Hi all, I want to use lme4 to predict air temperature using land surface temperature. I now can ran the package successfully. But I am not familiar to the parameters of the predict function. Here is my code: plsttest=predict(mod.xm,lsttest2,allow.new.levels = T) I have two questions: Is there some parameters missed? How does lme4 predict new levels (new climate station in my study?) Does it use fixed model or others? Thank you very much! Sincerely Xiaoma li
question about predict using lme4
2 messages · Li, Xiaoma [GE AT], Lionel
Dear Xiaoma Li, To answer your questions: - No parameters are missed (why should they?) - If you have in your lsttest2 data frame new levels for the random factors, new random deviates will be generated for these levels from a normal distribution with mean 0 and standard deviation equal to the estimated random standard deviation (to get these estimated values look at the summary output). Hope this helps. Yours, Lionel
On 05/05/2016 15:46, Li, Xiaoma [GE AT] wrote:
Hi all, I want to use lme4 to predict air temperature using land surface temperature. I now can ran the package successfully. But I am not familiar to the parameters of the predict function. Here is my code: plsttest=predict(mod.xm,lsttest2,allow.new.levels = T) I have two questions: Is there some parameters missed? How does lme4 predict new levels (new climate station in my study?) Does it use fixed model or others? Thank you very much! Sincerely Xiaoma li [[alternative HTML version deleted]]
_______________________________________________ R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models