It’s the understatement of the year to say that data is everywhere. It’s perhaps the second largest understatement of the year to say that data powers the lives we’ve grown accustomed to living.
Data informs decisions made by governments, conglomerates, advertisers, tech companies, and even everyday consumers.
In short, that means data influences most everyone’s life.
The different brands of data and sheer volume of information they yield does, of course, raise an ethical question of how all this information is leveraged. Let’s take a look at a brief outline of the different types of data, and how that information shapes the world as we know it today.
Perhaps one of the more common or easily understood types of data is qualitative data. Qualitative data is extremely varied in nature and includes any information that can be observed and captured, but that does not include anything numeral in nature. Three primary examples of qualitative data include:
- Interviews: Either individual or in group settings, interviews can be recorded via audio, video, and transcription with the goal of exploring certain topics or discussions with the interviewees via a designated interviewer.
- Direct observation: While similar to interviews, direct observation differs in that there is not a designated interviewer, nor is there necessarily a tract of topics of discussions that are explored. Direct observation includes everything from field research to photographs of a given phenomenon or subject matter.
- Written documents: Most commonly referring to documents that already exist, written documents can include everything from newspapers, books, magazines, websites, reports, and studies.
Also known as numerical data, quantitative data is measured in the form of numbers or counts, with a unique numerical value associated with each data set. Quantitative data can also be defined as groupings of quantifiable information that can be used in mathematical formulas and statistical analysis to inform real-life decision-making and predict real-world outcomes. Quantifiable data can be divided into two main categories:
- Discrete data, which consists of counting numbers only, and as such, cannot be measured. Examples would include the number of days in a year, or the number of people attending a concert.
- Continuous data, which takes on numeric values and can be broken down into smaller units to extract deeper meaning or insight. An example of continuous data would be a student’s grade point average on a 4.0 scale. Varying GPAs tell a different story relative to the academic success of said student.
Attribute is a bit trickier in terms of understanding and application, as this form of data possesses a subscribed attribute or characteristic to the collection information. Attribute data is data that has traits that do or do not meet a certain specific standard or benchmark. These characteristics can be sorted and counted to gain greater insight into the story the data tells.
Examples of attribute data would be combing through certain products in search of imperfections (such as blemishes) or non-conforming pieces (defective).
To better understand attribute data, let’s look at quality assurance in food production plants. Frozen pizza companies must inspect every frozen pizza that comes off the line to ensure the pizza is uniform and consistent and the packaging is safe for deployment in grocery stores. Variances in either of these areas would be classified as attribute data that informed whether the product was of high enough quality to sell.
Yes, we did briefly touch on discrete data as a subset of quantitative data, but let’s examine this type of data collection in just a bit more detail. As we discussed earlier, discrete data consists of counting numbers only and as such cannot be measured. This means that discrete data is comprised of:
- Variables that can only possess specific values.
- Countable values in a discrete data series.
- Whole numbers to write discrete data values.
Examples of discrete data would include the number of students in a classroom, the number of cereal boxes in the cupboard, or the number of basketball teams in a league. Discrete data is most often and most effectively represented visually through bar graphs, frequency tables, and line plots.
Perhaps you’re seeing a data pattern forming here as well, but another important offshoot of quantitative data worth exploring in greater detail is continuous data. We defined continuous data a few moments ago as numeric values and can be broken down into smaller units to extract deeper meaning or insight. Essentially, continuous data allows for range and nuance within the data set to tell a deeper and more precise story.
The core characteristics of continuous data include:
- Variables can take any value within a certain range.
- Values within this range cannot simply be counted but instead measured.
- Real number values to describe continuous data sets.
Real-world examples of continuous data include height or weight of each basketball player in the league, or the number of cereal pieces inside the boxes in the cupboard.
How is this data used?
While this discussion has to this point felt fairly basic and innocuous, it does lead to a bigger and more ethically murky conversation about how these kinds of data are used by companies every day to influence our buying decisions and consumer habits. As we said at the outset, data is everywhere, from the phone in your pocket to the Google Home or Alexa in your kitchen. These connected devices are gathering unfathomable numbers of data sets every day, and companies leverage it to better understand who their customers are, how they think and feel, where they live, how they move, and more.
Let’s imagine a fairly common scenario: you download a new app. When the download is complete, you are asked to agree to terms of service, and you of course click yes because who can squint and read such a lengthy document? However, in doing so, you likely just agreed to have data collected about your behaviors, geographic location, browsing history, and more sold to third-party consumer insight groups who work with companies to position products of most interest to you at a moment when you’re most likely to make a purchase.
Or, imagine you’re using a navigation app to find your way to the nearest coffeeshop. Because your geographic location, consumer interests, and buying patterns are being documented, this data can then be leveraged by other coffee companies to show you ads or offers for like-minded products.
As you can see, this is simply an extrapolation of the various kinds of data we outlined above for real-world application. And as with any real-world application, there are ethical questions about how this data is being gathered and used. Is this data being leveraged to provide a more tailored, customized consumer experience and thus a way of life where only that of the greatest interest is served to you? Or, is this simply an invasion of privacy or a malicious use and sharing of data that results in unfair business practices?
It’s a complicated question and one that certainly has a variety of answers and potential outcomes going forward as data collection becomes more powerful and precise. It’s also a question tomorrow’s best and brightest tech professionals will reckon with as societies come to grips with how data drives their livelihoods.
Are you ready?
Start Your New Tech Career Today
With our digital badge program, your path toward a software development career is more accessible than ever before. Designed for those who want to advance but can’t commit to a three-month, nonstop bootcamp, the digital badge program offers the same quality content and rigorous training in a flexible schedule designed to fit your life.View Details