Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
I'm trying to understand how to read a scatter plot based on the results of my confusion matrix. This is the CM:
I saw an high correlation between column 5 and column 6, a low correlation with column 11 and a medium correlation with column 1, so I decided to create a scatter plot to see the differences:
How do I read it? For example, the correlation between column 6 and 5 is expressed from the fact that I can linear divide the samples of each class? Why the column 11 has a different plot?
High correlation: It basically means that if one variable is changing, then another variable will change in the same direction. For example. The relationship between the amount of time spent studying and the grades a student receives. Generally, the more time a student spends studying, the better grades they receive. This would be a positive correlation because both variables increase together.
So if you get that, then you can actually see the variable 5 is changing and variable 6 is also changing in the same direction, but they are too close to differentiate from each other.
Medium correlation: It refers to a relationship between two variables that is real and statistically significant, but not strong enough to be considered a high correlation. For example. The relationship between the height and weight of a person. While there is a general trend that taller people tend to weigh more than shorter people, there are many other factors such as diet, lifestyle, and genetics that can influence a person's weight. Therefore, the correlation is not as strong or direct as in the high correlation example.
Your scatter plot shows that, column 5 is changing but column 11 is not changing as the column 5 is changing. And it looks like your column 11 is categorical in nature.
Low correlation: Low correlation refers to a relationship between two variables that does not fit a linear pattern. In other words, changes in one variable do not consistently correspond to changes in the other variable. For example, there might be a low correlation between the amount of coffee a person drinks and their income level. While there may be some relationship, it's not consistent or strong enough to suggest that drinking more coffee will necessarily lead to a higher income.
In the scatter plot, you can see that, even if the column 5 is changing, the column 1 is not changing that much.
