesting, that makes sense. Um, small follow-up, I'm interested how… In the subsequent years, what did the students who said they hated math? How is the reaction to their later coursework? Hmm… So, unfortunately, Robin is not one of the students who continue to interview. I think we got the first fall and spring, but we haven't heard from Robin, uh, since for interviews. Um, I… So I don't think I can really comment much more. I think I can say Robin Stayed in statistics. I do know that much, but we just weren't able to… Robin again. Okay. So it's hard to know what happened with the math there, but… This was also just to follow up on that, something that we noticed and we wondered is. Do you either have to have math or have code? Like, does one of those need to be your… like, handhold into the discipline, and as long as you have one of them, you can kind of, like, climb your way through to the other. Through the other, and so a lot of students coming in, like, had math but didn't have coding. Robin actually had done a really extensive internship where she had been thrown into R and, like, mentored in R. So, even though the math wasn't strong, the code was strong. And so, we… I think we are kind of seeing… you have to have at least one of those two, math or code. Um, in order, and so it might be the code carried Robin through. Mm-hmm. So was it the case that more of the students had like, AP Calculus, or a math experience, then had a lot of programming, like AP Computer Science or something else Yes. Um, I think we had two students who'd had, like. Pretty definitive coding experiences. Another 2 or 3 that had dabbled with coding, and then several that had no experience with coding that were just they walked into their first course, and we're a bit blindsided by the coding. Hmm. Mm-hmm. Um, whereas basically everyone had had either AP stats, AP Calculus, those were… much more common among the students Hmm, interesting. So let me ask… I see a question in the Q&A here. About the department the students were in. Were these… so these were statistics, declared statistics majors, but this is… is this a pure statistics department or a math department with a stats major? Or some combination of those things. Yeah, these are 9 students in a statistics major and a statistics department. Um, there is a separate mathematics department at this university, so… They're both in the same college, but the students are very much committing to statistics, um, and applying to be a statistics major in a statistics department. Mm-hmm. Cool, um, I just had a thought, and then it… disappeared again. Um… Oh, uh, and at the university, is it typical for students, most students, to have a declared major when they come in, or do students tend to… Some of them come in undeclared or, you know, in a general area, and then find something after a year or two. There are a good number of statistics majors at this university that, uh, transfer in or declare after admission to the university. It is a university where you declare… usually you declare for a major, and so that is how we identified our pool, is we specifically went after students who declared a major in statistics upon admission to the university. However, we're missing about a third to 40% of the statistics majors who ultimately graduate from the program. Hmm. Who don't start with the statistics major. A lot of students actually choose to add a double major in statistics at this university, so… so this is definitely a bit of a biased crew that we're looking at. The ones who start in statistics, who are kind of committing to it from the beginning. Okay. Um, and I see another question in the chat that's interesting whether you know, you mentioned several of the students had taken AP Statistics, and that was an influence on their you know, it's a positive experience. Uh, do you feel like the AP stats or other, like, sort of non-math stats courses Give them an accurate picture of what they're gonna end up doing in a statistics major, or what statistics is. I don't think that we can answer that question very well, because… Most of our students had done AP statistics. Um, and there was only, I think, one who had done a non-AP… I don't… Right. When did a college intro online course in stats, and then one didn't have any stats. Hmm. And I think it was during the pandemic, so you can't… yeah. Hmm. So that's really tricky to… to… to say. I will say that AP, in a lot of ways, I think. The AP stat, um… course, in a lot of ways, did a really great job with the real-world applicability. Like, a lot of students took that away. Um, that they could, you know, that statistics could be used to really, like, gain insights into The world, um… if I was gonna change one thing about the AP, Um, program based on, um, about the AP exam and so on, based on this research. I would be so keen for them to do a project that they submit as part of the AP exam, the way that computer science has started to have students do a project. Um, because the richness of students perceptions of the discipline. And their, um, kind of how much their perceptions of the discipline matched what we've used statistical thinking to be, according to Wilde and Fancouk's seminal papers, um, around 1999, Um, was so much better matched, we found, when they had rich project experience, and so… Um, if I was gonna… uh, you know, really push something to the AP program based on this work. It wouldn't necessarily be to do a big coding overhaul, where they have to learn to code. Um, I would save that, actually. But I would say they really ought to submit