The Effect of Statistical Error Model Formulation on the Fit and Selection of Mathematical Models of Tumor Growth for Small Sample Sizes

When fitting a mathematical model to a given data set using inverse problems, the correctness of both the mathematical model and the statistical error models are important since an incorrect statistical or observational model directly affects both the estimates and their corresponding standard errors.The effects of these models, among many other factors, are dependent on the sample size and the information content of the data set.In this article, we investigate how the choice of the statistical error model affects the mathematical model fit and accuracy of parameter estimates in small sample size tumor growth data sets.We specifically seek to determine the appropriate statistical error model for small sample size breast, lung and HPV tumor growth data sets obtained from studies on mice.