Datasets for Statistical Analysis

Mutagenicity assay

Keywords:

Ames test; salmonella

Categories:

science;
generalized linear models

Description:

The data give the number of revertant colonies (colonies that revert to their former gentype) for various doses of quinoline for TA98 Salmonella.

There are 18 observations on two variables.

Variables:

Dose	The dose of quinoline
Colonies	The number of revertant colonies

Data Quality:

There are no missing values.

Source:

Margolin, Barry H, Kim, Byung Soo an Risko, Kenneth J (1989). The Ames Salmonella/Microsome Mutegenicity Assay: issues of inference and validation, in Journal of the American Statisical Association, 84(407), p 651–661.

Notes:

• The given data represent only on replicate of the three given in Margolin, Kim and Risko (1984), but are as given in Breslow (1989).
• Three plates were used for each dose, hence the three observations per dose.
• The data are given in order of increasing numbers of colonies.
• Theory suggests one model for the data is Count = T[ 1 – exp( a – bx)]exp(-cx), for b and c greater than or equal to zero, where x is the dose of quinline, A good approximation to this is the log-linear model log(Count) = A + B log( x + C) - Dx.

References:

• Breslow, N. E. (1984). Extra-Poisson variation in log-linear models, in Applied Statistics, 33(1), pp 38–44
• Margolin, B. H., kaplan, N. and Zeiger, E. (1981). Statistical analysis of the Ames Salmonella/microsome test. Proceedings of the National Academy of Science USA, 76, 3779–3783.