(no answer)

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

(no answer)

Frank Harrell
I have never taken a statistics class nor read a statistics text, but
I am in dire need of help with a trivial data analysis problem for
which I need to write a report in two hours.  I have spent 10,000
hours of study in my field of expertise (high frequency noise-making
plant biology) but I've always thought that statistics is something
that can be mastered on short notice.

Briefly, I have an experiment in which a response variable is
repeatedly measured at 1-day intervals, except that after a plant
becomes sick, it is measured every three days.  We forgot to randomize
on one of the important variables (soil pH) and we forgot to measure
the soil pH.  Plants that begin to respond to treatment are harvested
and eaten (deep fried if they don't look so good), but we want to make
an inference about long-term responses.  In addition, we forgot to
measure the response on some of the days before the plant was
terminated.  Some baseline variables were not measured for some
plants, when some of the other variables looked OK.  The response
variable is only known to exceed a certain value in some cases, and in
others is only known to be less than a certain value.  The response
variable also has a great number of ties at zero, and has extreme high
outliers.  The variability of responses seems to depend on whether
there was missing variables for the plant.  And halfway through the
experiment we changed instrumentation and personnel.  All of these
problems seem trivial when compared to what I have to deal with every
day in measuring plant sounds, so I hope that someone can help me as
soon as possible.  I would appreciate receiving a few paragraphs of
description of the analysis that I can include in my report, and I
would like to receive R code to analyze the data no matter which
variables I collect.  I do value your time, so you will get my
everlasting thanks.


Note that I will be out of the office from 1:15pm to 1:25pm today.
This information should be valuable to many.

I. Ben Fuld
Technical University of Plant Kinetics
Slapout, Alabama

LEGAL NOTICE\ Unless expressly stated otherwise, this messag...{{dropped}}

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Frank Harrell
Department of Biostatistics, Vanderbilt University
Reply | Threaded
Open this post in threaded view
|

Re: (no answer)

Ted.Harding
On 01-Apr-06 Frank E Harrell Jr wrote:
> I have never taken a statistics class nor read a statistics text, but
> I am in dire need of help with a trivial data analysis problem for
> which I need to write a report in two hours.  I have spent 10,000
> hours of study in my field of expertise (high frequency noise-making
> plant biology) but I've always thought that statistics is something
> that can be mastered on short notice.

Dear Ibn Fuld (I apologise for rewriting your name correctly,
and I do appreciate the problems of people who do not natively
speak English, but I thought that doind so would be useful for
the members of the list who have the coverse problem),

You have an evidently complex problem there, but apparently a
very short time in which to solve it. Happily, I see a very
simple solution.

Just talk to your plants, ask them how they are, record their
acoustic responses, and use your existing expertise to analyse
and interpret the latter. I judge that you need to learn nothing
new to do this, your institution should posses the required
technology, and I suspect that little if any new R code would be
required.

Good luck,
ZB <[hidden email]>


> Briefly, I have an experiment in which a response variable is
> repeatedly measured at 1-day intervals, except that after a plant
> becomes sick, it is measured every three days.  We forgot to randomize
> on one of the important variables (soil pH) and we forgot to measure
> the soil pH.  Plants that begin to respond to treatment are harvested
> and eaten (deep fried if they don't look so good), but we want to make
> an inference about long-term responses.  In addition, we forgot to
> measure the response on some of the days before the plant was
> terminated.  Some baseline variables were not measured for some
> plants, when some of the other variables looked OK.  The response
> variable is only known to exceed a certain value in some cases, and in
> others is only known to be less than a certain value.  The response
> variable also has a great number of ties at zero, and has extreme high
> outliers.  The variability of responses seems to depend on whether
> there was missing variables for the plant.  And halfway through the
> experiment we changed instrumentation and personnel.  All of these
> problems seem trivial when compared to what I have to deal with every
> day in measuring plant sounds, so I hope that someone can help me as
> soon as possible.  I would appreciate receiving a few paragraphs of
> description of the analysis that I can include in my report, and I
> would like to receive R code to analyze the data no matter which
> variables I collect.  I do value your time, so you will get my
> everlasting thanks.
>
>
> Note that I will be out of the office from 1:15pm to 1:25pm today.
> This information should be valuable to many.
>
> I. Ben Fuld
> Technical University of Plant Kinetics
> Slapout, Alabama
>
> LEGAL NOTICE\ Unless expressly stated otherwise, this
> messag...{{dropped}}
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html

--------------------------------------------------------------------
E-Mail: (Ted Harding) <[hidden email]>
Fax-to-email: +44 (0)870 094 0861
Date: 01-Apr-06                                       Time: 15:44:50
------------------------------ XFMail ------------------------------

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

Re: (no answer)

Gabor Grothendieck
In reply to this post by Frank Harrell
Oh, and I forgot to add.  Please generate some test data for me since
I can't possibly take time out to provide such in order to clarify the
question.  By the way, I did try out R a bit but it did not work and its
too much effort to provide the R code I have or to reduce it to a small
self contained reproducible example to illustrate the salient point.

I am thanking you in advance since I will probably be too busy
to acknowledge the help or to summarize the answers for the
benefit of others and the list archives.  Its not that I don't want to
but I probably won't follow up on your answers anyways if they involve reading
and thinking about help pages, the manual, the FAQ, the posting guide,
statistics, mathematics, programming or other material.

By the way, please email me directly since I normally don't read
the list.

:)

On 4/1/06, Frank E Harrell Jr <[hidden email]> wrote:

> I have never taken a statistics class nor read a statistics text, but
> I am in dire need of help with a trivial data analysis problem for
> which I need to write a report in two hours.  I have spent 10,000
> hours of study in my field of expertise (high frequency noise-making
> plant biology) but I've always thought that statistics is something
> that can be mastered on short notice.
>
> Briefly, I have an experiment in which a response variable is
> repeatedly measured at 1-day intervals, except that after a plant
> becomes sick, it is measured every three days.  We forgot to randomize
> on one of the important variables (soil pH) and we forgot to measure
> the soil pH.  Plants that begin to respond to treatment are harvested
> and eaten (deep fried if they don't look so good), but we want to make
> an inference about long-term responses.  In addition, we forgot to
> measure the response on some of the days before the plant was
> terminated.  Some baseline variables were not measured for some
> plants, when some of the other variables looked OK.  The response
> variable is only known to exceed a certain value in some cases, and in
> others is only known to be less than a certain value.  The response
> variable also has a great number of ties at zero, and has extreme high
> outliers.  The variability of responses seems to depend on whether
> there was missing variables for the plant.  And halfway through the
> experiment we changed instrumentation and personnel.  All of these
> problems seem trivial when compared to what I have to deal with every
> day in measuring plant sounds, so I hope that someone can help me as
> soon as possible.  I would appreciate receiving a few paragraphs of
> description of the analysis that I can include in my report, and I
> would like to receive R code to analyze the data no matter which
> variables I collect.  I do value your time, so you will get my
> everlasting thanks.
>
>
> Note that I will be out of the office from 1:15pm to 1:25pm today.
> This information should be valuable to many.
>
> I. Ben Fuld
> Technical University of Plant Kinetics
> Slapout, Alabama
>
> LEGAL NOTICE\ Unless expressly stated otherwise, this messag...{{dropped}}
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html