[R] qt with ncp>37.62

From: <data_at_tulipany.cz>
Date: Sat, 14 Jun 2008 22:44:02 +0200


help(qt) states that:
"ncp non-centrality parameter delta; currently except for rt(), only for abs(ncp) <= 37.62"

so I would expect that calling qt with non-centrality parameter exceeding 37.62 should fail, instead e.g. calling

> mapply(function(x) qt(p = 0.9, df = 55, ncp = x),35:45)

gives:

 [1] 40.21448 41.35293 42.49164 43.68862 44.82945 45.97048 47.11170 48.25310  [9] 49.39467 50.53639 51.67826
Warning messages:
1: In qt(p = 0.9, df = 55, ncp = x) :
  full precision was not achieved in 'pnt' 2: In qt(p = 0.9, df = 55, ncp = x) :
  full precision was not achieved in 'pnt' 3: In qt(p = 0.9, df = 55, ncp = x) :
  full precision was not achieved in 'pnt'

so it seems calculation for (according to what is written in documentation) allowed values of ncp, i.e. in this case 35,36 and 37 is done and precision is checked, whereas calculation for the rest may be completely incorrect? Or was there any update of code (in pnt.c ?), allowing calculation of pt with higher ncp, not followed by documentation update?

Thank you,
Nikola Kaspříková



R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Sat 14 Jun 2008 - 23:32:12 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Sun 15 Jun 2008 - 19:30:40 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive