nag_deviates_studentized_range (g01fmc) returns the deviate associated with the lower tail probability of the distribution of the Studentized range statistic.
The externally Studentized range,
, for a sample,
, is defined as
where
is an independent estimate of the standard error of the
. The most common use of this statistic is in the testing of means from a balanced design. In this case for a set of group means,
, the Studentized range statistic is defined to be the difference between the largest and smallest means,
and
, divided by the square root of the mean-square experimental error,
, over the number of observations in each group,
, i.e.,
The Studentized range statistic can be used as part of a multiple comparisons procedure such as the Newman–Keuls procedure or Duncan's multiple range test (see
Montgomery (1984) and
Winer (1970)).
For a Studentized range statistic the probability integral,
, for
degrees of freedom and
groups, can be written as:
where
For a given probability
, the deviate
is found as the solution to the equation
using
a root-finding procedure.
Initial estimates are found using the approximation given in
Lund and Lund (1983) and a simple search procedure.
Lund R E and Lund J R (1983) Algorithm AS 190: probabilities and upper quartiles for the studentized range Appl. Statist. 32(2) 204–210
The returned solution,
, to equation
(1) is determined so that at least one of the following criteria apply.
(a) |
|
(b) |
. |
Not applicable.
To obtain the factors for Duncan's multiple-range test, equation
(1) has to be solved for
, where
, so on input
p should be set to
.