I enjoyed reading a communication by Prof. Joseph E. Lucas and Prof. Guillermo Sapiro about the conclusions that can be drawn from a research paper by Cristian Tomasetti and Bert Vogelstein.
You can read the "comment" HERE
I think we have here an example of at least two assumptions that might be misleading in statistical data analysis:
a) how "population averages" translate into individual "cases". Several different individual "configurations" may give the same "average".
b) consider that (process) variables are independent among them, and therefore if some have an effect-result on others, simply infer that the others do not have a "statistically significant" similar effect ("Environment" and "Genetics" in the "Number of stem cell divisions", Figure 1, in this paper).