
Hi,
I have a sample of values, and I like to find the mu and sigma to fit to a logn distribution.
I try to convert a Matlab code, that is using the lognfit method.
Does anybody has an idea to do this?



I've just added a
LogNormal.Estimate function for exactly that (maximum likelihood) that will be included in the next release.
In the meantime, simply take the natural logarithm of each sample and then compute mean (> mu) and standard deviation (> sigma) of these resulting samples.



Thanks a lot for the answer.
I'll have a look soon.
Le 15 août 2013 09:30, "cdrnet" <[email removed]> a écrit :
From: cdrnet
I've just added a
LogNormal.Estimate function for exactly that (maximum likelihood) that will be included in the next release.
In the meantime, simply take the natural logarithm of each sample and then compute mean (> mu) and standard deviation (> sigma) of these resulting samples.
Read the
full discussion online.
To add a post to this discussion, reply to this email ([email removed])
To start a new discussion for this project, email [email removed]
You are receiving this email because you subscribed to this discussion on CodePlex. You can
unsubscribe on CodePlex.com.
Please note: Images and attachments will be removed from emails. Any posts to this discussion will also be available online at CodePlex.com



Hi,
Do you have the same method for a normal distribution (like "normfit" MatLab method) to get mu and sigma ?
By the way, where is the extention for MeanVariance ?
Thanks a lot !



Yes, I had added the equivalent to the
Normal distribution as well, in the same commit.
MeanVariance is new in the Statistics.Statistics class, but you can just use Mean and Variance separately to the same effect (although two passes).
Both will be available in the next release.
Thanks,
Christoph



Thanks Christoph !
An other question :
Is it possible to have a "public double InverseCumulativeDistribution(double p)" method in LogNormal class, just as it is in Normal class ?
Thanks again,
Vinny




