Argument is not supported by the data
Law and Wald base their argument against thresholds on a set of
graphs of dose-response relationships, which they tell us exclude a
threshold within the range of population values. A closer look at the
graphs makes this hard to believe.
In the text we are told that 'the 95% confidence intervals about the
risk estimates exclude a threshold within the population range of values,
so that the lower the risk factor the lower the risk: no part of the dose-
response relation would fit a horizontal line'. This seems to be true only
of the relationship between diastolic blood pressure and ischaemic heart
disease or stroke, and between serum cholesterol and ischaemic heart
disease. In the other four pairs of graphs, the confidence intervals for
the two points at lowest risk overlap. In other words, the data seem to be
consistent with a threshold somewhere between the two lowest points shown.
Competing interests: No competing interests