[R] Fitting a distribution to peaks in histogram

Charles C. Berry cberry at tajo.ucsd.edu
Thu Jul 20 19:03:27 CEST 2006

On Wed, 19 Jul 2006, Ulrik Stervbo wrote:

[much deleted]

> I am measureing the amount of DNA in cells, and I need to know the
> percentage of cells in a part of the cell cycle; that the percentage
> of cells in the first peak, in the second peak and so on. I want to
> integrate the area between to two cells, because that apparently is
> how its none (as far as I can tell from the literature)

I do not doubt that that is how some do it, but a better approach is takes 
account of errors in the values used to form the histogram.

This is reviewed in

T. Lynn Eudey
Statistical Considerations in DNA Flow Cytometry
Statistical Science 1996, Vol. 11, No. 4, 320{334

A classic approach for this purpose is

John Mendelsohn; John Rice
Deconvolution of Microfluorometric Histograms with B Splines
Journal of the American Statistical Association. Vol. 77, No. 380, 1982.

A FORTRAN program is mentioned there and the authors say that they will 
provide listings on request (but that WAS a long time ago).

I don't know if this was ever implemented in S/R, but an email to 
Professor John Rice (UC Berkeley Dept of Stats) might help.



Charles C. Berry                        (858) 534-2098
                                          Dept of Family/Preventive Medicine
E mailto:cberry at tajo.ucsd.edu	         UC San Diego
http://biostat.ucsd.edu/~cberry/         La Jolla, San Diego 92093-0717

More information about the R-help mailing list