s-news
[Top] [All Lists]

Re: Visualising data by cleveland

To: Splus Mailing List <s-news@lists.biostat.wustl.edu>
Subject: Re: Visualising data by cleveland
From: "Austin, Matt" <maustin@amgen.com>
Date: Tue, 27 Jun 2006 07:56:59 -0700
Does anyone have any suggestions about books or papers on table design that
would be the equivalent of the books mentioned for graphics?  I have looked
at quite a few, but I have found that very few specifically discuss
describing large complex datasets in tables (such as from clinical trials).


Specifically, I have read Lang's "How to Report Statistics in Medicine" and
Few's "Show me the Numbers", but these seem to focus on simple single
statistic displays or re-displaying tables as in standard software.  What
I'm looking for is descriptions of the best way to arrange tables for
perception and interpretation. 

--Matt

Matt Austin
Statistician
Amgen, Inc
800 9AMGEN9 x77431
805-447-7431
"The purpose of computing is insight, not numbers" --Richard Hamming

  


-----Original Message-----
From: s-news-owner@lists.biostat.wustl.edu
[mailto:s-news-owner@lists.biostat.wustl.edu] On Behalf Of Spencer Graves
Sent: Monday, June 26, 2006 8:57 PM
To: Thompson, David (MNR)
Cc: Jonathan Dakin; Splus Mailing List
Subject: Re: [S] Visualising data by cleveland

          Are there script files for "The Elements of Graphing Data"?
Before I read David Thompson's email, I didn't know that scripts and data
for "Visualizing Data" were available.

          I agree with Frank that these are "awesome books", and I'd like to
explain briefly why I think so.

          For me, the the seminal contribution of "The Elements of Graphing
Data" is its chapter summarizing research in visual perception:  What can
you do in designing graphics so people get more information in less time?
The contents of this chapter have helped me, I believe, develop more
effective graphics.

          The graphics in the two books seem to be the foundations of
Trellis / Lattice graphics.  They do not discuss how to create the graphics
using S-Plus or R, only why those kinds of graphics are useful.  The data
and script files increase substantially the value of the book(s).  When I
read the books, I remember being frustrated by not knowing how to create the
graphics.  Thanks to David Thompson's email, I can now revisit "Visualizing
Data".

          Spencer Graves        

Thompson, David (MNR) wrote:
>> Frank E Harrell Jr wrote:
>>
>> Jonathan Dakin wrote:
>>> Could anyone comment on the relative merits of two of Cleveland's
> books: 
>>> "Elements of Graphing Data" (94), and "Visualising Data"  (93) ?
>>>
>>> I'm looking for fairly basic account of the principles of graphical 
>>> exploration, with particular reference to Splus, which is not too
> heavy
>>> on statistical theory.  My interest is medical data.  If the scripts
> and
>>> datasets used in either are publicly available that would be a big
> plus.
>>> Many thanks
>>> Jonathan Dakin
>> These are awesome books and everyone who looks at data should own them.
> 
>>  The Elements of Graphing Data book is the best how-to for scientific 
>> graphics.  There is a web site with scripts from the books although 
>> Cleveland used a few customizations.
>>
>> -- 
>> Frank E Harrell Jr   Professor and Chair           School of Medicine
>>                      Department of Biostatistics   Vanderbilt 
>> University
> 
> That scripts link (at least for Visualizing Data) is:
> http://cm.bell-labs.com/cm/ms/departments/sia/wsc/visualizing.datafig.
> ht
> ml
> 
> DaveT.
> **********************************************************
> Silviculture Data Analyst
> Ontario Forest Research Institute
> Ontario Ministry of Natural Resources
> Sault Ste. Marie, Ontario, Canada
> david.thompson@mnr.gov.on.ca
> **********************************************************
> --------------------------------------------------------------------
> This message was distributed by s-news@lists.biostat.wustl.edu.  To 
> unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with 
> the BODY of the message:  unsubscribe s-news
> 
--------------------------------------------------------------------
This message was distributed by s-news@lists.biostat.wustl.edu.  To
unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with the
BODY of the message:  unsubscribe s-news

<Prev in Thread] Current Thread [Next in Thread>