We’ve all seen and heard ads that begin with grim statistics:
“Every 10 minutes a new name appears on the organ transplant waiting list.”
“If you’re a woman, you have a 1 in 8 lifetime risk of breast cancer.”
“If you’re a man, you have a 1 in 6 chance of developing prostate cancer during your lifetime.”

But these statistics may be overly dramatic and conceal important truths. Robert H. Shmerling, M.D., of the Beth Israel Deaconess Medical Center has identified four reasons such statistical claims should be viewed with caution.

1. The numbers are based on averages.
The statistic about transplant cases given above is the outcome a mathematical calculation, not a literal observation. There are 525,600 minutes in a year; divide that by the number of people added to the transplant list in a year (47,782 – 49,000 people), and you get the average.

While calculating a statistic for something like how often a name is added to a transplant list might not be strictly speaking correct, the average may still offer a fairly accurate descriptive picture of the phenomenon. This is not so for cases where risk is seasonal. Take, for example, childhood drownings in the United States. The average occurrence of this phenomenon will vastly underestimate the actual risk during summer months (when the majority of drownings occur) and overestimate the risk during winter months (when drownings are rare).

2. When a range of numbers is involved, the more dramatic figures are quoted.
In 1999, the Institute of Medicine estimated that “at least 44,000 people, and perhaps as many as 98,000 people, die in hospitals each year as a result of medical errors that could have been prevented.” This fact has been re-calculated as “1 patient dies every 5 ½ minutes from a medical error in the United States.” But this statistic is based on the larger number (98,000). Other sources that used this report rarely quoted the lower number.

3. Risk estimates may include insignificant cases.
Not all cases of a particular phenomenon ought to be treated equally. For example, some breast cancers are so insignificant or well-contained that they are not rightfully considered health risks. Yet, these cases are often included when lifetime risk estimates are calculated, thus inflating the average.

4. The numbers may not apply to you.
The lifetime risk of lung cancer in the United States is approximately 1 in 13. But this is not a blanket risk for everyone; if you control for smoking status (by a process called “stratification”), the lifetime risk for smokers vs. non-smokers is starkly different. One study found that the lifetime risk of lung cancer for non-smokers is actually about 1 in 333, while the lifetime risk for smokers was between 1 in 4 and 1 in 5 ½. It is important to take into account the population that is being studied in each research project; the more you’re similar to the population under scrutiny, the more likely the found statistic will apply to you. But lifetime risk calculations often conceal an individual’s actual risk, just like the cases-by-the-minutes statistics do.

Read more here.