Facts are stubborn things, but statistics are pliable. – Mark Twain

Most people use statistics like a drunk man uses a lamppost; more for support than illumination. – Andrew Lang

If your experiment needs a statistician, you need a better experiment. – Ernest Rutherford

There are things we know we know, there are things we know we don’t know, and then there are things we don’t know we don’t know. – Donald Rumsfeld

There are three types of lies – lies, damn lies, and statistics. – Benjamin Disraeli

Despite these famous quotes, statistics are a major factor in the success of bringing a medical product to the market and the topic for today’s blog.

A pile of numbers is not very useful until they reveal a pattern, show a trend, tell a story, or make a prediction. The process that drives these outcomes is statistics. Depending on your level of interest and sophistication, the definitions of statistics have ranged from “the science of counting” to “a branch of applied mathematics that involves the collection, description, analysis, and inference of conclusions from quantitative data.”

In the Stability function, we have a number of opportunities to employ statistics, whether that be determining a shelf life, investigating out-of-specification/trend/expectation results, or validating a testing process. In all cases, statistics help us to tell a story, prove or disprove an expectation and offer evidence to regulatory authorities. A trained statistician has the skills to apply statistics to achieve these outcomes and are vital partners with stabilitarians. In that light, it becomes our duty to know about statistical requirements (such as ICH Q1E Evaluation of Stability Data) statistical tools, statistical best practices, and the role of our statistics colleagues.

What avenues of learning will you and your staff pursue to become knowledgeable participants in employing statistics for the cause of stability?

Share This Article with the Stability Community!