1

I'm trying to fit linear mixed models to 3 different DV (so three models). I understand that REML gives less biased variance estimates. As im more interested in the fixed effects, I use ML for the initial stepwise model reduction based on AIC-values, and use REML to fit my final (reduced) models.

However, if I got that right, REML ignores the fixed part for fitting the model, right? And since 2 of my 3 models have only very little random variance, I'm confused whether I should completely stick to ML-estimates? What is your opinion on this? Am I right in my understanding of REML vs. ML?

Frize
  • 115
  • 1
  • 1
  • 11
  • This is probably a duplicate, some possible targets: https://stats.stackexchange.com/questions/99895/why-does-one-have-to-use-reml-instead-of-ml-for-choosing-among-nested-var-cova/171529#171529 https://stats.stackexchange.com/questions/91652/when-no-model-comparison-should-i-use-reml-vs-ml https://stats.stackexchange.com/questions/143763/likelihood-ratio-tests-using-ml-vs-reml https://stats.stackexchange.com/questions/353985/why-are-the-coefficients-of-reml-and-ml-estimation-the-same-what-does-that-mean https://stats.stackexchange.com/questions/161103/citation-for-ml-vs-reml – kjetil b halvorsen Aug 29 '18 at 07:51
  • Note that you should not use stepwise model reduction. For more on that, it may help to read my answer here: [Algorithms for automatic model selection](https://stats.stackexchange.com/a/20856/7290). – gung - Reinstate Monica Oct 10 '18 at 15:45

0 Answers0