I have a response variable that is non-normaly distributed (~Gamma). Due to the fact that I have a lot of "contamination", I would need to use a robust mixed-effects model method that is able to remove it. I was thinking on using the package robustlmm, however, I don't know if I can use it since my data don't follow a normal distribution.
Does anyone know something about that?
robustlmm::rlmer(), right? I wonder what you mean distinguishing between inference and predictions. In my case,Yis a measure of activity (m.s⁻²) of an animal taken with one device (A), andXis the measure of the same thing (=activity) with another device (B) with more restricted settings and in a different position than deviceA. The advantage of devBis that it allows to record longer time periods. ThenYis more accurate measure thanXmight be very useful in my field (ecology). – Dekike Sep 23 '20 at 10:27YandXand discuss the suitability of using devB. My idea was to stablish if the relationship is linear or exponential between variables and also to calculate R². What is my problem? The animal(s) moves little, meaning that I get a gamma distribution of activities. However, the biggest problem is thatXmeasures sometimes go far from the general trend due to its settings and position, generating some extrange patterns in my plot of residuals vs predicted values. – Dekike Sep 23 '20 at 10:32Xinstead ofY, because it is clear that some settings ofXare doing that predictions are better or worst depending onXvalue. – Dekike Sep 23 '20 at 10:39r2mof 80%, which means thatXexplains 80% of the variance ofY, however, given that I have residual patterns, I don't know what to do. Your comment about that normal distribution is (or not) required depending on if I make inferences or predictions, has made me think about all this. Could you give me your advice? I am a little bit lost. – Dekike Sep 23 '20 at 10:39Bpredicts values from deviceA. In the simplest case, I guess it would be enough with R² measuring the relationship betweenAandBdevices (YandX, respectively). Since I have data for 6 individuals and data distribution is gamma, I though on a GLMM, and thus, calculate r2m instead of R². However, I get resial patterns. I guess that the only solution is either log-transforming or maybe, using a robustlmm? – Dekike Sep 23 '20 at 15:11Y(in the other post I call ita), hourly mean values ofX(in the post I call itb), and ALSO I have number of records per hour with methodB. All this is because I am interested on assessing the performance of methodB. – Dekike Sep 23 '20 at 16:35