Errors of Predictive Models
You’ve created a bunch of predictive models and you need to measure the accuracies of each of them to choose the one that’s best for your purposes.
In this course I’m going to show you all of the most used measures and teach you exactly when to use them – and when not to.
Most importantly I’m going to show you how to interpret each of them, so you always know which is the best measure for your uses.
Certificate of completion
Perfect for beginners
- LEARNING Outcomes
So you’ve created a bunch of predictive models and now you need to choose the one that’s best for your purposes.
How do you do this? Eeny meeny? Throw darts at them?
You need to be able to measure the accuracies of each of your models so you can choose between them objectively.
The only problem is that there are literally loads of different measures you can use. Reading around the internet and watching videos on YouTube will only make you more confused, because each method has its own set of dedicated fans.
In this course I’m going to show you all of the most used measures and show you exactly when to use them and – more importantly – when not to.
And there’s only one place in the universe that you can get this course – right here!
If you’re truly interested in measuring the effectiveness of your models, don’t miss this course!
Here's what you'll learn:
you’ll learn why most papers textbooks and articles get the terminology wrong – and how to get it right
you’ll learn how to calculate the errors of regression-based predictive models – with lots of practice sessions
you’ll learn how to calculate the errors of classification-based predictive models –lots more practice sessions
you’ll learn exactly which statistical tests to use, why, when and how – and how to interpret them correctly too!
Suitable for beginners to assessing predictive models, in this course you’ll learn to ‘play’ with your data, learning what you can and – more importantly – can’t do with it.
Each lesson starts with a quick question to find out where your strengths and weaknesses are, then you’ll dive straight into the data. There will be LOTS of playing and practising with data, and you’ll learn by doing.
Then you’ll finish each lesson with a quiz – by now you should have learned EXACTLY what the correct responses are, and answer with confidence!
In this course you will get:
- 1Over 2.5 hours of video content
- 2Over 2 hours of practice exercises
- 3Learn how to analyse regression-based predictive models
- 4Learn how to analyse classification-based predictive models
- 5Learn the strategy of which steps to perform – in the correct order
- 6Data files are provided for the student to practice with
- 7Practical learning experience with real data
In this course you will learn how to:
This course has a dedicated forum where you can ask questions, get answers and connect with our learners.
You can find the forum here:
Students completing the course will have the knowledge and confidence to be able to analyse regression- and classification-based predictive models quickly and accurately.
Complete with HD videos, data, examples and practice exercises, you’ll be able to work alongside the instructor as you work through each concept, and will receive a certificate of completion upon finishing the course.
Oh, yes – and there are lots of little surprises for you along the way!
Introduction to the Errors of Predictive Models
An introduction to this course and what to expect as you learn from the video lessons and practice exercises
Introduction to the course
Errors of Regression Models (Part 1)
In this chapter you'll learn the building blocks of calculating the variability of your data using R-Squared and Variance
Introduction to the Errors of Regression-Based Predictive Models
Errors, Residuals, Deviations
Errors of Regression Models (Part 2)
In this chapter you'll learn the building blocks of calculating the bias of your data, why how and when to use each measure
Mean Absolute Error
Errors of Classification Models (Part 1)
In this chapter you'll learn how to measure the accuracy of your models - and why you need additional measures!
Introduction to the Errors of Classification-Based Predictive Models
PPV & NPV
Sensitivity & Specificity
Errors of Classification Models (Part 2)
In this chapter you'll learn about the additional measures you need, how to calculate them, when and why!
F-measure & Youden’s J
AUC & Gini Coefficient
In this chapter you'll recap everything you've learnt about assessing regression-based and classification-based predictive models
Your Course Certificate