Skip main navigation

£199.99 £139.99 for one year of Unlimited learning. Offer ends on 28 February 2023 at 23:59 (UTC). T&Cs apply

Find out more

Introduction to uncertainty and errors in data

Learn about uncertainty and errors in data
(dramatic music) In this video, we will explore uncertainty and the reasons behind is cause in data. Let us refresh a concept from one of our previous sections, error bars in Excel. In some data sets each data point has a particular error amount associated with it. Perhaps in another column in a spreadsheet. In Excel and other tools this value can be referenced to render the error bars. Error bars can be added to a chart in Excel in the same way as many other chart elements by selecting add chart element, then error bars. There are many reasons why we might have uncertainty in our data. As an analyst, you are naturally expected to account for it while conducting your analysis.
Let us try to understand this with this scenario here. Let us assume that a weighing machine is certified for a particular accuracy and gives the correct weight every time a person measures their weight. Now if we take samples from a population who use this weighing machine, the mean of the population will be the same as the mean of the mean weight of multiple samples.
Let us assume that the measurement has some kind of error to it and this machine weighs the person as 60 plus or minus one kilogrammes. In such a case, if we take samples from a population who use this weighing machine, we know the mean of these samples probably won’t match the mean or other measuring attributes of the population. This results in uncertainties in your data and can be measured as standard deviation, standard error of the mean, and confidence interval. Depending on the size of the sample compared to the size of the population, we may have more or less error or confidence. Throughout this section, you will learn to create error bars in Matplotlib using Python.
You will also learn to display discrete data using the confidence bands. Lastly, we will see what bootstrapping is and how effective the method is. Let’s get started.

Before we start learning how to display uncertainty using Python, watch this video to:

  • familiarise yourself with the constant changes in errors and uncertainty
  • understand the various methods of preparing your plots and choosing an appropriate plot type according to the data set.

Download your Jupyter Notebook

Before you start with this week, download your accompanying Jupyter Notebook containing explanations and codes in cells that you can run to receive outputs.

The Notebook contains only the code snippets that you can run to get an immersive and interactive experience, as well as instant results of the codes alongside the explanations.

Make best use of this opportunity to familiarise yourself with using the Notebook.

Download: Showing uncertainty

This article is from the free online

Data Visualisation with Python: Seaborn and Scatter Plots

Created by
FutureLearn - Learning For Life

Our purpose is to transform access to education.

We offer a diverse selection of courses from leading universities and cultural institutions from around the world. These are delivered one step at a time, and are accessible on mobile, tablet and desktop, so you can fit learning around your life.

We believe learning should be an enjoyable, social experience, so our courses offer the opportunity to discuss what you’re learning with others as you go, helping you make fresh discoveries and form new ideas.
You can unlock new opportunities with unlimited access to hundreds of online short courses for a year by subscribing to our Unlimited package. Build your knowledge with top universities and organisations.

Learn more about how FutureLearn is transforming access to education