What do numbers and words have in common?

Well, they are both data! Data, when processed, creates information that can be useful in our everyday lives and shape our experience and decisions. We are bombarded with data every day, whether it be from the news, newspaper, or social media feeds. It can feel a little overwhelming, but understanding it and knowing why you should care about data can help you develop a better understanding of those around you and the world we live in.

This sounds great, but what kind of data exists?

There are two main types of data: quantitative and qualitative.

	Quantitative data is all about the numbers, things that are measurable by counts, scales, or given a numerical value.  You can use this data to identify trends, support hypotheses, and make comparisons. This type of data is gathered using questionnaires, surveys, forms, analytics tools, and statistical analysis. One of the biggest benefits that this data provides is its ease of collection and scalability. To generate meaning, this data type uses descriptive statistics, regression analysis, factor analysis, and other methods of statistical analysis.
	Qualitative data is all about the “why” and “how”. It uses words to describe characteristics that can’t easily be measured with numbers, such as feelings and attitudes. This type of data is collected interviews, focus groups, customer testimonials, and observations and have small sample sizes. Qualitative data uses thematic analysis to find meaningful themes or sentiment analysis to interpret emotions.

Take a closer look at these data types: 

Want to see these data types in action?

Now that you understand the two types of data, let’s explore how they work in action by examining two research articles: one that uses qualitative data and another that uses quantitative data.

Quantitative Data Example

The first research article, The Democratic Value of Strategic Game Reporting and Uncivil Talk, uses quantitative data to examine how news coverage of political debates posted on Facebook by news agencies relates to the quality and characteristics of posts by users. This study had a large sample size with over 42,000 comments across 11 political debates. The researchers employed machine learning techniques to analyze the comments and regression modeling to analyze relationships between data (see a sample table in Figure 1).  The research found that strategic game framing and negative news were not linked to uncivil comments and news posts focusing on personalities and attacks were associated with less relevant comments.

Qualitative Data Example

The second research article, News Consumption and Trust in Online and Social Media, uses qualitative data to examine news consumption and trust of 35 young adults in Austria (see Figure 2 which shows the participant demographic data). The researchers used semi-structured interviews to gather insights of how the youth consume news and their trust level with various media channels, sources, and content. Qualitative data was used to explore the ‘how and why’ of young adult behavior and trust. This allowed for the discovery of unexpected themes/patterns, provided deep, detailed data on media consumption, and allowed researchers to explore participant’s reasoning. The results showed that young adults trusted traditional media the most, social media was a main news source, and peers were more important as influencers than the ‘irrelevant’ journalists.

Numbers Speak Louder (to Me Anyway)

While both types of data offer valuable information, I find myself drawn toward research that employs quantitative data. I like that quantitative data allows you to identify trends and relationships within large datasets. This makes it possible to make generalizations about populations, test hypotheses, replicate findings, and validate theories with confidence.

What’s Your Favorite Data Type? I’d love to hear your opinion, please comment below.