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
 advanced(?) data masking options for sigmoidialfit

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
suras Posted - 02/01/2010 : 01:23:58 AM
Hi,
First: I am a newbie on Origin. I tried to find answers for my questions on the forum but without luck. However since I am new to this, it is likely already described but i just dont know the right terms to use for the search... Sorry if that is the case.

Anyway; my question
General problem: to do intelligent masking of data before fitting.

I am analyzing multiple (96 as minimum, sometimes over 1000) sigmoidial curves.
To get good precision fits with low and well behaved residuals its crucial that the all the data points that's not a part of the transition are masked. The values for this (the points that needs to be masked) is not global, so the masking has to be done for each curve to be fitted individually. This is what I want to learn how to do. So i need guidance in how to approach this in the most intelligent way.

In the most simple case, with just one well defined transition, just normalizing the dataset and going with max and min can be "ok" but not more. But on several occasions i have more complex data to fit with multiple transitions or a lot of noise.

I guess this is a problem for most sigmoidial fitting?

Thanks in advance
/S
1   L A T E S T    R E P L I E S    (Newest First)
easwar Posted - 02/01/2010 : 09:53:19 AM
Hi,

Can you send us some of your data? Please include best and worst case datasets, and refer to this post in your message. You can send files using the instructions on this page:
http://originlab.com/index.aspx?s=1&lm=123&pid=752

Easwar
OriginLab

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