Premium
Alternative Models for Correlating Toxic Effects
Author(s) -
Verducci J. S.
Publication year - 1987
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710290511
Subject(s) - correlation , class (philosophy) , mathematics , carcinogenesis , population , econometrics , statistics , computer science , biology , cancer , artificial intelligence , medicine , genetics , geometry , environmental health
Two very different types of correlation are examined. First, the problem of correlating two different toxic potentials, such as mutagenesis and carcinogenesis, over a class of chemicals is discussed and shown to be quite difficult unless strong assumptions are made about the dose‐response curves for each effect. The second type of correlation is that of joint occurrences of symptoms over a population of subjects. A latent class model whose parameters are linear functions of dosage is proposed based on a two‐stage theory of carcinogenesis. This model surpasses various alternative models in predicting multiple site tumors resulting from exposure to the solvent 1,3‐butadiene.