New stuff in BCEA

[This article was first published on R | Gianluca Baio, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

After my talks in Barcelona, I have started thinking about potential improvements or changes, mostly to do in BCEA — I got some nice comments from quite a few people, some of whom were asking for some tweaks or extra facilities.

Obviously, I’ve not prioritised any of those requests… But: I did think a bit and finally found some time to work on something that I think may be rather useful, particuarly in helping people standardise their workflow using R in health economics. So I have started making a new function make.report(...), which essentially uses some of the facilities that are already in place in BCEAweb. I have updated the GitHub repository so the newest (development) version, code 2.2-63 includes this feature.

In particular, the function takes as inputs a BCEA object and uses it to create the most common analyses (summaries, cost-effectiveness planes, EIB and CEAC plots, etc) and creates a report with some (for now, a bit rudimentary) pre-compiled text. Basically something like this

devtools::install_github("giabaio/BCEA")
library(BCEA)
data(Vaccine)
m=bcea(e,c,ref=2,interventions=c("Status quo","Vaccine"))
make.report(m)

compiles and creates the report with the following analyses:

  • Summary (for a given willingness to pay threshold, which can be specified using the non-mandatory input wtp. For now, the default is at the maximum value of the WTP grid contained in the m object);
  • Cost-effectiveness plane (again, it is possible to select the input wtp);
  • Expected incremental benefit graph (at the moment, including 95% interval estimates);
  • Cost-effectiveness frontier;
  • Cost-effectiveness acceptability curve;
  • Expected value of perfect information.

The idea is to also allow for the possibility that the user may have performed some extra analyses (eg EVPPI, EVSI, or even missing data analysis), so that, once the relevant object has been created, it is post-processed and the relevant text is appended to the report.

Inspired by the British Prime Minister, I will listen to people, so if you have comments or desiderata, I will try hard to implement them — at this stage, this is pretty much open to everything (within reason)…

On related news, I have heard from Springer and, apparently, our BCEA book has done rather well — I am told, over 7000 downloads! The evil master plan is on!

To leave a comment for the author, please follow the link and comment on their blog: R | Gianluca Baio.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)