Alter Everything

A podcast about data science and analytics culture.
Alteryx Alumni (Retired)

Welcome to “Data [in the] Sandbox”, a podcast mini-series for kids! Have you ever wondered what analytics is? It sounds complicated right? Or maybe you’re curious about why data is important to everyday life. Tune in to hear a real life Data Science Journalist, Susan Currie Sivek, teach her friend Maddie Johannsen, about how data collection and analytics can help you solve tough questions, such as “How can data about snacks help Maddie run faster??”





Maddie Johannsen - @MaddieJ, LinkedIn, Twitter

Susan Sivek - @SusanCS, LinkedIn, Twitter







Episode Transcription

MADDIE: 00:00

Hey everyone, it's Maddie Johannsen, and I want to introduce you to our brand-new miniseries called Data in the Sandbox where my friend and community data science journalist Susan Currie Sivek walks me through the basics of data, correlation versus causation, predictive and spatial analytics, and jobs that deal with data. The Data in the Sandbox miniseries is available right here on the Alter Everything Podcast Channel and your favorite listening app or on the Alteryx community. It's perfect listening for any kiddos or teens out there who might be wondering, what is data, what is analytics, and why is it important? It's also great for the parents and teachers out there who want to inspire them. Plus, we just launched a new program called Alteryx For K Through 12, which we'll talk about more at the end of the show. So let's jump into Data in the Sandbox. Hey Susan, so I hear my parents talking about data all the time, the stuff they do with it and somehow it's their jobs. It's weird, but I don't really get it.

SUSAN: 01:06

So what's confusing about it?

MADDIE: 01:09

Well, they always tell me I can't watch too many videos on my phone or play certain games on my phone, and I don't really understand. So data is how much we use the phone? Like when you see ads for, "Unlimited data," for phones? How is that a thing that they can spend all day working on?

SUSAN: 01:25

Oh, Okay. Yeah. I see how that's definitely confusing. So it's not quite the same thing, no.

MADDIE: 01:32

Oh. What is it then?

SUSAN: 01:33

Well, it's all different kinds of information. Sometimes data is numbers, like on the cereal box, when you see the nutrition information there. Sometimes data could be words, like when people write reviews of things that they buy online and they say what's good or bad about them. And sometimes data might even be other things, like photos or locations on a map.

MADDIE: 01:55

Those all seem like really different things, numbers or words or photos.

SUSAN: 01:59

Yeah. I know it seems like it, but they're actually all just information of different types, and we can get computers to understand all of those too. They're all data that we can analyze in lots of different ways. Really, data is everywhere. We are surrounded by data.

MADDIE: 02:16

Wow. Well, all right then. What are some places I see data in everyday life if it's supposedly everywhere?

SUSAN: 02:23

Well, teachers at school have to grade students' work and that data helps the teachers see how the students are doing. If they're learning or not. And when you go to the doctor's office, the medical assistant will get information about you, like your temperature. So your temperature, that data, has to be the normal number for humans, and that's how we make sure that you're healthy.

MADDIE: 02:46

Okay. Yeah. I know in sports people have to keep track of a lot of numbers, like how fast they throw a baseball or how many free throws they made. Is that data too?

SUSAN: 02:56

Yeah. Absolutely. But why do you think they want to keep track of that information?

MADDIE: 03:00

I guess they want to see if they're improving or not.

SUSAN: 03:04

Yeah. Yeah. For sure. So they're looking for patterns and trends that are important to them. Did the basketball player make more or fewer free throws? If they made more, what was different that time?

MADDIE: 03:16

So the athletes or teachers or doctors, they're all getting information and keeping track of it somehow, then looking for changes? I guess if the teacher saw the students get better grades or the basketball player made more free throws they'd want to keep doing whatever helped them get better?

