A Student’s Introduction to Data
DecisionData.org presents information collected independently from official provider websites. We regularly update the site in an effort to keep this information up-to-date and accurate at all times. The offers that appear on this site are from companies from which DecisionData.org receives compensation.
In This Article
- Data is for everyone!
- How to start learning about data
- What can I do with data?
- Getting hands-on with data
- A future with data: career paths, school and scholarships
- Your next steps
Today’s data experts do some of the most important work in the world. They make almost all the technology we enjoy today possible, whether it’s the phone in your pocket or the plane flying across the sky. They work in the healthcare industry, the automotive industry and even in marketing and finance.
But data can be intimidating, especially when you’re dealing with large amounts of it. You’ve likely heard the term “Big Data.” This refers to data sets that are so large, they must be analyzed by computers to reveal trends.
Even if you don’t fully understand data, that’s okay! This guide will give you an introduction to data and show you just how accessible data-based careers can be for every student.
The first thing you need to understand is that data isn’t as difficult to understand as many students think. Almost anyone can learn how to use and analyze data, no matter which subjects they’re most interested in.
Data is for everyone!
Working with data is all about reading the story that exists within the figures. As long as you have an open mind and a calculator or computer, you can recognize trends and understand what they are trying to tell you.
That’s why data isn’t just for math experts or students who are great with numbers. Students learn critical thinking skills in almost every class they take, especially in classes like English and History. The key to being successful with data is applying those same skills to sets of data.
Myths vs. facts about data
Unfortunately, there is a lot of misinformation out there about what data is and who can work with it. Data might seem complicated at first. But if you dispel the myths, anyone can understand data, just as they understand other subjects.
Here are a few myths about data that we can debunk right now.
Myth: Data is only for people who get straight A’s.
Fact: Just because you aren’t getting straight A’s in math class, that doesn’t mean you can’t pursue a career in data. Even if you find math boring, you may find data very interesting.
Consider the Scottish-born inventor of the telephone, Alexander Graham Bell. Bell struggled to stay interested in math class, and his grades suffered for it. According to Bell’s biographer, Robert V. Bruce, “So far as schoolboy mathematics held any interest for [Bell], it was as a grab bag of diverting riddles. Even the rigor of following a perceived method to its precisely correct result bored him.”
Myth: Data is only for analytical people, not creative people.
Fact: Both creative and analytical people can excel with data.
Analytical people tend to be more practical and logical, whereas creative people tend to be more artistic and daring. But both types tend to be curious, intuitive and experimental. These are important qualities to have when dealing with data.
Myth: You shouldn’t concern yourself with data if math isn’t your best subject.
Fact: When dealing with data and mathematics, much of the heavy lifting will be done by computers.
Beyond understanding certain concepts, you likely won’t be doing complex math equations using pen and paper if you have a career in data. Even if math isn’t your best subject, you can still excel with data.
Liz Miller, Industry Analyst at Silicon Valley-based Constellation Research wasn’t too fond of math class, but she found a rewarding career in data regardless. “I can remember being in high school and thinking, ‘When will I ever need to know how to calculate distance or understand what a mean average is’,” says Miller. “Then, in college, when I set out for my Politics degree, I thought, ‘Why do I need math at all…and WHY am I being forced into this statistics class let alone a string of three of them?’ Thank goodness I did! I use that knowledge almost every day, from survey design, customer intelligence and understanding to raw data management and metrics calculations for marketing operations.”
Myth: You have to study computer science, engineering or math in college to start a career in data.
Fact: There are no rigid requirements for a career that involves data, and data is important to many different types of careers. Hard work and an eagerness to explore are more important than anything, and you can achieve both these qualities by studying the Humanities as well as the Sciences.
“For kids who are thinking about a career in sales, marketing or even something emerging like digital or customer experience, remember this: Data is not just a series of numbers or a compilation of 0s and 1s. It is literally the personification of your customer. All that raw material in both structured and unstructured formats is your customer. If you can’t unravel the mystery of it, extrapolate from it, understand it, learn from it, you will not understand and know your customer, and quite frankly, that is at the core of every business.”Liz Miller, Industry Analyst at Silicon Valley-based Constellation Research
Data: an overview
We tend to think of data as information stored on a computer.
