See the result first:

	Approximated Val: 28.5041 Actual Val:14.1421
	

My approach is first calculate the linear regression function for each variable, no matter how they are co-related. I don't care at the moment. And it sums up the total of all intercepts and break them up into 4 slopes which contributes to each component (4 IVs), then the result is about the double of the actual value, why?

thanks

Jack

Maybe because you ignored the correlations between the variables?

Also, if you could post the full example it would be helpful.