[R] (no subject)

Ivan Krylov kry|ov@r00t @end|ng |rom gm@||@com
Mon Nov 7 09:20:58 CET 2022


On Sun, 6 Nov 2022 23:34:46 +0000
Nick Wray <nickmwray using gmail.com> wrote:

> Most of the sets work fine with MICE but with a few I get an error
> message:
> 
> This data set, which generated the error message has five columns
> 
> iter imp variable
>   1   1  986Error in terms.formula(tmp, simplify = TRUE) :
>   invalid term in model formula

Currently, there doesn't seem to be any issues [*] related to your
problem, so you could be the first to report it. (This does look like a
bug in mice; at the very least, the error message could be improved.)
How could the maintainer reproduce your problem in order to debug it?
[**]

traceback() and options(error = recover) are invaluable when trying to
find out what is going on before a crash (see ?traceback, ?recover and
?browser for more information; also the free book R Inferno [***]).

For example, if you set options(error = recover) and then reproduce the
crash, you'll be able to print(tmp) at the time of the crash and see
the term that terms.formula is having a problem with. The next step
would be finding out how this formula came to be, and so on.

> 	[[alternative HTML version deleted]]

Please post in plain text to R mailing lists. This particular message
came through mostly fine, but in many cases, the plain text version
automatically generated by the sender's mailer from the user-composed
HTML version makes for very unpleasant reading.

-- 
Best regards,
Ivan

[*]
https://github.com/amices/mice/issues?q=invalid+term+in+model+formula

[**]
See also: https://www.chiark.greenend.org.uk/~sgtatham/bugs.html

[***]
https://www.burns-stat.com/documents/books/the-r-inferno/



More information about the R-help mailing list