[R-sig-ME] Seeking guidance on nonlinear mixed-effects modeling
Azadeh Aghaeeyan
@@gh@eey@n @end|ng |rom brocku@c@
Thu Jan 23 01:10:23 CET 2025
Hello everyone,
I am currently working on a project where I aim to use a mixed-effects modeling approach to estimate the parameters of a model. I am new to both R and mixed-effects modeling and would greatly appreciate any advice on which specific approaches or packages would be suitable for my work.
Here is my model
Yij ~ NB(mu_{ij}, overdispersion)
where
mu_{ij} = a_i (exp(-k_i(j-1)) - exp(-k_i(j))) + (Wi - a_i)(exp(-p_iXi(j-1)-q_iZi(j-1)) - exp(-p_iXij-q_iZij))
Yij is the outcome variable for group i, i=1,2,..,I, at time index j=1,2,..,J; Xij and Zij are two time-varying covariates for group i at time index j; Wi is a fixed covariate for group i,
a_i ~ ab_1, k_i ~ kb_2, p_i ~pb_3, q_i ~ qb_4, where a,k,p, and q are positive fixed-effects parameters, and b_l, l=1,2,3,4, are log-normal distributed.
I do not have any prior assumptions on the overdispersion parameter.
Thank you in advance for your time
Best Regards,
Nil
[[alternative HTML version deleted]]
More information about the R-sig-mixed-models
mailing list