Seriously. I will need it for work. I haven’t been able to understand that shit from any online resource until now. Please ELI5
In: 380
So you have a bunch of data, and you would like to put a line through it. The problem is that your data doesn’t sit on a line. So instead you just pick a line that gets as close to all your data points as possible. This is a linear regression.
Some of your points won’t be on that line. The difference between a data point and the line is called the error. When you have a computer do this it’s going to select a line that minimizes the overall error.
Depending on your data this might work really well and it might not. The R-squared value is just a way of determining how well the line fits the data. If you have a R-squared value close to one, then you have a really good line. If you have an R-squared value close to zero, then your data is totally random and can’t be fit to a line.
Latest Answers