Hi, I’m Craig Wiles, Senior Consultant at Public Sector Consultants in Lansing, Michigan. I provide research and evaluation services for clients in health and human services, education and the environment. I am sharing a tip on how to use Tableau as part of a data exploration process with a group of stakeholders.
To begin, I did the heavy statistical lifting outside of Tableau, so this would not lapse into a data-mining exercise. In this case, I worked with a state-level stakeholder group to identify data sources, research priorities, and statistically significant correlations in the data. Once we had our short list of correlated variables to explore in more detail, we convened a series of two hour, interactive data exploration sessions. At these sessions, we used Tableau to visually display the data (in this case, educational data), identify high and low performing school districts, and look for other obvious patterns or outliers in the data.
We tended to use stacked bar charts and scatter plots to help with this visual part of the data exploration. One tool in Tableau that was especially helpful in this context was the filter bar. Using the filter tool, we were able to adjust the range of scores we were looking for in our combination of variables according to tolerances set by the stakeholders. For example, we looked for school districts that had a high graduation rate, low dropout rate, and a higher ratio of students with disabilities in general education classrooms.
I recommend using Tableau for data exploration because it is:
- Interactive, and
- Builds capacity and ownership.
I could have presented this data in charts and graphs and led a typical ‘sit-and-get’ meeting and landed at the same place (conceptually) at the end of the day. This kind of visual and interactive process, however, really helped to engage my stakeholders, especially those that are usually averse to numbers and data. Ultimately, this was as much about the process as it was about the data.
After our interactive sessions, this group began a series of local focus group conversations with voluntary school districts to further explore the relationships we identified. This qualitative data has provided depth of detail and rich context to the quantitative relationships we explored together.
Using the filter tool:
Using a scatter plot:
Do you have questions, concerns, kudos, or content to extend this aea365 contribution? Please add them in the comments section for this post on the aea365 webpage so that we may enrich our community of practice. Would you like to submit an aea365 Tip? Please send a note of interest to email@example.com . aea365 is sponsored by the American Evaluation Association and provides a Tip-a-Day by and for evaluators.