a project the way that computer science does. I… yeah, and I think that, again, it's a very small sample size. We don't generalize very broadly, as much as we're just kind of noticing theories and asking questions. The students who had a project experience in high school tended to have a little bit more of a comfortable adjustment into the major, and with the coding, it was… the couple of students who didn't really have any kind of project were a little bit more hit and miss about How well they were able to adjust. We definitely noticed that that was… a lot more struggles with recognizing subjectivity, feeling agency over their work with data. Hmm. And that seems to connect with another question I see here. Um, talking about how a lot of students had a good experience thinking, oh, I'm good at statistics, like, in their AP stats class, but then discovered later how much math, how much coding, all these other things that are involved. Uh, so the question I see is whether there's some way to we're under prepare them in advance. Uh, maybe in AP stats or otherwise, of what… more what the major looks like. Mm-hmm. Yeah, I don't know that any of our students, at least the 6 that stayed with us, we can't speak to the 3 that we didn't hear… hear from again after year one, but of the six who stayed with us, none of them really got scared of the math. Like, they seem to at least make it through, whether… they, you know, thrived, or whether they just kind of… muddled through some of the math. Um… they were able to get through that. I think that the biggest discrepancy Nicola and I noticed was with the coding and the comfort with the projects. That was a big theme with some of these students finishing their major now, where it's like, wow, there are some big discrepancies in how comfortable these students are Working with real-world data, and… you know, even just doing… doing some coding with that. I think regarding that question in the chat about should we warn them or prepare them beforehand. I don't know, it's really tricky because So many of them were, like, terrified. But then when we asked them, you know, later on to reflect back, like, what would you tell an incoming student? They said, like, you know. Just stick with it, like, you can do it, you're gonna grow to love it, and that kind of stuff, and um… So, I don't know if warning them about coding will just, like, scare them away from the discipline. I feel like, morally, like, divided, because Mm-hmm. You really… the students in our… in our study, they already were kind of a stat major, and so they had, like, a certain level of, like, commitment that were like, I gotta just I gotta just figure it out, and then they ended up loving it. So if you tell all these, like, AP stats students, yeah, you're gonna code a lot, like, are they gonna be like, oh, never mind? When it's like, really, they should give it a good shot? I mean, and part of this maybe is my own bias, because I didn't… I wasn't really excited about coding until Andy Ziffler, like, forced me to do it a lot, and then I grew to love it. Um, so anyway, I… I have mixed feelings about how to warn them now. Mm-hmm. Preparation, you know, if we could do, you know, if they can take, like, an AP computer science course at the same time Um, I mean, that was great. Our students who had a lot of coding experience were… but I don't think it should be viewed as, like, necessary that they… because they can… Do it. One insight that was really interesting that we kind of probed was, why are you not a computer science major? Like, once they learn to code, you know, and then… Um, we kind of realized that the statistics students tended to say, I… The computer science students, kind of, they would, like, build something, like, they'd build software, and then you could, like, check that it works, and they're like, this is my product that I built. And our statistics students tend to say, I don't think I'd like that as much, because my goal is to get insights. Like, I like to learn. And to learn about what I can. And so the, kind of, the difference in the goal between building a product or building something that creates something versus learn about something was an interesting distinction that we saw. Coming up. Yeah, I just want to echo that last piece as kind of like, what is… what is the takeaway? How should we attract students? I think what Nicholas said is… is the thing, and that is help students think about like, statistics is the way to learn how to build insights from data. Um, it's not necessarily statistics as a way for you to use math, statistics is something that involves coding, it's, like, it's something… it's a discipline that lets you be a lifelong learner in your job. And learn how to learn from data. I think that was something that a lot of the students really resonated with from start to finish. Great. Well, I would… I would… bring in another question here, but I think your psychic can just answer it, is there's one question from my colleague here, Zach Branson, about differentiating a statistical career from a software engineering career, and the differences which he just Hmm. I think just addressed there. And that does bring us to 445, um, and I think That's all of our questions I see. I do see we have a link, if anyone's interested in the chat Apparently, the College Board is looking at project-based learning and AP statistics, so… Another also psychic, I guess. Um, but with that, um, thank you both for taking the time to present this, and thanks everyone for your interesting questions. Um, hope to see you