I am using lmerTest to run linear mixed models (LMM) to get the p-values. However, in the articles I have written, they will show both lme4 and lmerTest. Then I am not sure if I also have cite lme4 when I use only lmerTest to run LMM models.

Do you have any idea about this?


lmerTest basically offers a bunch of convenience functions on top of lme4. The actual important software is lme4, which implements the model framework. You should definitely give the reference for lme4 as specified in citation("lme4"):

Douglas Bates, Martin Maechler, Ben Bolker and Steven Walker (2014). lme4: Linear mixed-effects models using Eigen and S4. R package version 1.0-6. http://CRAN.R-project.org/package=lme4

This is not only important for giving well deserved attribution, but also to state the lme4 version number.

  • 2
    $\begingroup$ +1, wholeheartedly agree with giving version number. In my field this is often neglected. $\endgroup$ – Patrick Coulombe Mar 5 '14 at 16:23
  • 2
    $\begingroup$ +1 and a 3rd possibly important reason to cite the package is that R comes with ABSOLUTELY NO WARRANTY. So, even though we are fairly confident the algorithm is correct, we need to make the methods transparent so that, should any well understood peculiarity arise in the future, we can retrospectively ascertain the validity of your results now. $\endgroup$ – AdamO Mar 5 '14 at 17:12
  • 4
    $\begingroup$ @AdamO I believe that point is valid for most software tools. There were well known bugs in Excel for years and I don't think Microsoft reimbursed anyone. $\endgroup$ – Roland Mar 5 '14 at 17:16
  • 1
    $\begingroup$ Okay. So I will cite both lme4 and lmerTest. Thanks very much Roland. $\endgroup$ – user3288202 Mar 5 '14 at 17:24
  • $\begingroup$ @NickStauner Thank you for your suggestion. Sorry for haven't done this for many questions I have posted as I am very new to this website, but now I know that I can do it. (I always wonder who people give me vote and how I can vote for other people) $\endgroup$ – user3288202 Mar 6 '14 at 10:06

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.