Qualitative and quantitative data are both critically important to crafting a data strategy. For a person to fully understand data that is gathered, one must have data from both data types to best comprehend the data that is analyzed and used for a data strategy. In research, data needs to be collected to paint a clearer and more informed picture. It is easier and quicker to gather large swaths of data from a quantitative process as that data is very structured and controlled. Multiple choice questions, yes/no, true/false, age, gender, ethnicity and so on – these are all examples of quantitative data. One can quickly and easily put together massive amounts of information with little effort from this type of data.
Qualitative data – this is data that essentially looks to dig deep and gather specifics. I always like to think that quantitative data focuses on quantity, whereas qualitative data focuses on quality -- the names are the definition. These are data-sets that are not easily structured as they could be images, feelings or perceptions, videos, preferences, etc., and are often subjective with no clean way to organize. They are often open-ended when verbal and therefore cannot be selected from a simple list of options. You can easily put quantitative data in an Excel spreadsheet and organize by data-sets, whereas with qualitative data, you cannot organize by personal opinion.
A great example of both data-sets being utilized simultaneously are the end-of-semester instructor surveys my school sends out at the end of each semester. The surveys ask us a blend of quantitative data and qualitative data questions. Multiple choice, or index rating scales on a scale of 1-5 are quantitative, but questions that ask the students for direct feedback about an instructor are qualitative as they are based on the feelings and perceptions of each individual student. There is no drop-down, multiple choice, select the best answer for this type of question – it requires each student to write something and that data will therefore always be unique, but high in quality as the open-ended question digs deep to uncover information that statistical data alone cannot account for.
While it is extremely important to use both data-sets in research, an argument can be made that business decisions don’t require qualitative data as business decisions would appear at first glance, to be more statistical and numerical playing to a quantitative data-set process. However, humans are emotional, quantitative data is not. Humans make decisions not based solely on logic, but also emotion. As no two people are the same, each person is going to have a differing viewpoint which could alter a person’s behavior. Understanding that behavior is important.
One example of this process in action would be what I like to call the curious case of Wal-Mart, Pop-Tarts, beer and hurricanes. In 2004, Wal-Mart learned through big data analysis that Pop-Tarts and beer are the most popular commodities to sell when a hurricane makes landfall (Engard, 2017). Therefore, Wal-Mart heavily stocks these supplies when a hurricane comes barreling through. It goes against all rational thought that beer and Pop-tarts would outsell items like bread, flashlights or batteries, but they do. Qualitative data is needed to understand why. By utilizing qualitative data, we could possibly uncover more truths leading to even better forecasting capabilities for Wal-Mart.
Qualitative data would ask “why are these products so popular during a hurricane?” Asking many individual people that question would never yield the exact same answer. But once enough qualitative data is gathered and analyzed, patterns and information could be uncovered answering the question of “why”. This data is highly valuable and could possibly be utilized to answer many other questions regarding human emotion and disaster-planning allowing for Wal-Mart to continue to properly stock its shelves based on demand – otherwise known as prescriptive analytics. Prescriptive analytics allows for a forecaster to ask the question “what will happen” and react accordingly based on all data available (Schmartzo, 2015).
References
Engard, B. (2017). Discoveries from Big Data Insights. Retrieved from https://online.jefferson.edu/information-technology/discoveries-big-data-insights/
Schmartzo, B. (2015). Big Data MBA: Driving Business Strategies with Data Science. Hoboken, NJ: John Wiley & Sons, Incorporated.