[R] Fitting of lognormal distribution to lower tail experimental data

[David Winsemius]

On Jan 16, 2009, at 3:39 AM, Mattias Brännström wrote:

> Hi,
>
> I am beginner with R and need firm guidance with my problem. I have  
> seen
> some other threads discussing the subject of right censored data,  
> but I am
> not sure whether or not this problem can be regarded as such.
>
> Data:
> I have a vector with laboratory test data (strength of wood specimens,
> example attached as txt-file). This data is the full sample. It is a
> common view that this kind of data follows a lognormal distribution.

But it's not in this case. See attached summary and QQ plots.

 > wood <- read.table("C30.txt")
 > str(wood)
'data.frame':	697 obs. of  1 variable:
  $ V1: num  14.8 16.1 17.5 20.1 21.7 ...
 > summary(wood)
        V1
  Min.   :14.81
  1st Qu.:39.45
  Median :45.92    # median is suspiciously close to the mean
  Mean   :45.80
  3rd Qu.:52.41    # hinges also symmetric
  Max.   :75.70

 > qqnorm(log(wood$V1))


-------------- next part --------------
A non-text attachment was scrubbed...
Name: qqnorm-log-trans.pdf
Type: application/pdf
Size: 151096 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20090116/1d8668d7/attachment-0004.pdf>
-------------- next part --------------



 >
 > qqnorm(wood$V1)
-------------- next part --------------
A non-text attachment was scrubbed...
Name: qqnorm-untrans.pdf
Type: application/pdf
Size: 168521 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20090116/1d8668d7/attachment-0005.pdf>
-------------- next part --------------


The tails do not appear to be systematically different either, so it  
looks like both premises of the analysis are not found in this data.

-- 
David Winsemius
>
>
> Background:
> When fitting a distribution to the lower tail, it will usually be very
> different compared to fitting the whole data. The lower tail COV is  
> the
> decisive measure in my analysis (due to resistance estimations of
> buildings).
>
> Problem:
> I would like to fit a lognormal distribution to the 10%-lower tail  
> of the
> attached data.
>
> Question:
> Which function would you recommend me to use, and how to formulate  
> it in R
> using the attached data?
>
>
> Best regards,
> Mattias Brännström
>
> PhD student
> Luleå Technical  
> University<C30.txt>______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.