Understanding through Discussion

QuickSearch

 Welcome! You are not logged in. [ Login ] EvC Forum active members: 78 (8896 total)
 Current session began: Page Loaded: 03-23-2019 12:23 AM
36 online now:
Dredge (1 member, 35 visitors)
Chatting now:  Chat room empty
Post Volume:
 Total: 848,563 Year: 3,600/19,786 Month: 595/1,087 Week: 185/212 Day: 0/27 Hour: 0/0

Author Topic:   Generalized Least Square Method
eaihua
Member (Idle past 3705 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:
φ = ∑(yi - y)^2 (2)

Take (Formula 1) to (Formula 2) to get :

φ = ∑(yi - a0 - a1 xik )^2 (3)

When the square of ∑(yi - a0 - a1 xik ) is the smallest, we can use functionφ 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

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

Director
Posts: 3879
Joined: 09-26-2002

 Message 2 of 11 (474887) 07-11-2008 11:15 PM

Thread moved here from the Proposed New Topics forum.

This seems to be the most sophisticated piece of spam that we will ever see. I put it in the "Coffee House" for our resident math geeks.

Personally, integral symbols tend to cause nausea.

New Cat's Eye
Inactive Member

 Message 3 of 11 (474893) 07-12-2008 12:01 AM Reply to: Message 1 by eaihua07-11-2008 10:39 PM

Wow, this is the most elegant spam I have ever seen.

Who buys these "studios" and what do they use them for?

It seems that your market would be so small that spam would be uselessly ineffective.

 This message is a reply to: Message 1 by eaihua, posted 07-11-2008 10:39 PM eaihua has not yet responded

 Replies to this message: Message 4 by Brad McFall, posted 07-12-2008 8:00 PM New Cat's Eye has not yet responded

Member (Idle past 3110 days)
Posts: 3428
From: Ithaca,NY, USA
Joined: 12-20-2001

 Message 4 of 11 (475003) 07-12-2008 8:00 PM Reply to: Message 3 by New Cat's Eye07-12-2008 12:01 AM

chinese frame
China(internet addresses) have been known to break into CIA computers and they try to get western science information (so said NPR) so why should they not also be trying to extract information from EvC? I know we can say things here that do not exist in "everyday" life nor 2nd life.

The idea that they would steal information in last years' digital picture frames is just a really bad use of a good communication medium.

 This message is a reply to: Message 3 by New Cat's Eye, posted 07-12-2008 12:01 AM New Cat's Eye has not yet responded

 Replies to this message: Message 5 by Taz, posted 07-12-2008 8:11 PM Brad McFall has not yet responded

Taz
Member (Idle past 1368 days)
Posts: 5069
From: Zerus
Joined: 07-18-2006

 Message 5 of 11 (475007) 07-12-2008 8:11 PM Reply to: Message 4 by Brad McFall07-12-2008 8:00 PM

Re: chinese frame
 Brad writes:China(internet addresses) have been known to break into CIA computers and they try to get western science information (so said NPR)...

I think you and I listened to the same program.

The more important question is who are you and what have you done with our beloved Brad McFall? Our beloved Brad McFall usually doesn't make this much sense.

 This message is a reply to: Message 4 by Brad McFall, posted 07-12-2008 8:00 PM Brad McFall has not yet responded

eaihua
Member (Idle past 3705 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 yet responded

Member (Idle past 3110 days)
Posts: 3428
From: Ithaca,NY, USA
Joined: 12-20-2001

 Message 7 of 11 (475290) 07-14-2008 5:36 PM Reply to: Message 6 by eaihua07-13-2008 7:18 AM

exchange - how?
Do you mean exchange of variables or commerce when you posted
quote:
Exchange can...to develop technology
?
 This message is a reply to: Message 6 by eaihua, posted 07-13-2008 7:18 AM eaihua has not yet responded

eaihua
Member (Idle past 3705 days)
Posts: 6
From: china beijing
Joined: 07-11-2008

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

Yes, exchange of commerce for technology.

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

Member (Idle past 3110 days)
Posts: 3428
From: Ithaca,NY, USA
Joined: 12-20-2001

 Message 9 of 11 (475714) 07-17-2008 5:23 PM Reply to: Message 8 by eaihua07-15-2008 9:53 AM

what is the subject?
Does this mean that you are simply using EvC to advertise the "change discipline" Studio you linked above?

If you were interested in a discursive conversation on how numbers can relate to curves (whether the design exists or not etc)and so to what figures the thing might be put I suppose you would have something here to engage others as well as me on, but if you were simply trying to let EvC members know of the data manipulation capacity of the prodcut avered then perhaps you should have responded to Cathloic Scientist above (who uses the stuff?).

 This message is a reply to: Message 8 by eaihua, posted 07-15-2008 9:53 AM eaihua has responded

 Replies to this message: Message 10 by eaihua, posted 10-30-2008 2:17 AM Brad McFall has responded

eaihua
Member (Idle past 3705 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 McFall07-17-2008 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.

Purchase contact: ww_yypp@163.com
Purchase web: http://www.eaihua.com

 {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}

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

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

Member (Idle past 3110 days)
Posts: 3428
From: Ithaca,NY, USA
Joined: 12-20-2001

 Message 11 of 11 (487399) 10-30-2008 10:36 PM Reply to: Message 10 by eaihua10-30-2008 2:17 AM

Re: what is the subject?
Yes I SEE all that.

I need to know how your maths(sic!) relate to this image if I am to have any conversation with you.

You may feel that I am simply trying "to sell" my own ideas as you may be doing for a product but I am willing as a member of EVC to take the conversation where the thread goes, no matter what, even if this takes me off my own game plan.

You seem to be using EvC simply to promote a/your product. We all (I think I can speak for a gaggle of EvC) "got" that, at the first. I did. That much I know.