Analysing relationship between numerical variables - Correlation (2022)
In this one let's understand correlation in clear detail. Now, one thing that you must understand is correlation is a bi variate analysis technique.
That means, in order to compute correlation you need to have two different variables, while other metrics such as mean standard deviation, coefficient of variation and so on.
Complete Machine Learning Course for FREE: https://rb.gy/posrbk
Checkout complete Data Scientist Learning Path here: https://edu.machinelearningplus.com/s...
🔹 Analzing relationship between numerical variables - Correlation
These all require only one variable in order to be computed, whereas, in order to compute correlation you need two variables. And that is why it is also considered as a part of by way rate analysis technique.
So, in this video, we will see everything about correlation starting from what is correlation, the intuition when and when not to use it, the formula computations and there are other types of correlations.
Also, there is not just one single formula for correlation, there are multiple variations of it, we will explore that In brief, we won't we won't go into the details of the other types of correlation which we will not cover here, but you will get an idea of what it is about, let's get right into it.
When someone uses the term correlation, what they typically are referring to is the Pearson's correlation, there are two other forms of correlation we will get to that later, but what you see here is the formula for Pearson's correlation.
Now, this may seem a bit complex, I will walk you through this shortly, but here the top part in the numerator is also called the covariance of x and y. So, what is happening here is given two variables, so, you have variable A and B, you have certain values over here B also have certain values over here you have the mean of a as a dash and being mean of BS B dash now, from a from every value of a, you subtract a dash,
I'm calling this number one this is number two, let me call it write it as 123 and so, on for every value in a, you subtract the mean of a likewise in every value in B, you subtract the mean of B that is what is written out over here, then multiply both of them and do a summation i will walk you through this process in more detail. Now, this whole summation is called the coefficient of variation.
Whereas, there are two terms over here on the bottom the first term here is the standard deviation of x the first variable and this term is the standard deviation of y what this means to us essentially is correlation coefficient is nothing but covariance of x comma y divided by standard deviation of x standard deviation of y, this is the formula for correlation or to be more precise, it is Pearson's correlation.
Now, this correlation value can vary between minus one to plus one it is always between minus one to plus one and what does this mean to us to understand that, we need to understand what correlation is in the first place, what does it actually represent.
Let me know in the comments section if you have any questions!
🤝 Like, Share, Subscribe for more!
Follow us on our social media handles for all updates, events and live sessions-
✅ Instagram: / machinelearningplus
✅ LinkedIn: / machine-learning-plus
✅ YouTube: / numyard
✅ Twitter: / r_programming
✅ Website: https://www.machinelearningplus.com/
If you enjoyed this video, be sure to throw it a like and make sure to subscribe to not miss any future videos!
Thanks for watching!
#machinelearningplus #python #machinelearning #datascience