Statistics tell us passing a PQ is not easy!
In validation we’re providing objective evidence the process is capable of successfully making the product consistently.
3 consecutive lots have typically been used to demonstrate this (although FDA does not specify a required number of lots and it is up to the manufacturer to justify.)
For key characteristics the capability is typically justified in statistical confidence and reliability. For example, 95% confidence / 97% reliability means we want to be 95% confident that greater than or equal to 97% of units made by the process meet the specification.
Although the statistical confidence & reliability apply to the manufacturing PROCESS, very often the sample size and acceptance criterion is applied per LOT. In that case, if 3 consecutive lots are made, what is the probability of passing the study?
Assuming an attribute quality characteristic and accept on zero failures criterion (a=0), the (binomial) probability of passing all 3 lots is shown in the figure below.
As can be seen, having a successful process validation is NOT easy!
To have a reasonable chance at passing the study, the actual process % defective must be MUCH LOWER (<1/20th) than would be indicated by the reliability!
Fortunately, there ARE ways of boosting the odds in our favor.
More in a future post...