NONMEM Users Network Archive

Hosted by Cognigen

RE: forest plots in Xpose?

From: Lindauer, Andreas <Andreas.Lindauer>
Date: Thu, 17 Sep 2015 08:55:10 +0200

Dear all,

Folks at Metrum published some R-code on how to generate these kind of covariate plots, including uncertainty of the effect size from a bootstrap:

Here is also a very nice presentation from Marc Gastonguay about this topic:

Regards, Andreas.

From: owner-nmusers -nmusers
Sent: Thursday, September 17, 2015 02:09
To: Pascal Girard <pascal.girard
Cc: nmusers
Subject: Re: [NMusers] forest plots in Xpose?

dear Pascal,

there seem to be copies of that library e.g. here ( and here ( You should be able to download from there and install from the local zip file. I don't know this library, so I'm not sure if it still works with current version of Xpose. I also don't know of a different module that creates these plots, but with the dplyr and ggplot2 libraries it shouldn't be more than 5-10 lines of code to create such a plot.

On a sidenote, I'm not a fan of the term "Forest plot" for these plots. The "original" Forest plots show data across multiple studies (e.g. in a meta-analysis), so calling it "Forest plot" could lead to confusion with statisticians or clinicians. A more important reason, however, is that it is not immediately clear what is actually shown in the plot. Various covariate data can be summarized using the "Forest plot style", such as:

- uncertainty in covariate effect size (e.g. obtained from covariance step, bootstrap, or posterior distribution from MCMC)
- inter-individual variability in covariate effect (distribution of observed covariate values * covariate effect size)
- time-variance of the covariate effects
- a combination of 1 and 2?

So a covariate "Forest" covariate-plot should always be accompanied with a description of what data is actually shown.
BTW, I think all of the above plots have utility in some way, either in diagnosis, data checkout, or communicating modeling results. Would be great if someone implemented an R package that could do all of the above :) I assume the popPK package makes type 2, but it is not mentioned in the manual.

best regards,

On Wed, Sep 16, 2015 at 12:57 AM, Pascal Girard <pascal.girard
Dear NONMEM users, Dear Uppsala Folks, Dear Christopher

I was looking for some Xpose function that would automatically create a forest plot from NONMEM output in order to present the results of covariate analysis, assuming that all covariate models have been implemented the same way with same NULL value. The only thing I found was the Covariates function in the popPK package, which makes use of Xpose, developed by Christoffer Tornoe while he was at FDA.

But this package looks like to be no longer supported and has been removed from the CRAN.

Has anyone developed such a package?

With best regards / Mit freundlichen Grüßen / Cordialement / 祝好 / よろしくお願いします


Pascal Girard
Director, Pharmacometry
Merck Serono | Global Early Development

        "Merck – Living Innovation"

Merck Institute for Pharmacometrics - Merck Serono S.A.
EPFL Innovation Park - Building I, CH-1015 Lausanne, Switzerland
Phone: +41 21 900 3702<tel:%2B41%2021%20900%203702> | Mobile: +41 79 508 7898<tel:%2B41%2079%20508%207898>
Email: pascal.girard <mailto:pascal.girard
Mandatory information can be found at:
Please consider your environmental responsibility before printing this e-mail

This message and any attachment are confidential and may be privileged or otherwise protected from disclosure. If you are not the intended recipient, you must not copy this message or attachment or disclose the contents to any other person. If you have received this transmission in error, please notify the sender immediately and delete the message and any attachment from your system. Merck KGaA, Darmstadt, Germany and any of its subsidiaries do not accept liability for any omissions or errors in this message which may arise as a result of E-Mail-transmission or for damages resulting from any unauthorized changes of the content of this message and any attachment thereto. Merck KGaA, Darmstadt, Germany and any of its subsidiaries do not guarantee that this message is free of viruses and does not accept liability for any damages caused by any virus transmitted therewith.

Click to access the German, French, Spanish and Portuguese versions of this disclaimer.

Pirana Software & Consulting BV

Information in this email and any attachments is confidential and
intended solely for the use of the individual(s) to whom it is addressed
or otherwise directed. Please note that any views or opinions presented
in this email are solely those of the author and do not necessarily
represent those of the Company.
Finally, the recipient should check this email and any attachments for
the presence of viruses. The Company accepts no liability for any damage
caused by any virus transmitted by this email.
All SGS services are rendered in accordance with the applicable SGS
conditions of service available on request and accessible at
Received on Thu Sep 17 2015 - 02:55:10 EDT

The NONMEM Users Network is maintained by ICON plc. Requests to subscribe to the network should be sent to:

Once subscribed, you may contribute to the discussion by emailing: