229527_en-US

liliconcom

Stability Regression Analysis - Analyzing multiple parameters at the same time

 

When performing stability regression analysis  (Analyze/Reliability and Survival/Degradation – than Stability test), to the field  "Y, Response" it is possible to add only one parameter.

It will be great to have option for analyzing multiple parameters at same time (like in Capability analysis)?

Sometimes there is  a lot parameters to be analyzed during stability check .

 

 

 

Statistics and AnalyticsRe: Stability Regression Analysis - Analyzing multiple parameters at the same time

These are all good suggestions! And, while we are there, it may be time to include an option to use the MSE (as required, correctly, by the FDA in ICH Q1E, https://www.fda.gov/regulatory-information/search-fda-guidance-documents/q1e-evaluation-stability-data) from the ANCOVA model, rather than performing a separate regression for each batch, when there is (for example) a batch*time interaction.  

More here: Question about Stability Analysis (ANCOVA) and the pooled MSE 

Re: Stability Regression Analysis - Analyzing multiple parameters at the same time

Thanks!

Re: Stability Regression Analysis - Analyzing multiple parameters at the same time

Another good reference for accelerated stability testing in Pharma is Accelerated Predictive Stability, Academic Press, Qiu, Scrivens (Editors), and it describes many of the commonly used models for APS.  

Re: Stability Regression Analysis - Analyzing multiple parameters at the same time

Building on this comment, it would be very useful to have a platform for building a combined model across temperatures for accelerated stability studies of pharmaceutical products. This challenge is described in the paper "Pharmaceutical solid-state kinetic stability investigation by using moisture-modified Arrhenius equation and JMP statistical software" by Fu et al. in the Journal of Pharmaceutical and Biomedical Analysis 2015, pp 370-377. There is a commercial software ASAP Prime available but I would like to be able to do this in JMP.

Re: Stability Regression Analysis - Analyzing multiple parameters at the same time

This is a good suggestion.  

 

I would add that this platform could use a good general overhaul, to make it more useful for those in the pharmaceutical industry.   

- Add a methodology to aid in determining internal release limits (see, for example, http://files.pharmtech.com/alfresco_images/pharma/2018/10/17/b1a79f86-0961-4d14-b285-97bd1ecf6680/PT1018_PeerReview.pdf) 

- Improve the "non-linear path" modeling to allow easier analysis of accelerated stability studies

- Clean-up the layout of the report, make it into a more directly "printable" layout that can be used for standardized reporting

- Add ability to flag out-of-specification (OOS) and out-of-trend (OOT) signals in stability data (for example, http://www.pharmtech.com/methods-identifying-out-trend-results-ongoing-stability-data)