[R] Measurements of 3000 criminals

[(Ted Harding)]

On 28-Oct-06 Jean lobry wrote:
>>  Hallo everyone,
>>
>>  excuse me if this is not a genuine R question but I do not
>>  know where to ask else.
>>
>>  Referring  to e.g.
>>
>>  https://stat.ethz.ch/pipermail/r-help/2004-December/062114.html
>>
>>  I wonder if these measurements of 3000 criminals (raw data)
>>  are available anywhere. At least I didn't find them in the
>>  R datasets package or by means of Google. What I did find
>>  was a table of frequencies of the central values for *grouped*
>>  classifications (finger lenghts) in the Handbook of Small Data
>>  Sets.
>>
>>  Thank you in advance.
>>
>>  D. Trenkler
> 
> Dietrich,
> 
> I'm not sure, but this is perhaps what you want:
> 
> crim <-
> read.table("http://pbil.univ-lyon1.fr/R/donnees/criminals1902.txt")
> 
> For some R code playing with this dataset, open this (draft)
> document:
> 
> http://pbil.univ-lyon1.fr/members/lobry/R/convergencet.pdf
> 
> and jump to section 4.
> 
> HTH,
> 
> Jean

Following up Dietrich's original URL

https://stat.ethz.ch/pipermail/r-help/2004-December/062114.html

I find that the seed for this thread was originally planted
by myself!

If you go back to that posting, you will read in the quotation
from Student (1908):

  "Before I had succeeded in solving my problem analytically,
   I had endeavoured to do so empirically. The material used
   was a correlation table containing the height and left
   middle finger measurements of 3000 criminals, from a paper
   by W. R. Macdonnell (Biometrika, I, p. 219). ... "

[NB Typo: "Macdonnell" should be "Macdonell"; for "219" see
 below]

The crucial phrase is "correlation table", i.e. a 2-way table
of counts in intervals of one variable by intervals of another
variable.

On that basis, and having looked at Jean's PDF

http://pbil.univ-lyon1.fr/members/lobry/R/convergencet.pdf

the table on the 11th page thereof (Section 4) seems to be
a facsimile reproduction of the corresponding page in the
Biometrika article by Macdonell. (I do not have access at
the moment to the original Biometrika, so cannot verify this),
and that table gives the data as originally published by
Macdonell.

This is not, of course, the "raw data" which would have been
3000 records each with the measurements of each of the 3000
individuals.

But I think that it is as close as one can get!

The references to Student's and Macdonell's articles are
given in Jean's PDF, including the fact that the table in
question was found on Macdonell's p. 216, not 219.

Cross-checking Jean's data file

http://pbil.univ-lyon1.fr/R/donnees/criminals1902.txt

against the Macdonell reproduction shows that the counts
are the same, the left-hand margins (finger length in mm)
agree, and the top margins also agree on the basis that
the heights are given by Jean in cm corresponding to the
midpoints of Macdonell's intervals in feet/inches.

Thus where Macdonell has 4' 7"9/16 -- 8"9/16, Jean has
142.24 which is 2.54*56 = 2.54*(4' 8").

Hoping that this helps!
Ted.

--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861
Date: 28-Oct-06                                       Time: 13:55:28
------------------------------ XFMail ------------------------------