Re: Find a distribution!

From: Lurker (spamkill_at_spamkill.co.uk)
Date: 10/15/04 

Date: Fri, 15 Oct 2004 09:03:02 +0100

"LWn" <lars.wahlgren.pleasenospam@stat.lu.se> wrote in message
news:7bzbd.106157$dP1.396840@newsc.telia.net...
>
> "viktor eriksson" <viktor_eriksson@hotmail.com> skrev i meddelandet
> news:j1oesizgn9c5@legacy...
> > I am working on a project at a company in Sweden where the amount of
> > bacterias in food are simulated in Excel. The problem is to find a
god
> > distribution to my strange indata:
> >
> > minimum: 0.04.
> > mean: 0.04
> > maximum:1 000 000
> >
> > What kind of distribution is best adapted to this strange (and
> > impossible) indata? I think you have to choose a mean value that is
a
> > bit bigger than 0.04 but what kind of distributionh is that, and how
> > can I use it in Excel to find samples?
>
> The exponential and the gamma distribution I think can give you quit
> skewed distributions. I don't remember about the parameters but
> "trial and error" might give you some hints to get it positively
skewed.
>
> hth / LWn
>
>
Tried to post this yesterday, but I didn't see it arrive.
This time I'm cross-posting to the food-science and
microbiology groups.
===============
Sorry about the anonymous post, it has to be!

1) Microbiological concentrations are often modelled by a
   logNormal distribution.

2) Microbiological concentration are often measured by
    counting organisms in small amounts of material. Beware
   of the "censoring" this can introduce. e.g. 0.04 cfu/g
   may correspond to 1 cfu in 25 g. If this is a pathogenic
   organism I would suspect that "mean 0:04" means the
   vast majority of samples resulted in a count of zero. It
  is possible to make inferences from censored data, but
  the techniques are not elementary, I wouldn't try in Excel.

3) If you're looking at pathogens in food it may be that you
    need different distributions for "contaminated" and
   "non-contaminated" foods. It is likely that contamination
   occurs by "discontinuous" processes.

4) You should not base risk management on any kind of
   statistical model; you cannot get the required confidence.
   Risk management should be based on understanding the
   ways in which the hazard arises and blocking them, by
  a structured approach such as HACCP.

5) If you are assessing risk, rather than managing it, you
  should look at the huge volume of prior art. I suggest
  starting at http://www.foodriskclearinghouse.umd.edu/

6) All except the most recent versions of Excel gave
   wrong results when calculating distributions in the tails.
   (Recent version may have improved, I don't know).

HTH

A lurker

Relevant Pages

  • Find a distribution!
    ... bacterias in food are simulated in Excel. ... distribution to my strange indata: ... What kind of distribution is best adapted to this strange (and ...
    (sci.stat.math)
  • Find a distribution!
    ... bacterias in food are simulated in Excel. ... distribution to my strange indata: ... What kind of distribution is best adapted to this strange (and ...
    (sci.stat.math)
  • Re: Problem with Data Subtotals
    ... Dave Peterson wrote: ... Multilevel subtotals are in the wrong position in Excel 2002 and in Excel 2003 ... Hours, Amount and State. ...
    (microsoft.public.excel)
  • Re: Autocreating probability distribution
    ... this functionality is not built into Excel. ... In the case of the Normal distribution, the NORMDIST function takes its mean ... and standard deviation as arguments. ... Excel probability functions are not consistent as to whether they calculate ...
    (microsoft.public.excel)
  • Re: Continuity correction.
    ... Actually for Excel 2003 and 2007, NORMSDIST is accurate from z values ... MIcrosoft viewed Excel as a business tool. ... marketing advantage to add to Excel's stat capabilities. ... The t distribution only as a test, not a visual concept of the ...
    (sci.stat.math)