Imperfect data

Let’s say you’ve built a great data extraction form and your team is using it to collect information from a pile of research studies. But before too long, one of your data extractors encounters a problem.

Remember this example from earlier in the course?

Data for the 40 patients who were given all 4 doses of medications were considered evaluable for efficacy and safety. The overall study population consisted of 10 (44%) men and 24 (56%) women, with a racial composition of 38 (88%) whites and 5 (12%) blacks.

This paragraph says there were 40 patients in the study, but if you look at the demographic data, the numbers don’t add up:

10 Men + 24 Women = 34 PatientsMaybe some of the patients didn’t identify as male or female? But that still doesn’t explain why data about the racial background of the patients adds up to more than the total:

38 white patients + 5 black patients = 43 patients

So, what should you enter in your extraction form? Were there 40, 34, or 43 patients in the study?