[R-sig-ME] lmer estimation with repeated identifiers

Yashree Mehta y@@hree19 @end|ng |rom gm@||@com
Fri Feb 4 15:03:21 CET 2022


I am working with a random intercept model on a cluster dataset (Repeated
measurements of plots per household). I have the usual "X" vector
of covariates and one id variable which will make up the random
intercept. For example,

Response variable: Production of a crop
Covariates: Size, input quantities, soil fertility dummies etc..
ID variable: Household_ID

Now one aspect of my data is that for some cases, the same plot is repeated
within a household due to different seasons. So this would leave me with
duplicate occurrence of the combination of household ID and plot ID.

My question is: Is the treatment of such data different than the
traditional panel data random effects (because to specify random effects
one has to specify a unique combination of household and plot for every
observation). Is the MLE of lmer different than random effects in such a
case? I tried to compare the two but random effects estimation cannot be
implemented with such data.

Thank you,


	[[alternative HTML version deleted]]

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