In a few recent conversations with some of my peer groups and customers the discussion on the importance of “quality data” and how to identify or manage “quality data” came about. There was concern that in some instances decision makers at the C-Suite didn’t understand some of the key skills and attributes in having good “data people” in their organisation. So, I decided to write a small frequently asked questions on the topic of data literacy. I am hoping that this will help a broad audience to understand the topic of data and data literacy a bit better.

Defining Data

Let’s start at the beginning: What is Data? Webster’s defines data as “factual information (such as measurements or statistics) used as a basis for reasoning, discussion, or calculation”. Essentially, data is one or more facts.
So, Facts make Data, data makes Information, recalling that information makes Knowledge, and correctly applied knowledge makes Wisdom – and the whole point of Data Literacy is helping you making wise decisions.

This skill set is akin to traditional literacy, where we learn the building blocks of language, grammar, and interpretation to derive meaning from text. Similarly, data literacy empowers us to navigate the vast sea of information, identify reliable sources, and extract meaningful insights to solve problems and make sound judgments.

1. What is Data Literacy?

Data literacy is the ability to find, understand, evaluate, and use data effectively to make informed decisions. It’s like learning a new language – you need to understand the basic building blocks (data), the grammar (relationships and context), and how to interpret complex works (analysis) to gain meaning and wisdom.

2. What are the key skills involved in Data Literacy?

Data literacy involves four key skills:

1. Finding authoritative data: Identifying reliable data sources, distinguishing between primary and secondary sources, and understanding research methodologies.
2. Working with data using various tools: This includes using spreadsheets, understanding basic statistics, and potentially learning languages like SQL, R, or Python for data manipulation and analysis.
3. Analysing data in context: Critically examining data from multiple perspectives, understanding the limitations of statistical measures, and considering the context surrounding the data.
4. Using data for intelligent decisions: Defining problems clearly, applying appropriate data and analysis, considering alternative solutions, and communicating findings effectively.

3. What is the importance of identifying authoritative data?

Not all data is created equal. It’s crucial to identify authoritative data sources to ensure accuracy and reliability. This involves:

• Differentiating between primary sources (original data collected firsthand) and secondary sources (interpretations or analyses of existing data).
• Evaluating the credibility of the source by considering their expertise, potential biases, and motivations.
• Cross-referencing information from multiple sources to verify accuracy and identify potential discrepancies.

4. What are the different types of data?

There are two primary data types:

• Quantitative data: Numerical information that can be measured and analysed statistically, such as age, height, or income.
• Qualitative data: Descriptive information that cannot be measured numerically, such as opinions, colours, or experiences.

Understanding these types is crucial for selecting appropriate analysis methods.

5. What is meant by “analysing data in context”?

Analysing data in context means going beyond simply looking at numbers. It involves:

• Understanding the background, environment, and potential biases surrounding the data.
• Considering external factors that may have influenced the data.
• Relating the data to the specific problem or question being addressed.

This approach helps derive more meaningful insights from the data.

6. How can I avoid bias in data analysis?

Cognitive biases are systematic errors in thinking that can unconsciously skew data interpretation. To minimise bias:

• Be aware of common biases like confirmation bias (favouring information confirming existing beliefs) and availability bias (overemphasizing easily recalled information).
• Actively seek out diverse perspectives and challenge your own assumptions.
• Use structured analytical techniques and frameworks to minimize subjective interpretation.

7. How can I use data to make better decisions?

Data-driven decision making involves a systematic approach:

• Define the problem clearly: Ask the right questions to ensure the data analysis aligns with the desired outcome.
• Select relevant data and appropriate analysis methods: Ensure the chosen data and analytical techniques are suitable for addressing the problem.
• Consider alternatives: Explore different perspectives and potential solutions before reaching a conclusion.
• Communicate findings effectively: Clearly articulate the insights derived from the data analysis to stakeholders.

8. What is the importance of documenting data analysis?

Documenting the data analysis process is crucial for:

• Transparency and reproducibility: Allows others to understand the steps taken and verify the findings.
• Learning from mistakes: Provides a record to identify errors and improve future analyses.
• Knowledge sharing: Enables others to benefit from the insights and methodologies used.

Resources

After you know where to find data, you need to ensure that it is valid – accurate, representative, and sufficient.

How to do Research (If you haven’t done this at School / University)

Being a Data Skeptic