Skip to Main Content
It looks like you're using Internet Explorer 11 or older. This website works best with modern browsers such as the latest versions of Chrome, Firefox, Safari, and Edge. If you continue with this browser, you may see unexpected results.

Data Reference Toolkit: 1. Research Question

Defining your Research Question

A research question is a statement of what you want to study. The research question has to be doable. To see whether your research question is feasible try the following “suggested feasibility test”:

1. Can you answer the question with a simple descriptive statistic (like an average, median, count, percentage, etc)? If so, then it may be too narrow and not require a lot of research. 

2. Does the answer to your question have too many angles.

For example: What best practices solve poverty? Here you need to be more specific: what do you mean by ‘best practices’? Where? The US, the world? The question assumes that poverty has been solved somehow somewhere and trying to find an answer here may take you everywhere. The question is not focused enough and is too broad.

3. A feasible research question is answerable on time. You need to consider deadlines, whether the data is available immediately or not (and in the format you need). Do you have enough time and the necessary resources to answer the question?

4. There is no magic procedure to craft a research question. It is a back-and-forth process and you may need to repeat certain steps several times.

For example, after searching for data you may find that you need to adjust your research question to align with available data. 

Source: Oscar Torres-Reyna, "Finding Data," Princeton University,

What are the characteristics of data needed?

Think about your research question. The data that you will look for will have certain types of attributes and information. Use the google doc and address these areas as best as you can:


  • Unit of Analysis (e.g. individuals, households, companies, players, teams, counties, states, nations)

  • Geography (e.g. parcels in a city, counties in a region, democratized countries)

  • Time Period (e.g. 1980-2006)

  • Frequency (e.g. annual, quarterly)

Remember not all characteristics may be captured by a dataset. For example, the availability of geography may be limited to data at a county, state, or zip code level. Try to account for data limitations and see how you might be able to address them.


Developing your Research Question

This guide is by Dr. Robert Labaree and will help you develop and adjust your research question.