Quantcast
Channel: Pentaho Community Forums
Viewing all articles
Browse latest Browse all 16689

What approaches other than linear regression can help in finding weights for features

$
0
0
I have a numeric dataset in the following format
X1 X2 output(Y)
1 2 3
2 5 1
2 3 2
2 2 2 . . .
I am looking for a way to model the data and find the weights (b0,b1,b2)
Y = b0 + b1X1 + b2X2
One way to do this is to use, linear Regression for Multiple Variables.
http://www.nd.com/NSBook/NEURAL%20AN...ple_Varia.html
http://www.statsoft.com/Textbook/Multiple-Regression
But I wonder if there is a better way to build a model? For example, we can build a model and know the weights such as Y = 1.3433 + 0.2836*x1 + 0.004*x2But the values 1.3 or 0.28 don't say much about the relations in the data. There should be better ways to find weights and build models. Something that have summations or divisions, square root, etc, such as
Y = b0 + ∑b1*x1 + b2*x2^2
Any suggestions that can Weka help with ?
Thanks!

Viewing all articles
Browse latest Browse all 16689

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>