Would you re-test liraglutide after ten weeks at 25 °C, or accept the original certificate?

For reference: liraglutide · ten weeks · 25 °C.

I would like to define my thresholds before I have a result, for obvious reasons.

I want a plan with explicit stopping rules, not just steps.

What is the minimum version of this that is still defensible?

It helps to be literal here: sampling plans exist precisely because testing everything is expensive, and they define the statistical relationship between sample size and lot-wide inference.

Acceptance Sampling by Attributes defines the number of samples you need from a lot to claim a specified quality level at a specified risk — it is in ANSI standard Z1.4.

Stratified sampling — testing one vial from the top, one from the middle, and one from the bottom of a shipment — is cheap insurance against segregation.

Lyophilised peptide homogeneity studies show that vial-to-vial variation is usually small but occasionally large, depending on the distribution in the freeze-dryer.

The practical summary: a lot number without a sampling statement is a lot number without meaning.

Start from the question: how many vials from this lot do I need to test to claim that the lot meets specification, and the answer depends on both the lot size and the acceptable risk.

If you have reason to suspect inhomogeneity — different appearance in different vials, or a long or warm shipment — testing more vials is the diagnostic move.

It helps to be literal here: for a quantitative result like content, the acceptable range determines how many vials you need to test to establish the lot complies.

Published data on lot homogeneity from manufacturers who sample multiple vials consistently find variation below the published specifications, suggesting the sampling plans work.

I would treat a "complies with" statement without sampling details as a claim rather than as evidence.

Assume segregation is possible, and design your sampling to catch it if it exists.

Concretely, most suppliers test one vial per lot and report the result as lot homogeneity, which is sampling one item from one lot and extrapolating wildly.

The statistical foundation here is well-established, which is why sampling plans from decades ago are still valid.

If the lot was manufactured in multiple batches, testing vials from each batch separately establishes whether batch-to-batch variation is acceptable.

Sampling plans for pharmaceutical manufacturing are defined in ISO 2859 and ANSI Z1.4, and they are based on statistical sampling theory.

If testing multiple vials, state how many you tested and why you chose those vials.

Stated carefully, the failure mode here is publishing a result that applies to the tested vial alone while implying it applies to the entire lot.

Under AQL sampling plans, testing two vials from a fifty-vial lot gives you an operating characteristic curve that tells you what risks you are accepting.

Lyophilised peptide homogeneity studies show that vial-to-vial variation is usually small but occasionally large, depending on the distribution in the freeze-dryer.

One qualification: testing more vials gives better confidence, but at some point the cost outweighs the benefit.

The practical summary: a lot number without a sampling statement is a lot number without meaning.

Worth being precise here: the practical consequence is that spot-testing one vial from a new supplier is better than assuming they are all the same.

The sample size determination requires choosing a confidence level and an acceptable error rate, and the smaller the error rate you want, the larger your sample must be.

The caveat is that sampling is a trade-off between cost and confidence, and neither test nor assumption is cost-free.

Assume segregation is possible, and design your sampling to catch it if it exists.