For example, when you send an email, you are transmitting data over the internet. When someone opens your email, their computer is translating that data into a format they can read and understand. This is just as true for the images and files attached to emails as it is for the text within them.
Data is all around us. As Jeremy Chevallier, Marketing Director at Crash Inc. puts it: “You’re already exposed to data science every single day. When you ‘like’ stuff on social media, you’re teaching the algorithms what you want to see. You may have already noticed that your Instagram ‘browse’ section (the magnifying glass) is probably full of posts that catch your eye. Data science is why. Another great real-world example of data science is when you call an Uber or Lyft. As soon as you press that Request button, the app runs a bunch of code that determines which driver(s) get your request, and which ones don’t see it.”
Data doesn’t have to be digital, either. If you were to walk through your neighborhood and write down how many houses are painted white, you’d still be creating a data set. This is why data is relevant to every field.
In the public health sector, researchers may use data to measure the effectiveness of a new health program or to gather information about the health status of a specific group of people. As an example, John Kollman, MS and Holly L. Sobotka, MS — researchers at the Center for Disease Control and Prevention (CDC) — found that people in low-income communities in Ohio are at a higher risk of cancer than those in wealthier communities. Officials can use this information to direct health services and public resources where they’re needed most.
Data is also essential for businesses. Some businesses hire writers and analysts to produce written reports that outline what data is saying about specific industries. They then market those reports to potential customers or use them to inform their business strategies.
Businesses also collect data about their customers so they can serve them better. For example, if data collected from visitors to a business website suggests most of them access the website on a mobile device, the business will know that it needs to make the website mobile-friendly.
Data is the future
The reality is that the future depends upon data. The organizations of tomorrow will need people skilled in data analysis to complete their missions. Most of the innovations we now accept as commonplace wouldn’t be here if it weren’t for data, either.
Autonomous vehicles would not be able to navigate on their own if the computers inside them couldn’t collect and analyze large quantities of sensor data. You wouldn’t be able to call someone on the other side of the world if cell phone carriers and internet providers couldn’t transmit and process data in real time.
We can use data to create smart farms that plant, water and harvest themselves. We’ll be able to predict when machines will break down so we can repair them and keep them running. We’ll even be able to use data to solve social problems and predict societal trends around the world. In the future, data will be used in almost every discipline, from technology and transportation to business and agriculture.
Whether you’re a writer, an artist, a scientist or an astronaut, your job will require some degree of data literacy.
How to start learning about data
But what exactly is data? It’s not as complicated as it may seem.
Data is simply information that is collected through observation. Data tends to be numerical, but it can come in a variety of forms. In the simplest terms, data is a collection of facts.
Learn the basics: What is data?
There are two types of data: qualitative and quantitative.
Qualitative data is information that describes something. If you’ve ever taken a survey and were asked to write about an experience you had, your response would have been an example of qualitative data. Surveyors can use these descriptions to add context to their research.
For example, a question might ask you how you felt about your recent visit to a restaurant. A qualitative response to this question might be something like, “I enjoyed the fast service, the tasty food and the low prices.”
You can represent this type of data on a chart. However, qualitative data can help you find new meaning when you compare it to your numerical, quantitative data.
Quantitative data is numerical information, such as a person’s height or the number of jellybeans in a jar. There are two types of quantitative data: discrete and continuous.
Discrete data only takes the value of whole numbers. If you were to say that there are 100 jellybeans in a jar, this would be an example of discrete data.
Continuous data can take any value that falls within a range. If you were to say that Jim is five feet and nine inches tall or that the distance between two cities is 15.7 miles, these would be examples of continuous data.
There’s an easy way to understand the difference between the two: Discrete data is counted, whereas continuous data is measured.
