NONMEM Users Network Archive

Hosted by Cognigen

Re: Statistical power computation based on the wald test

From: Ayyappa Chaturvedula <ayyappach>
Date: Mon, 22 Mar 2021 11:01:47 -0500

This is a related article using Monte Carlo Power Mapping (MCPM) that I rece=
ntly used. It is time efficient and takes the spirit of simulation and LLR t=
est.

Vong C, Bergstrand M, Nyberg J, Karlsson MO. Rapid sample size calculations f=
or a defined likelihood ratio test-based power in mixed-effects models. AAPS=
 J. 2012 Jun;14(2):176-86. doi: 10.1208/s12248-012-9327-8. Epub 2012 Feb 17.=
 PMID: 22350626; PMCID: PMC3326172.

https://pubmed.ncbi.nlm.nih.gov/22350626/


Regards,
Ayyappa

> On Mar 22, 2021, at 9:41 AM, Ken Kowalski <kgkowalski58
>
> 
> Hi Ibtihel,
>
> I think you are probably asking for covariance matrix of the parameter est=
imates. This should automatically be outputted as the .cov file assuming th=
at the $COV step runs successfully. Note that since NONMEM minimizes a func=
tion related to -2LL, the Hessian (R matrix) in NONMEM is equivalent to Fish=
er’s Informaton matrix. I know you can print the R matrix in the NO=
NMEM output and I assume this can also be outputted to a file…perhap=
s others might know
>
> I’ll leave it for you to decide whether you really want to perform=
 power calculations say to design/justify a sample size to detect the covari=
ate effect using a Wald-based test as opposed to performing simulations and r=
elying on a likelihood ratio test.
>
> Ken
>
> Kenneth G. Kowalski
> Kowalski PMetrics Consulting, LLC
> Email: kgkowalski58
> Cell: 248-207-5082
>
>
>
> From: owner-nmusers
n Behalf Of Hammami, Ibtihel /FR
> Sent: Monday, March 22, 2021 9:22 AM
> To: nmusers
> Subject: [NMusers] Statistical power computation based on the wald test
>
> Hi,
> We would like to compute a covariate inclusion statistical power based on=
 the Wald test and using SE given by the fisher information matrix.
> Is there any method to implement this directly in NONMEM or is there at le=
ast a way to output the Fisher Information matrix in NONMEM?
>
> Thank you.
>
>
> Virus-free. www.avast.com

Received on Mon Mar 22 2021 - 12:01:47 EDT

The NONMEM Users Network is maintained by ICON plc. Requests to subscribe to the network should be sent to: nmusers-request@iconplc.com.

Once subscribed, you may contribute to the discussion by emailing: nmusers@globomaxnm.com.