[R-sig-ME] treating measurement occasions as a numerical or as a factor predictor

K Imran M drki.musa at gmail.com
Sat Dec 12 17:18:20 CET 2015


Hi all,

I am (almost) sure this question has been asked before but I am new
here and I have not found the best answer yet after some googling.

I would like to ask a question about treating measurement occasions in
a longitudinal analysis specifically when using linear mixed model. In
my study, I have taken data on 3 separate occasions (at baseline, at 1
month and at 3 months post baseline). I am not sure what is best
approach treat these measurement occasions in my analysis using lmer
or lme functions. Should I treat them as a numeric or as a factor
variable. My feeling says that I should treat such measurement
occasions as a factor but I do not have strong theoretical reasons for
that.

Treating them as a factor predictor will make my nlme::lme codes like these;

for random intercept:
lme(y~1+ covariateA+factor(occasion), random=~1|subject, data=data)
and for random slope:
lme(y~1+covariteA+factor(occasion),random=~1+factor(occasion)|subject,
data=data)

I appreciate someone can enlighten me on this issue or point to any
useful literature.

Thanks very much.

Best wishes,

Kamarul

-- 
Dr. Kamarul Imran Musa (MD MCommunityMed)
Dept of Community Medicine,
School of Medical Sciences,
Universiti Sains Malaysia,
16150 Kbg Kerian Kelantan
MALAYSIA

ResearcherID: http://www.researcherid.com/rid/N-3198-2015
Personal blog: http://designdataanalysis.wordpress.com
Email : drki.musa at gmail.com , k.musa at lancaster.ac.uk



More information about the R-sig-mixed-models mailing list