Types of data you can collect yourself
Data is all around you, and you don’t need special equipment to collect and understand it. The easiest way to collect data is to observe your surroundings and record what you see.
Imagine there’s a flowering meadow in your neighborhood where butterflies like to drink nectar. If you count the number of butterflies in the meadow every day for a month, you’ll have a data set. If you do this month after month, year after year, you could tell whether the population of butterflies in the meadow is going up or down.
This is an example of quantitative data.
Now, imagine your local school is hosting a play. If you want to find out how much the audience enjoyed the play, you could ask every attendee to describe their experience. You could either have them write this information down or record it in an interview.
This is an example of qualitative information.
What can I do with data?
Now that you know the basics, you can start to make your own data sets. When collecting data, try to do so to answer a specific question or a set of questions. For example, you could be trying to answer the question, “Is the local butterfly population rising or declining over time?”
If you have bigger questions to answer, you can combine your data with publicly available data sources. You can typically find publicly available data on government websites (.gov), university websites (.edu), nonprofit websites (.org) and in online scientific journals.
For example, one group of researchers did a study on the butterfly population in Ohio and published their results in July of 2019. They found that the butterfly population in the state has been in decline for over 20 years.
If you were to learn that your local butterfly population is increasing, you could then work to understand why. Once you know why, you might be able to help butterfly populations recover elsewhere!
How can I visualize data?
When gathering data, you’ll likely end up with a sequence of numbers or a list of qualitative responses. Even if you know what the data says, other people may not just by looking at it.
To present data, you need to make it easy to understand. The easiest way to do this is through visualization. If you’ve ever looked at a graph or chart, you’ve seen an example of “data visualization.”
The first step is to ask yourself, “How can I illustrate this data to describe it to a friend or family member?”
Different types of charts are effective for different types of data. Bar charts are good for showing how the sizes of different data points compare to each other. Line graphs are great for showing how information changes over time.
Check out the table below to learn about different types of data visualizations.
Common Types of Data Visualizations
|Type of Visualization||What Types of Data it’s Best for||How You Can Make It|
|Bar Graph||Comparing sizes of things.||Place data about what is being measured on the horizontal axis. Place data about the size of measurements on the vertical axis. Use bars to represent the size of each data point.|
|Scatter Plots||Showing how one variable is affected by another.||Collect pairs of data. Draw a graph with an independent variable on the horizontal axis and a dependent variable on the vertical axis. Plot each data point with a dot.|
|Line Graphs||Showing how data is connected or how it changes over time.||Place increments of time on the horizontal axis. Place measurements of data on the vertical axis. Plot the data points on the graph with dots, then draw straight lines connecting the dots in order.|
|Histograms||Grouping numbers of things into ranges.||Place data about how many things were measured on the horizontal axis. Place the size of the measurements on the vertical axis. Represent how many things fall into each range of measurement using bars.|
|Stem and Leaf Plots||Showing the frequency of certain values.||On the vertical axis, place “stem” values (the first digit) in ascending order, top to bottom. Then, place “leaf” values (the last digit) in ascending order, left to right, on the horizontal axis next to the stem values they correspond with.|
|Frequency Distribution||Showing the frequency of various outcomes.||Place measurements for how often something occurs on a vertical axis, in ascending order, top to bottom. Then record the frequency with which those things occurred next to each corresponding measurement.|
How can I measure data?
You’ll need to measure your data to draw any meaning from it. To measure the data you collect, you should first ask yourself, “What do I want to know about this data set?”
Are the values from one group different from the values of another group? If so, how much do the data points differ from each other? Changes in your data could indicate a change in circumstance or even a trend.
By measuring your data, you’ll be able to identify insights that aren’t easy to see at first.
Use the table below to learn different ways of measuring data.
