1. Exploring and describing data
In this video, we'll focus on how data-fluent individuals explore and describe data. Let's dive in!
2. Scenario: analyzing the customer engagement drop
To get started, let's consider a scenario. Katia is a customer success manager at "Xcelerate Solutions", the tech startup that provides innovative software solutions to businesses. After noticing a drop in user engagement, she formed the analytical questions to investigate further. She now wants to analyze data to find the root cause of the issue. After collecting data about active user numbers, customer feedback, and software performance, she checks for data quality and explores the data. She creates data visualizations to see the changes in user engagement and identify any noticeable patterns or trends.
3. Scenario: finding the root cause
By correlating the user engagement metrics and software performance, she finds that user engagement actually drops during periods of poor software performance which is measured by the software response time. This finding is fully confirmed when she additionally checks the customer feedback data where she can see more cases of customer complaints because of software performance during the same period. This example demonstrates how the ability to explore and describe data leads to finding the root cause of the business problem. Let’s dive deep into these skills in more detail.
4. Assessing data quality
Data-fluent individuals know how to navigate and explore datasets. However, before delving into data exploration they first ensure that the data is reliable. They take the time to examine and assess the integrity and accuracy of the data. They can discover missing, duplicate, or inconsistent entries and understand their impact on the analysis results. As a next step, they can perform simple data cleaning or highlight these issues to the data experts to take the necessary actions to resolve them.
5. Exploring data with visualizations
The purpose of data exploration is to help uncover potential insights. The main technique used is exploratory analysis through data visualization. Data-fluent individuals use various data visualization techniques to present the data visually. They create graphs, and plots. From bar charts and line charts to help them understand patterns and trends up to histograms and box plots to understand the data distributions. They have the ability to recognize spikes, variations, outliers or relationships that might indicate interesting insights.
6. Describing data
Besides exploring data, data-fluent individuals can effectively describe data. This enables data-fluent individuals to communicate key features of the dataset to make comparisons and draw conclusions from the data. Describing data involves providing a detailed and systematic summary of the dataset's characteristics. Descriptive statistics is the main technique used to quantitatively summarize and describe various aspects of the data. This includes measures of central tendency, such as the mean and median, measures of variability such as the standard deviation, as well as measures to assess the relationship between variables such as the correlation coefficient.
7. The analytical mindset
While working with data, it is essential to have an analytical mindset. Consider the context in which the data was collected, take into account external factors that might impact the data. This ensures a more accurate and comprehensive analysis. In addition, data-fluent individuals approach data analysis with a critical and curious mindset. They question assumptions, challenge interpretations, and seek alternative explanations for patterns they observe to find answers to their business problems.
8. Utilizing tools and technologies
Last but not least, to explore and describe data effectively, data-fluent individuals have the skills to use the required data tools and technologies. This mainly includes data visualization and reporting tools to create reports and interactive and visually appealing data visualizations in an easy way as well as spreadsheet software mainly used for analysis and basic visualizations. It's worth noting that with the emergence of generative AI, the tools are becoming more powerful and easy to use, leading to new possibilities for data fluency. Being able to rely on your skills to leverage those tools is necessary for any successful analysis.
9. Let's practice!
Essentially, data-fluent individuals including business users can learn these simple but powerful skills to perform their own analysis. Now, let's reinforce what you learned with hands-on exercises to deepen your understanding.