Continue to Site

Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronics Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Multivariate Regression Problem

Status
Not open for further replies.

raylito

Junior Member level 1
Junior Member level 1
Joined
Jun 6, 2006
Messages
17
Helped
0
Reputation
0
Reaction score
0
Trophy points
1,281
Activity points
1,443
My problem is as follows:

I have 1000 marbles labelled M1 to M100 (10 of each M number)

Each marble has a different mass, but generally the higher the number, the higher the mass. It is possible for a lower number to have a mass greater than a higher number, but not likely.

Someone packs up 10 bags of these marbles for me. Each bag has a number of marbles in, who's masses add up to 10Kg.

I open up each bag and table the results which will look something like:
Bag1: M1,M1,M1,M5,M6,M7,M17,M20,M20,M21,M22,M23,M23,M23,M30,M31,M32
Bag2: M2,M2,M5,M6,M6,M7,M8,M9,M20,M20,M21,M22,M50,M55,M80

And so on.... for 10 bags. The number of marbles in each bag varies, but each bag's marbles must add up to 10Kg.

What would be the best way to work out the mass of each marble? There are too many unknowns for the simultaneous equations to work, but are there some assumptions or shortcuts or estimates we can make?

Would I use mutivariate regression to solve this or something else?
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Back
Top