[R] Fitting a batch of histograms

Timur Elzhov etv at nf.jinr.ru
Mon Jul 1 17:00:06 CEST 2002

On Mon, 1 Jul 2002, Liaw, Andy wrote:

> Can you clarify what you mean by "fitting a histogram"?  To me a histogram
> is simply a summary of the data (frequencies in equally spaced bins), and
> hardly involves any fitting with parameters.

Well.  I'll try to describe my raw data file.
That is muon-decay (lifetime tau = 2.2 mks) spectrum, counts (N) vs. time
(t), with fixed time bin width = 0.000625 mks.  So, this spectrum N(t) I
call either as histogram, i.e., one _raw_ data file _initially_ consists
one time-histogram N(t).

Next, while muon decays, it emits positrons in _all_ directions, so
usually _several_ positron telescopes around muon site used (to have more
statistics, you know), so, we have _several_ data files after each

All spectra I fit with N(t) ~ exp(-t/tau) * (1 + P(t)) function,
i.e., I would be happy to find the appropriate P(t) function.
P(t) often found as

  P(t) = p1 * exp(-p2*t) * cos(p3*t + p4).

So!  I'd like to fit all spectra with this formula, with, say, p2 and p3
parameters being equal for each spectrum from corresponding telescope.

Thank you!


r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list