Jump to content


Photo
- - - - -

Q&A from session about nonlinear elimination model and bootstrap

nonlinear elimination bootstrap

  • Please log in to reply
No replies to this topic

#1 bwendt@certara.com

bwendt@certara.com

    Advanced Member

  • Administrators
  • 282 posts

Posted 24 May 2018 - 12:41 PM

Q: What is next step if the number of tries in bootstrap fails. Does this mean the model is not correct?

A: If a sample fails to converge, it is re-tried as many times as indicated in the box next to 'max tries' under Run Options. This is applied in an effort to get a full set of samples evaluated. If a particular sample fails all the retries it is excluded from statistical analysis. The failure is due to the data generated. If failures do not happen frequently ( e.g. in less than 5% of the replicates) it is less of a concern. But if it is more than that you would need to investigate.

Q: How to perform Monte Carlo simulation in Phoenix ?

A: There is a run mode Simulation/Visual Predictive Check that performs Monte Carlo simulations . The simulation is based on the results from your final population model and will generate replicates. It creates new data sets just like the original and samples both the random effects (omega) and observation errors (epsilon). 

Simulations will be the topic of another PML School webinar session: 

https://support.cert...ation-with-vpc/







Also tagged with one or more of these keywords: nonlinear elimination, bootstrap

0 user(s) are reading this topic

0 members, 0 guests, 0 anonymous users