Java Linear Regression not working

Question

Let me start off by saying I am terrible with math. I do not claim to be an expert (or even an advanced) mathematician by far.

What I'm trying to do is take this output:

And from those values (x,y) produce the following:

Slope (b): 0.96112312980002
Regression line equation: y=12.280535000464+0.96112312980002x
Correlation coefficient (r): 0.98120789611439

I used this website to calculate the above values can be found here. Any help in this matter would be greatly appreciated. I attempted using a snippet for this on stackoverflow found here, however the results are dismal. Can someone point me to a way of calculating these things via a library or even a class of its own?

The value i am most interested in is the correlation coefficient.

Is the problem that you don't understand the formula at the alcula.com link? — ajb, Dec 23 '14 at 20:25
Pretty much, im not sure how to do the calculation better than the stackoverflow snippet i found. — ThatGuy343, Dec 23 '14 at 20:29

Paul Boddington · Accepted Answer · 2014-12-23T20:32:26.370

1

The Apache Commons Math class SimpleRegression does it all.

You use addData() to input the x and y values. You use getSlope() and getIntercept() to get the equation of the regression line. You use getR() to get the correlation coefficient.

It couldn't be easier!

edited Dec 23 '14 at 20:32

answered Dec 23 '14 at 20:24

Paul Boddington

37,127
10
65
116

you weren't kidding about how easy this is.. :) thanks – ThatGuy343 Dec 23 '14 at 21:30

score 0 · Answer 2 · answered Dec 23 '14 at 20:26

0

Check out Apache Commons PearsonsCorrelation! (http://commons.apache.org/proper/commons-math/apidocs/org/apache/commons/math3/stat/correlation/PearsonsCorrelation.html)

answered Dec 23 '14 at 20:26

haley

1,165
7
13

Java Linear Regression not working

2 Answers2