link.pA, link.pB: Link functions applied to pA and pB. See Links for more choices.
ipA, ipB, ipO: Optional initial value for pA and pB and pO. A NULL value means values are computed internally.
zero: Details at CommonVGAMffArguments.
Details
The parameters pA and pB are probabilities, so that pO=1-pA-pB is the third probability. The probabilities pA and pB correspond to A and B respectively, so that pO is the probability for O. It is easier to make use of initial values for pO than for pB. In documentation elsewhere I sometimes use pA=p, pB=q, pO=r.
Returns
An object of class "vglmff" (see vglmff-class). The object is used by modelling functions such as vglm
and vgam.
References
Lange, K. (2002). Mathematical and Statistical Methods for Genetic Analysis, 2nd ed. New York: Springer-Verlag.
Author(s)
T. W. Yee
Note
The input can be a 4-column matrix of counts, where the columns are A, B, AB, O (in order). Alternatively, the input can be a 4-column matrix of proportions (so each row adds to 1) and the weights
argument is used to specify the total number of counts for each row.
See Also
AA.Aa.aa, AB.Ab.aB.ab, A1A2A3, MNSs.
Examples
ymat <- cbind(A =725, B =258, AB =72, O =1073)# Order matters, not the namefit <- vglm(ymat ~1, ABO(link.pA ="identitylink", link.pB ="identitylink"), trace =TRUE, crit ="coef")coef(fit, matrix =TRUE)Coef(fit)# Estimated pA and pBrbind(ymat, sum(ymat)* fitted(fit))sqrt(diag(vcov(fit)))