SUSAN: 03:35

Yeah. Exactly. And that's what we mean when we talk about analytics, really [music]. That's just the fancy word for what you just described. We keep track of some data in whatever form it takes. We just maybe write it down in a notebook, or we can do more complicated things with computers. Then, we analyze it. So we look for a pattern or a trend. And that might be something like, are the numbers going up or down? Am I running around the track faster or slower? Is the class getting better grades or not so much? And depending on what I see there, I can decide on the next thing I should do. Maybe I need to focus on getting stronger and doing more weights so I can run faster or maybe the teacher decides the class needs to review some particular subject because they're just not quite understanding it yet.

MADDIE: 04:21

Okay. So say I want to become a faster runner. How do I know what to write down about my running? Do I just write down everything? What I ate on a certain day when I ran? What the weather was? What shoes I wore? How do I know what matters?

SUSAN: 04:36

Yeah. That's a really important question. And honestly, it can be hard to answer. So there's two main issues to think about. First, what theories or possible ideas do you have about what might help you be a faster runner [music]? Let's pick one possibility to get us started.

MADDIE: 04:53

Okay. Well, let's go with snacks because I really like snacks.

SUSAN: 04:57

Yeah [laughter]. Me too. So, okay, perfect. Maybe you think that for you, it really matters whether you eat a snack before running or you didn't eat a snack. If that's something that you think could make a big difference in your running speed, then you definitely want to keep track of it.

MADDIE: 05:13

And then I'd have data?

SUSAN: 05:15

Yeah. You would be gathering data. It's so fancy. So basically, you're collecting information on whether you ate a snack or not, and also on what your running speed was. So you could maybe do that for a couple of weeks. Then, you could divide up the runs where you did eat a snack and the runs where you didn't eat a snack, and you could see whether the snacky runs or the snackless runs were faster.

MADDIE: 05:42

So that would be like a pattern, if I'm faster with or without a snack before running?

SUSAN: 05:48

For sure. Yeah. You could maybe just see that pattern by looking at the times, or you might want to do some math, like averaging the run times for the snacky runs and the snackless runs to see which type of run was faster. What's cool is that you got some data and made a decision using it. It's analytics.

MADDIE: 06:07

That's awesome [laughter]. I'm pretty sure snacks would help me be faster. Also, that's all there is to analytics? It sounded so much more complicated.

SUSAN: 06:16

Well, this is a pretty simple example, but yeah basically the idea is to gather information in a careful way, like being sure you measure it correctly and record it every time you run, and then do some analysis of it. Think about it and see what patterns are there.

MADDIE: 06:32

Wow. So now I'm analyzing data by finding patterns too? Awesome.

SUSAN: 06:37


MADDIE: 06:38

But you said that there's two issues to think about though.

SUSAN: 06:41

Yeah. That's right. So the second issue is where things get tricky. So your theory, your main idea here, was that there was a connection between your snacking and your running speed, right? That somehow, they were related?

MADDIE: 06:56

Yeah. That's what I was guessing.

SUSAN: 06:58

Yeah. Well, but was that the right question? Maybe there's something else that explains you being faster on the days you ate a snack? Maybe on days you ate a snack you had more time, you weren't rushing from school to track practice and feeling stressed [music]? You were more relaxed and being relaxed helped you run faster?

MADDIE: 07:19

Oh. I think I see now. So maybe it was being less stressed on snack days that made me faster instead of just eating a snack?

SUSAN: 07:26

Yeah. Precisely. So we're going to talk more about this tricky kind of problem in our next episode. And spoiler alert, it has to do with what we call correlation and causation. So hang in there for that super important idea.

MADDIE: 07:41

Oh, suspense [laughter]. That sounds like a big issue. All right. So I sort of switched the thing I should have been counting. I got information, data, about my snacking and not about my amount of stress. And now I'm going to be eating a snack before every run when instead maybe I should be relaxing or taking a nap or meditating or something?

SUSAN: 08:02

Yeah. Yeah. Exactly. And asking the question about snacking seemed like a really good idea. We know we need food to fuel us for exercise and snacks are just generally awesome.

MADDIE: 08:12

That totally seems like a good thing to think about.