Ways to Measure Data
|Level||Measurement||What’s being measured?||What does it tell me?|
|Beginner||Mean||Central Value||The average of a set of numbers.|
|Beginner||Median||Central Value||The middle number in a set of numbers.|
|Beginner||Mode||Central Value||The number which appears most often in a set of numbers.|
|Beginner||Range||Spread||The difference between the lowest and highest numbers in a set.|
|Advanced||Interquartile Range||Spread||The dispersion of numbers within the middle 50%, or 2nd and 3rd quarter, of the data set, when a data set is broken into equal quarters.|
|Advanced||Standard Deviation||Spread||How spread out the numbers in a set are compared to the set’s average (mean).|
|Advanced||t-test||Difference between data sets||How significant the differences between groups of data are, and if those differences may have occurred by chance.|
|Advanced||Chi-square||Difference between data sets||How likely a distribution of data is due to chance.|
|Advanced||ANOVA||Difference between data sets||Whether there are statistically significant differences between the means of two or more unrelated groups of data.|
When determining how you should measure your data, start with what questions you need to answer. What questions arise when you look at the numbers? What questions did you start with, and do they change now that you see the data?
One simple way to measure data is to use what’s called a “linear regression model,” which is usually represented as a line graph. In this model, you plot data points on a graph, usually with a measurable value on the vertical axis and measurements of time on the horizontal axis. You then draw a line that best fits the data. You can then use this line to predict when a value will reach a specific point.
Getting hands-on with data
If you’re already a data pro, you don’t have to take time to collect data on your own to get started. You can use publicly available data sets to start learning just how powerful data is for understanding the world around us.
Here are some public data sets you can use to start analyzing.
Publicly Available Datasets
|General||The World Bank: Health, Education, Climate Change, Education||https://data.worldbank.org/indicator?tab=all|
|Healthcare||U.S. National Library of Medicine||https://www.nlm.nih.gov/hsrinfo/datasites.html|
|Healthcare||Centers for Disease Control & Prevention||https://wonder.cdc.gov/|
|Healthcare||Substance Abuse and Mental Health Services Administration||https://www.samhsa.gov/data/|
|Education||Higher Education Datasets||https://www.data.gov/education/|
|Education||National Center for Education Statistics||https://nces.ed.gov/programs/coe/indicator_cfa.asp|
|Education||U.S. Department of Education||http://www2.ed.gov/rschstat/landing.jhtml?src=ft|
|Information Technology||Data.gov IT||https://catalog.data.gov/dataset?tags=information-technology|
|Jobs||U.S. Bureau of Labor Statistics||https://www.bls.gov/data/|
|Jobs||The International Labour Organization (worldwide labor statistics)||https://ilostat.ilo.org/|
|Consumer||The U.S. Economic Research Service||https://www.ers.usda.gov/|
A future with data: career paths, school and scholarships
There are many different types of careers you can build with a foundation in data, and you don’t necessarily need to focus on math or science for a background in data to add to your career prospects. According to research conducted by IBM, the number of jobs for all U.S. data professionals will increase to 2.72 million in 2020.
Here are just a few of the careers you can get with a background in data, and what degrees students should consider to pursue them. Most professions require a Bachelor’s degree or higher.
Formal data careers
|Career||Degree Required||Annual Salary Range*|
|Data Scientist||IT, Computer Science, Mathematics, Physics||$83,000 – $154,000|
|Researcher||Physics, Biology, Chemistry, Economics, Sociology or Other Specific Fields||$35,000 – $89,000|
|Data Engineer||Software Engineering, Computer Science||$72,000 – $158,000|
|Statistician||Statistics, Mathematics, Survey Methodology||$57,000 – $102,000|
|Actuary||Mathematics, Statistics, Finance, Economics, Business||$76,000 – $126,000|
|Healthcare Data Analyst||Health Information Management and Technology, Mathematics, Biostatistics||$43,000 – $95,000|
*Salary ranges based on information from Glassdoor.com.
