Often, the small things make the biggest difference in life. Sometimes these things we do not recognize at first as big but as soon as we draw our attention to them, they become more important.

In analytical method validation, one of these small things is the so-called sum of squares or residual sum of squares (RSS). The (residual) sum of squares you will often find as a number in validation reports that, at first sight, might be of no interest at all. That is why, in this article, we will explain in more detail what this number actually means and why it is of importance. We will discuss its meaning and its importance, as well as the pros and cons and what can be done to avoid statistical pitfalls when using the RSS.

Microbiological methods are used in many applications in the pharmaceutical industry. Since it involves working with living organisms, various factors must be considered during an ongoing experiment. Many traditional methods have been established over the years and are listed universal methods in the pharmacopoeias. Considering the given requirements in the instruction their application doesn’t need a validation, only a verification is sufficient. Due to recent technological advancements, it is possible to use alternative methods developed by the laboratory or a company itself. To ensure the new method also demonstrably leads to correct results, a previous validation is must.

In every drug manufacturing process, controls are mandatory. Thinking about the patient, the goal should be to implement processes that are 100% error free, but that is practically impossible. For example, it is not feasible to unpack, check, and analyse every tablet from a batch to check that no mistake has been overlooked.

In any quantification method of a drug or its active ingredient, the linearity of the calibration line is a crucial criterion for the correctness of the values. The measured values should, in the best case, be directly proportional to the concentration of the analyte in the sample. Most methods have their limits; therefore, you often narrow the measurable range (linear range).