Register | Sign In


Understanding through Discussion


EvC Forum active members: 65 (9162 total)
6 online now:
Newest Member: popoi
Post Volume: Total: 915,815 Year: 3,072/9,624 Month: 917/1,588 Week: 100/223 Day: 11/17 Hour: 0/7


Thread  Details

Email This Thread
Newer Topic | Older Topic
  
Author Topic:   Generalized Least Square Method
eaihua
Member (Idle past 5628 days)
Posts: 6
From: china beijing
Joined: 07-11-2008


Message 1 of 11 (474885)
07-11-2008 10:39 PM


When studying the relating relations between the two variable numbers (x, y), we can get a series of binate data(x1, y1, x2, y2.....xm, ym), describing the data into the x - y orthogonal coordinate system(Chart), the points are found near a curve. suppose the one-variant non-linear variant of the curve such as (Formula 1)
y = a0 + a1 xi ^k (1)
There into, a0, a1 and k are arbitrary real numbers
To set the curve variant, the numbers of a0, a1 and k must be set. Use the same way with “The Least Square Method data regression” based on the square sum of the deviation of the true measure value yi and computing value.
Order:
= ‘(yi - y)^2 (2)
Take (Formula 1) to (Formula 2) to get :
= ‘(yi - a0 - a1 xik )^2 (3)
When the square of ‘(yi - a0 - a1 xik ) is the smallest, we can use function to get the partial differential coefficients of a0, a1 and k, make the three partial differential coefficients zero.
(4)
(5)
(6)
Get three variant groups about a0,a1 and k which are the unknown numbers, solve the groups can get mathematical model.
Also, we can judge the right of the mathematical model with the help of correlation coefficient R, statistical variable F, residual standard deviation S to judge, it is better that R tends to 1,the absolute value of F is bigger and S tends to 0. the validation is good, but error of model computing sometimes are big, to improve the mathematical model farther, the biggest error, equal error and the equal relating error of computing model are computed to validate the model.
The Method to do multivariate nonlinear model chart
Web address:

Replies to this message:
 Message 3 by New Cat's Eye, posted 07-12-2008 12:01 AM eaihua has not replied

  
eaihua
Member (Idle past 5628 days)
Posts: 6
From: china beijing
Joined: 07-11-2008


Message 6 of 11 (475051)
07-13-2008 7:18 AM


Exchange can, Not to vilify the Chinese people, Chinese people have the ability to develop technology.

Replies to this message:
 Message 7 by Brad McFall, posted 07-14-2008 5:36 PM eaihua has not replied

  
eaihua
Member (Idle past 5628 days)
Posts: 6
From: china beijing
Joined: 07-11-2008


Message 8 of 11 (475336)
07-15-2008 9:53 AM


Mr Brad McFall
Yes, exchange of commerce for technology.

Replies to this message:
 Message 9 by Brad McFall, posted 07-17-2008 5:23 PM eaihua has replied

  
eaihua
Member (Idle past 5628 days)
Posts: 6
From: china beijing
Joined: 07-11-2008


Message 10 of 11 (487335)
10-30-2008 2:17 AM
Reply to: Message 9 by Brad McFall
07-17-2008 5:23 PM


Re: what is the subject?
Soft name: DRS
Soft Ver: 2008
Soft language: Engish
Run environment: Win9x/NT/2000/XP
Soft size: 1901 KB
Soft presentation: Least Cubic Method is a new method for data regression analyse , it expanded Least Square Method, According to the principle, this program can be used to work out single factor linear data regression, multi factors linear data regression, single factor non-linear data regression, and multifactors non-linear data regression.
Soft download1: http://jlbc.skycn.com/down/eDRS2008.zip
Soft download2: http://jlbc.skycn.com/down/eDRS2008.zip
Soft download3:DRS - Free download and software reviews - CNET Download
Purchase contact: ww_yypp@163.com
Purchase web:
{Note: This message is from a shut down "Links and Information" topic - Multivariate nonlinear regression analysis DRS. There is a bit more to be seen at this other topic. - Adminnemooseus}
Edited by Adminnemooseus, : Add note in green box.

This message is a reply to:
 Message 9 by Brad McFall, posted 07-17-2008 5:23 PM Brad McFall has replied

Replies to this message:
 Message 11 by Brad McFall, posted 10-30-2008 10:36 PM eaihua has not replied

  
Newer Topic | Older Topic
Jump to:


Copyright 2001-2023 by EvC Forum, All Rights Reserved

™ Version 4.2
Innovative software from Qwixotic © 2024