Informal data careers
Of course, you can use data in many other types of careers. Any career path that works less formally with data will allow you to use numbers in conjunction with all sorts of real-world applications. Many employers are eager to hire people who are data literate, even if the job in question isn’t centered around data.
|Career||Degree Required||Annual Salary Range*|
|Market Researcher||Marketing, Business Administration, Psychology, Social Science, Mathematics, Statistics||$37,000 – $78,000|
|Economist||Economics, Ph.D. in Philosophy||$64,000 – $144,000|
|Sociologist||Psychology, Sociology||$56,000 – $81,000|
|IT Systems Analyst||Computer Science, Computer Systems Analysis, Computer Information Systems (CIS), Business Intelligence||$43,000 – $83,000|
Business Administration, Business Management, Marketing, Accounting, Statistics, Economics, Computer Science
$35,000 – $89,000
|Digital Marketer||Market Research, Computer Science, Business Administration||$37,000 – $89,000|
Economics, Finance, Business Management, Statistics, Demography, Criminal Justice, Sociology
$50,000 – $117,000
*Salary ranges based on information from Glassdoor.com.
You can get a degree that’s relevant to a career in data at almost any college, but some colleges are better known for their data programs than others. Here are some colleges students should consider if they’re pursuing a career in data.
There are also scholarships available for students pursuing degrees in analytics, data science and related fields. These scholarships can provide financial assistance to students while they are in school. Here are a few of the scholarships students should consider.
|Scholarship||Amount||Eligibility||How to Apply|
|AACE International Scholarship (Undergraduate)|
Up to $2,500
|Full-time sophomores, juniors, and seniors in college. Must be enrolled in select programs and have a 3.0/4.0 GPA.||Apply on the AACE website starting in January 2022.|
|UPE/ACM Scholarship Award (Graduate and Undergraduate)||$1,000||Graduate and undergraduate students who are members of the Association for Computing Machinery (ACM).||Download the application form from the scholarship website and email it to email@example.com.|
|The National Science Foundation Graduate Research Fellowship Program||Three-year annual stipend of $34,000 and $12,000 for tuition and fees.||Students in STEM fields pursuing research-based graduate and doctoral programs.||Apply online at the Graduate Research Fellowship Program website.|
|The ACM SIGHPC/Intel Computational & Data Science Scholarship||$15,000 annually for up to two years.||Students pursuing graduate degrees or higher. Must be a woman or a member of an underrepresented racial/ethnic group.||Must be nominated by an advisor. Must submit a CV and a candidate statement alongside an endorsement from an instructor or supervisor.|
|The Department of Energy Computational Science Graduate Fellowship||Annual stipend of $36,000 for up to four years.||Students beginning graduate or doctoral research in STEM fields.||Apply online at the start of fall. Must provide transcripts, references and a program of study (POS)|
Your next steps
As you can see, data is an inclusive field that encompasses many different career types and courses of study. Maybe math and science aren’t your favorite subjects right now, but that doesn’t mean you can’t have a lucrative and fulfilling career in data.
Your first step should be to familiarize yourself with the data concepts presented here. Once you have a full understanding of them, you can start to experiment with ways to apply data in the real world.
If you want to pursue a career in data, choose a college that has a strong data, science or business program. You may not know what you want to major in during your first year of college, but you should be considering your options as you complete any general education requirements.
You may decide to major in a subject that isn’t related to science, engineering, technology or mathematics (STEM). That doesn’t mean you have to give up on data. Many Humanities majors choose to pursue a minor in data, mathematics or another scientific field.
Remember, data literacy will be essential for almost every future career. According to Justin Butlion, Founder of ProjectBI, “The demand for analysts and data specialists continues to rise as more and more companies understand that data is the new gold. The tools and technologies in this space have become incredibly powerful and significantly cheaper to integrate. Analytics has become commoditized so the demand for data specialists is higher than ever before.”
Butlion goes on to say that “a good data scientist is technically sound and good with numbers. A great data scientist understands how to use his [or her] skills to provide massive value to his [or her] company, the market or a combination of both.”
By learning the right data skills, you won’t just be setting yourself up for a brighter future, you’ll be contributing to a brighter future for everyone.
About the Author
Michael Rand is a freelance content writer who covers topics like marketing, personal finance and technology. He lives in Beverly, Massachusetts.