Analyzes dose responses for two populations, using the PROBIT model and the abbreviated protocol as described by Link et al(1996).
Link, W. A. E. F. Hill J. E. Hines and P. F. P. Henry. A Resource
Conservative Procedure for Comparison of Dose-Response Relationships.
Environmental Toxicology and Chemistry. 1996; 15(9):1612-1617.
Abstract
The evaluation of effect of toxicants on a wildlife community can be complicated by varying responses among the
community's constituent populations. Even within populations, considerable variability in dose-response relations may result from
different avenues of exposure to the toxicant. Full-scale investigations of the dose-response relations among a variety of species and
avenues of exposure can therefore be prohibitively expensive, whether this expense is measured by the number of experimental animals
needed, by the human resources committed to the study, or by the laboratory expenses. We propose an abbreviated protocol for investigations
of multiple dose-response relations that is designed to limit these expenses. The protocol begins with the judicious chouce of a baseline
dose-response relation to be estimated by a full-scale study involving a minimum of five doses levels, with 10 subjects per dose level.
This relation is then used as the basis for rapid screening of subsequent dose-response relations, which are compared th the baseline
to the estimated median lethal concentration fro the baseline study. We describe MS-DOS-compatible software available from the
authors that can be used to analyze these data.
Keywords
Cyanide, Dose-response, ED50, Probit, Toxicity
Data required are the number of responses ("deaths") and the
sample size ("subjects") at each of a variety of level of doses. NOTE: Dose
levels must be entered according to the scale on which the analysis is
performed (e.g., log-transformed).
Data for the first population is referred to as "baseline" data.
The program is designed to allow for a preliminary analysis of these data,
which is used for choosing dose levels and sample sizes for the experiment on
the other population ("secondary" data). If desired, p-values for results of
a secondary study involving "m" animals at the estimated baseline ED50 can be
calculated as part of the baseline analysis.
If the secondary data are obtained at a variety of dose levels, the
user is given the option of testing the assumption of equal slopes of the dose
response curve. If the secondary data are obtained at a single dose level
(typically the ED50 arising from the baseline study), it is necessary to assume
that the slopes of the two dose response curves are equal.
If the baseline data indicate poor model fit (likelihood ratio
statistic significant at alpha = 0.10) a heterogeneity factor is used in
subsequent tests of significance.