Beginner’s Guide to Correlation Analysis: Bite-Size Stats, #4

By Lee Baker

Your correlation results are probably wrong. Sorry, but they are.

You see, there is one really important thing to know about your correlations that mean that whatever results you get you can't be sure they are correct.

This book fixes that.

Correlation is a way of describing how a pair of variables change together as a result of their connection. In other words, if one of your variables changes, the other is likely to change too, and correlations measure by how much.

Correlation analysis is one of the most used – and misunderstood – statistical techniques. Most correlation results are wrong, and for one very good reason. In this book we're going to understand just why this is, and learn how to fix it.

Beginner's Guide to Correlation Analysis explains how to look at correlations with a focus on understanding the data, how to work with it, choose the right ways to analyse it, select the correct statistical tools and how to interpret the results in a way that is easy to understand.

Best of all, there is no technical or statistical jargon – it is written in plain English.

It is packed with visually intuitive examples and makes no assumptions about your previous experience with statistics or correlations – in short, it is perfect for beginners!

Discover the world of correlation analysis. Get this book, TODAY!

• Language: English
• Publisher: CSI Publishing
• Release date: May 3, 2019
• ISBN: 9781386394136

Book preview

Introduction

Most books about correlations are difficult to read. In fact, most books about statistics are difficult to read and it leads you with the distinct impression that statistics is hard. I’m not going to tell you that it isn’t, but I will tell you that statistics is probably a lot easier than you think it is.

Over the years, I’ve taught statistics to scientists of all sorts of backgrounds. Nurses and surgeons, technicians and pathologists – even marketers, business executives and sales people. They all had two things in common:

they insisted that they didn’t understand statistics, and

they all had the light-bulb moment when they suddenly realised that getting the result they were looking for wasn’t so hard after all.

You see, statistics isn’t about statistical tests. Really, it isn’t. It’s also not about ‘pressing buttons until I get a p-value that looks about right’, as one renowned, world-class researcher once said to me.

It’s about understanding data, what you can and can’t do with it, and how to extract the right kind of information from it. Statistics is just a toolbox that you can use to reach the story locked inside the data.

So here in this book, we’re going to look at correlations and associations with a focus on understanding the data, how to work with it, choose the right ways to analyse it, select the right tools from our statistical toolbox and how to interpret the results in a way that is easy to understand.

We’re going to start out by learning the difference between correlations, associations and statistical relationships. From there we’re going to delve a little deeper into correlations and two different types of associations, learning how to arrange your data, how to plot it and how to interpret the plot. We’ll learn how to analyse the data to get a better understanding of what it’s trying to tell us, which statistical tests to use in various situations, and we’ll learn to recognise which statistical results are the ones that we need to pay most attention to.

Then I’m going to throw a spanner into the works by telling you that you can’t trust any of it!

We’ll then visit the world of multivariate