The Origin Forum
File Exchange
Try Origin for Free
The Origin Forum
Home | Profile | Register | Active Topics | Members | Search | FAQ | Send File to Tech support
 All Forums
 Origin Forum
 Origin Forum
 fitting with numerial series

Note: You must be registered in order to post a reply.
To register, click here. Registration is FREE!

Screensize:
UserName:
Password:
Anti-Spam Code:
Format Mode:
Format: BoldItalicizedUnderlineStrikethrough Align LeftCenteredAlign Right Horizontal Rule Insert HyperlinkUpload FileInsert Image Insert CodeInsert QuoteInsert List
   
Message:

* HTML is OFF
* Forum Code is ON
Smilies
Smile [:)] Big Smile [:D] Cool [8D] Blush [:I]
Tongue [:P] Evil [):] Wink [;)] Clown [:o)]
Black Eye [B)] Eight Ball [8] Frown [:(] Shy [8)]
Shocked [:0] Angry [:(!] Dead [xx(] Sleepy [|)]
Kisses [:X] Approve [^] Disapprove [V] Question [?]

 
Check here to subscribe to this topic.
   

T O P I C    R E V I E W
lesaout Posted - 05/02/2007 : 03:35:17 AM
Origin Version (Select Help-->About Origin): OriginPro7.5 SR6
Operating System: XP

Dear All,

I have experimental data D(t) and try to fit them using a numerical series as:
D(t=0) = 0
D (t) = D(t+dt)+ dt*K1 (K1 is the parameter to adjust, the real function used is of course a little bit more complicated).

Do you think it is possible under ORIGIN?

Thanks for your answer,

Gwenn
4   L A T E S T    R E P L I E S    (Newest First)
larry_lan Posted - 05/02/2007 : 11:45:33 AM
Hi Gwenn

There are several methods, such as, you can add one column, say dt, and set dt = x[i] - x[i-1], like the graph below, and define a two Independent Varianble fitting function, like:

Parameter Names: K1
Independent Var: x, dt
Dependent Var: y
Function:
if (x == 0)
{
y = x;
} else
{
y = x + dt*K1;
}

Then you can fit and evaluate K1.



Hope it helps

Larry
OriginLab Technical Services

Edited by - larry_lan on 05/02/2007 12:12:14 PM
lesaout Posted - 05/02/2007 : 09:41:48 AM
Dear Larry,
Experimentally, at early age (from t=0 to 3 days) we have points with a short delta t (delta t=6hours for example) and at later age we have points with a large delta t (delta t=1 month). The experiment time is about 2 years.

For the fitting, dt is defined as the time step. We have to define the fitting function D at early age with a short dt until 3 days then we can increase the step (for ex. dt= 15 days).

dt is defined as: dt = t[i] - t[i-1]

The equation can be changed like: D(t[i+1]) = D(t[i]) + dt*K1

Thanks for all,

Gwenn

Better to know what your data looks like, and how you define dt. Generally, dt = t[i] - t[i-1]. If so, dt should be equal spaced, or we don't know what's D(t+dt). Another comment is, can you change the equation like:

D(t=0) = 0
D(t[i]) = D(t[i+1])+ dt*K1 --> D(t[i+1]) = D(t[i]) + dt*K1

So could you please provide more information?

Larry
OriginLab Technical Services
[/quote]
lesaout Posted - 05/02/2007 : 09:41:01 AM
quote:

Better to know what your data looks like, and how you define dt. Generally, dt = t[i] - t[i-1]. If so, dt should be equal spaced, or we don't know what's D(t+dt). Another comment is, can you change the equation like:

D(t=0) = 0
D(t[i]) = D(t[i+1])+ dt*K1 --> D(t[i+1]) = D(t[i]) + dt*K1

So could you please provide more information?

Larry
OriginLab Technical Services

larry_lan Posted - 05/02/2007 : 07:23:33 AM
Better to know what your data looks like, and how you define dt. Generally, dt = t[i] - t[i-1]. If so, dt should be equal spaced, or we don't know what's D(t+dt). Another comment is, can you change the equation like:

D(t=0) = 0
D(t[i]) = D(t[i+1])+ dt*K1 --> D(t[i+1]) = D(t[i]) + dt*K1

So could you please provide more information?

Larry
OriginLab Technical Services

The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000