Skip to Main Content
JMU Libraries logo .jmulib-logo-purple{fill:#450084;}
Loading

Data Literacy: Getting Started with Data

This guide introduces data literacy

Critical Thinking

Critical Thinking: Engage with data through a lens of skepticism and curiosity. Ask questions about what the data is showing, evaluate its sources, and make informed decisions based on evidence. Don’t take data at face value—always check its quality, relevance, and potential biases.

Data Evaluation: Assess the quality and reliability of data sources and collection methods. Look at how data was collected, its accuracy, and if it's representative of the issue at hand. This helps you distinguish between trustworthy data and potentially misleading information.

Hypothesis Testing: Start with a question, not just a trend you see. Formulate hypotheses based on specific questions and then seek data to support or refute these hypotheses. This method ensures your conclusions are driven by genuine inquiry rather than data patterns you might find appealing.

Bias Awareness: While it’s impossible to completely eliminate bias, acknowledging and accounting for it is crucial. Ask is the data is too biased to be reliable. Recognize your own biases and consider how they might affect your interpretation of data. This self-awareness helps you approach data more objectively.

Data Ownership: Minimizing Bias

Understanding Bias in Data: Bias in data can happen in two ways: it can be hidden (implicit) or obvious (explicit). Bias is something that can affect every step of research, from the data you collect to the way you analyze it. Being aware of bias is important to ensure that your research is fair and accurate.

Evaluating Data for Bias: When you're using data that someone else collected, it's important to ask some key questions:

Fair Collection: Was the data gathered in a way that includes everyone? For example, during the COVID-19 pandemic, some communities were left out of data collection, leading to an incomplete picture of how the virus affected different groups. Missing this info can have serious consequences for public health.

Ethical Use: Were the people who shared their data treated fairly? Did they know how their data would be used? Remember the Facebook-Cambridge Analytica scandal? People’s data was used in ways they didn’t expect, influencing elections without their consent.

Transparency: Is it clear how the data was collected? Are any biases openly acknowledged? Think about AI facial recognition technology. A lack of transparency in how data was gathered has led to some serious issues, like wrongful arrests, especially among people of color. These hidden biases can cause real harm.

Reducing Bias in Your Work: It's almost impossible to collect data without any bias, but you can work to reduce it. Always check for documentation that explains how the data was collected and whether any biases are acknowledged.

Confronting Bias in Everyday Tools: We use tools like Google every day, but do we really understand why we get certain results? Check out our interactive tutorial, “Uncovering Hidden Bias in Your Online Searches,” to learn about algorithms—how they work, and how they might be biased.

This tutorial was peer-reviewed and accepted into an online resource for use by librarians and instructors around the world!

Real World Example: Ever wonder why your social media feed seems to know you so well? That’s because of algorithms, which are sets of rules computers follow to make decisions. But if these rules are biased, they might not show you the whole picture. For example, if an algorithm was trained on data that wasn’t adequately representative, it might favor certain posts or ads over others, leading to a skewed experience.

Why It Matters: Bias in data can lead to unfair outcomes, like certain groups being left out of important research or receiving different treatment. By understanding and reducing bias, you can help create more fair and accurate research.