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
Username:
Password:
Save Password
Forgot your Password? | Admin Options

 All Forums
 Origin Forum
 Origin Forum
 Lognormal parameters
 New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

b.harris

Australia
Posts

Posted - 10/10/2005 :  12:02:40 AM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
Origin Version (Select Help-->About Origin): 7.5
Operating System: XP

I am needing a little clarification regarding the meaning of the parameters for the lognormal equation.

From the sample curve, it appears that xc is the mode, w the width, and A the value of the mode above y0 (the baseline). However after running this equation several times, and looking at the formula from other sources I gather this is not quite right?

By my reckoning:
y0 = offset of baseline
w = sqrt of variance (Standard Dev)- a measure of width
xc = median (not the mode or mean)
and A = The area under the curve if y0 = zero (which can be demonstrated by integrating the curve using the analysis -> calculus -> integrate)

Is this correct??

Many thanks

Ben

Leo_Li

China
Posts

Posted - 10/10/2005 :  01:44:21 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hello b.harris,

You're right. The expression of Origin's Log-normal function is fine but the meanings of xc and w are mis-leading.

i) xc, this parameter doesn't correspond to the Y maximum. The reason is that Log-normal is asymmetric peak function. xc corresponds to the peak center when the Log-normal is approximately symmetric (when w is small). In another word, xc is the "distorted" peak center.

ii) w, this is an asymmetric factor. The peak will be approximately symmetric when w is small.

iii) In some literature, xc and w are also called "mean" and 'standard deviation" respectively. (ref: http://en.wikipedia.org/wiki/Log-normal_distribution )

Leo

Go to Top of Page

kvidovic

Slovenia
1 Posts

Posted - 06/08/2022 :  02:55:40 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,

I am also struggling with these parameters. So if I am understood it correctly, xc splits the distribution in two half's. Than xc represents the median or the geometric mean?

If not can you please explain how to calculate the median or geometric mean from xc.

Thank you.

k.v
Go to Top of Page
  Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic
 New Topic  Reply to Topic
 Printer Friendly
Jump To:
The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000