Information Quality

8Healthcare

8.1 Introduction

Many physicians, patients, health journalists, and politicians do not understand health statistics. Unfortunately, the statistics community makes little effort to educate the public or healthcare providers in understanding health statistics. This collective issue in statistical illiteracy has resulted in serious consequences for health. We list in the following text a few examples described in more detail in Gigerenzer et al. (2007). See also Kenett (2012).

The British Committee on Safety of Medicines issued a warning that the third‐generation oral contraceptive pill increased the risk of a thrombosis twofold—that is, by 100%. This caused great anxiety among women taking the pill, many of whom stopped using it. The studies on which the warning was based showed that among every 7000 women who took the previous generation pill, one had a thrombosis and that this number increased to two for women who took the third‐generation pill. The relative risk increase was indeed 100%, but the absolute risk increase was one in 7000. The pill scare led to an estimated 13 000 abortions in the following year in England and Wales, resulting in a cost increase for the National Health Service estimated at about £4–6 million. The scare was due to the low level of information quality (InfoQ) contained in the official warning. A report of absolute increase would have had higher InfoQ, with a lower level of generated panic.

A second example comes from a study of 150 gynecologists, ...