My apologies for the silly question: I've been running a mixed effects model and since I have a small number of clusters (11) I've been using REML. Having plotted the residuals for one of my models, and seeing they were nowhere near being normal (variable is heavily negatively skewed), I ran the model again using robust standard errors. It gave me completely different results, and different variables being significant. I've been reading around the subject to understand it, and was wondering if anyone had any insight into why they're so different, and what would be the best approach here: REML or robust SE's? TIA.
Related Posts with Multilevel model: REML or robust SE's?
Creating a Propensity Score Robustness Check TableHi, Does anyone know if there's a way to create a table like the attached image of different propen…
How to test goodness of fit in multinomial logistic regression having used the subpop rather than sub sample optionoptionHow do I test the goodness of fit for multinomial logistic regression, having used the subpop option…
Panel Data: xttest2 errorHi, I am running a long panel (t=15, N=8), 8 countries and 15 years. after running for fe I ran the…
merge vars do not uniquely identify observations in master data - but no duplicates foundI am struggling to perform a 1:m merge on two merge variables that are both string variables. When I…
Help - Create Variable Indicating Percent who Agree or Strongly Agree by DepartmentHi, All, I have survey data with responses from individuals (n = 1077, some missing data), and thos…
Subscribe to:
Post Comments (Atom)
0 Response to Multilevel model: REML or robust SE's?
Post a Comment