Lies, Damn Lies, and Statistics

Not long ago, a biostatistics colleague of mine told me an interesting story. She was working with a (now former) collaborator to analyze some clinical data that had some limitations (small sample size, inadequate power, large variability in the primary outcome). After a brief discussion, he said to her: “I don’t care what statistical test we use; I just need the one that’ll show my results are significant.” This comment was probably met with a heavy sigh, eye roll, and/or fit of rage.

There are a lot of misperceptions about statistics and data interpretation. For those of you with an interest in numbers, statistics, and what they all mean, this paper highlights and clarifies some common statistical misperceptions in medical and health research.


2 thoughts on “Lies, Damn Lies, and Statistics

  1. Did your colleague mean “I just need the one that’ll show the WANTED results are significant”… That would be really difficult for some cases..

    • Exactly! He didn’t care about what test he used; he just wanted to use whatever test was needed to confirm the result he wanted to show. It was a good example of someone wanting/trying to manipulate the statistics to satisfy his own needs rather than being true to the scientific process and letting the best possible analyses determine whether his findings were significant or not. In my experience, this doesn’t appear to be all that common.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s