Linear weighting

[lingaa]

Hi everybody

We have more options in MS for regression purpose. Linear 1/x,Linear1/x2
Quadratic 1/y and Quadratic 1/y2. Generally all are preferring with linear 1/x2 . Why? How to select the regression for calibration curve? Any specific method is there? I have read some of other compnies document, they have given some table for why they have selected Quadratic.
But i cant understand.
So please help me.[/quote]

[tom jupille]

This has been discussed a number of times here on the Forum. Do a search using "weighted regression" and you will find what you need.

I've stuck an excerpt from our LC/MS/MS course that discusses this up on the LC Resources web site:
http://www.lcresources.com (click on "Resources", then on "Exchange").