Knowing how they can work in harmony is key to making the best, data-driven decisions. Quantitative data is critical for measuring impact and ROI. Use quantitative data to answer questions like: “how many people are using this feature?” or “how common is this pattern?” It can tell you the magnitude of a specific problem or behavior, reveal how many people are affected, and help you to determine financial impact. This data, however, needs to be balanced with a deeper understanding. It tries to answer: “why are we seeing this behavior from our users?” That’s where qualitative data truly shines. What does combining both look like? A mixed methods approach combines quantitative and qualitative techniques to gain a broader perspective on a problem. The most effective mixed methods approaches take advantage of each method’s strengths-and work to mitigate their respective weaknesses. So where do we start? Types of mixed-methods researchĭesigning a mixed methods research approach can be difficult. Always look at your objectives, and make sure you keep them top of mind when choosing methods.These are the steps I take myself through when trying to choose the best approaches for a project: To have the best impact, we should be working back from our research goals-and picking qual and quant methods that are most appropriate. Acknowledge the timeline of the project.If quantitative data reveals something that is disruptive to the study, are the methods flexible enough to be changed? Consider how the data will be collected, and how data will impact other parts of the study.Choose methods that have complementary strengths and don’t have any overlapping weaknesses.If you know what you want your results to look like, it’ll give you some direction on what you should be viewing from a qualitative versus quantitative lens.
Understand your own comfort level with qualitative and quantitative approaches, and be okay with asking for help if you feel unfamiliar with a certain situation.Īt this point, there are three main ways you can combine qualitative and quantitative data.This can impact whether certain methods are realistic. An explanatory sequential design that emphasizes quantitative analysis and data collection first-followed by qualitative data collection. We use the qualitative data to further explain and interpret results from the quantitative data. For example, a survey may be used to collect quantitative data from a larger group. A convergent parallel design that occurs when you collect qualitative data and quantitative data simultaneously and independently-and qualitative and quantitative data carry the same weight.An exploratory sequential design that starts with the qualitative research and then uses insights gained to frame the design and analysis of the subsequent quantitative component.Thereafter, those participants would be selected for interviews where they can explain and offer insights into their survey answers. They are analyzed separately, and then compared and/or combined to confirm or cross-validate findings. Imagine you are a user researcher at TeamTicket, a (fictional) ticket comparison app.
Research goal example: How are users currently using our ticketing app, and where are they running into problems? You and your team want to better understand how your customers currently are using the ticketing services, in order to make improvements. These aren’t necessarily the only methods to be used-they’re a few different ways to approach these goals.
Certain elements of each design can be combined or omitted from projects.Įxplanatory sequential design: quantitative-first approachġ. Quantitative: The first thing to do on this team is to understand and determine which metrics are most relevant to observe, and what will determine our success criteria.
0 kommentar(er)