SUSAN: 08:15

Yeah. It made a lot of sense as a starting point. But we ended up counting snack days and missing out on something else really important about how you were feeling, stressed or relaxed. And so this is the second really important point. What's the right question to answer? How do you know what to measure to deal with the problem that you're trying to fix or the thing that you want to improve? What if it wasn't the snacking or the stress all along, but it was the weather? We didn't even keep track of the temperature or the humidity when we were writing down our running times and our snacks.

MADDIE: 08:49

So we got data on snacks but not stress or the weather or other stuff?

SUSAN: 08:55


MADDIE: 08:55

I see. There was a lot we didn't think about there.

SUSAN: 08:58

Yeah. And it's hard because there's a lot of different things that could affect your running. So ideally, we would work really hard on focusing our questions and gathering the right data or the information. To figure out the right question in this kind of situation you've got to pull together everything you know about the problem.

MADDIE: 09:17

Okay. But what if I'm not an expert on the topic? I don't know all the things about food and running and stress. How do I find out the stuff I need to know to help me come up with the right question?

SUSAN: 09:29

Yeah. It's okay. You don't have to be an expert on it. There's a few things you can try. Of course, you could try just searching the internet for information, but you might not find the best stuff without some digging.

MADDIE: 09:40

Yeah. There's a lot of crazy stuff on the internet.

SUSAN: 09:43

Yeah. No kidding [laughter]. So instead you could go look for solid books and articles from people who have read lots of stuff and who talk to experts and who basically did all the research for you. Even better, you could go talk, yourself, to someone who's an expert.

MADDIE: 10:01

Oh, I don't know if experts would want to talk to me about stuff.

SUSAN: 10:03

Oh, well, you would be surprised. You should definitely try it. People who know a lot generally like to share and to talk about things they're interested in. So don't be afraid to reach out to experts with what might feel like silly questions. Odds are, they will be excited that you're interested in the same things that they're curious about and they'll want to share what they know.

MADDIE: 10:24

Oh, okay. So once I have all that background information, I can start thinking of questions that are better or more focused? I can figure out which things are most important to count or to get the data on?

SUSAN: 10:36

Yeah. Exactly. So if you go talk to that running expert, and they say, "Well, weather, food, and stress, they're all super important in determining how fast someone can run," then, all right, I should keep track of all those things. Then, you'll have a complete set of data, and we just call that a dataset - one word - that you can look at and you can analyze all those data together.

MADDIE: 10:58

Cool. That's a lot of information. But here's a question. Can I tell how fast I will run in the next race, depending on the weather, my snack, and my stress level? Can I see the future, at least for that run?

SUSAN: 11:10

Oh. Yeah. That is a fantastic question. And the answer is maybe. So we're going to talk a lot more about this question around making predictions for the future in another episode. So hang in there.

MADDIE: 11:24

All right. I guess I can wait [laughter]. More suspense. What else are going to learn about?

SUSAN: 11:29

Well, sharks show up in our next episode, so that'll be fun.

MADDIE: 11:34

Awesome. Sharks are so cool. What else?

SUSAN: 11:38

We're going to talk about psychics in our third episode.

MADDIE: 11:41

Ooh. I knew you were going to say that. Get it?

SUSAN: 11:44

Yeah [laughter]. And then we're going to talk about treasure maps, and then how to get a job using all this cool data stuff if you like it.

MADDIE: 11:55

Fantastic. Anything else?

SUSAN: 11:57

There might be some robots. Well, artificial intelligence, at least. And we'll talk about what that actually means.

MADDIE: 12:04

Snacks, sharks, psychics, robots? This podcast series has it all.

SUSAN: 12:09

We aim to please.

MADDIE: 12:13

Thanks for listening to Data in the Sandbox. This miniseries was written by Susan Currie Sivek and our theme music is by Andy Atley. If you know a K through 12 educator or student or are one yourself, we're excited to offer a new learning and certification program designed for kids and young adults. To sign up or learn more, visit That's Catch you next time. [music]



This episode of Alter Everything was produced by Maddie Johannsen (@MaddieJ).
Special thanks to @SusanCS for writing this episode, @andyuttley for the theme music track, and @jeho for our album artwork.