In this episode, we take a deep dive into distribution analysis — a critical concept in descriptive analytics that helps us understand how data is spread, not just where its average lies. We explore the most common types of statistical distributions, where they appear in real-world processes, and the practical methods used to identify them.

This discussion also ties directly back to the previous two episodes in the series, where we explored the concepts of averages, standard deviation, and outliers. All of these ideas are connected to the same fundamental problem: understanding the true character of a dataset. An average tells us what value we might typically expect, standard deviation reveals how much variation exists around that value, and distribution analysis helps us understand the overall shape of the data that produces those patterns.

Understanding the shape of a distribution changes how we interpret averages and what we should expect from a system. In maintenance, finance, healthcare, and many other fields, recognising the underlying distribution can reveal risk, variability, and hidden patterns that a simple average cannot show.

A quick warning: parts of this episode do become a bit technical when discussing how distributions are selected and identified. Don’t be intimidated. These concepts will be explored in more detail in later episodes — think of this episode as laying the groundwork for deeper analytical tools as the series progresses.

An average tells us the center of the data — but it doesn’t tell us how reliable that number really is.

In this episode, we explore variance and standard deviation, two fundamental concepts in descriptive analytics that reveal how much data varies around the mean. A dataset with a small standard deviation behaves consistently and predictably, while a larger one signals volatility, uncertainty, and potential risk.

We unpack the mathematical logic behind these measures and explain why variance forms the foundation, while standard deviation translates variation back into practical units we can understand.

Using examples from finance, healthcare, and industrial maintenance, we show how measuring variation helps professionals detect unstable processes, identify early equipment faults, and understand inconsistent human performance.

Because in analytics, the average is only part of the truth — the real story lives in the variation.

In this episode, we move into the analysis stage of the analytics process, beginning with descriptive analytics.

One of the most fundamental tools in descriptive analysis is the average. But what does an average really represent? In this episode, we unpack the idea of an average as our best estimate of a typical value when limited information is available.

We also explore the common traps of relying on a single average and how it can hide important variation within the data.

Turning data into measurable organizational value through strategic alignment and capability development.

This episode is based on a talk delivered by Melvon Ekandjo at Henley Africa business school in Johannesburg, South Africa.

This episode explores the ETL concept. It is used to connect the analysis tool to the data source and automated the flow of data to produce consistent quality data.