admin管理员组文章数量:1391991
If I am interested in understanding the effect of an interaction between treatment and covariates on the variance of my response, as well as how they may affect the mean of my response, can I write a glmm like this?
brm(bf(response ~ treatment * distance + treatment * orientation + (1|Individual), sigma ~ treatment * distance + treatment * orientation), family = Gaussian)
Can somebody please explain if sigma can be reliably used in this way to understand the effect of my covariates on the response? How does this sigma response work within the model?
Can the sigma output be trusted if I have uneven treatment groups (i.e. treatment 1 has more observations than treatment 0), or will the smaller group always display greater variance?
If anybody knows of any resources for understanding how to use this sigma term, it would be much appreciated.
本文标签:
版权声明:本文标题:standard deviation - What is happening when I model the sigma term in a glmm with a Gaussian distribution in brms - Stack Overfl 内容由网友自发贡献,该文观点仅代表作者本人, 转载请联系作者并注明出处:http://www.betaflare.com/web/1744635344a2616791.html, 本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容,一经查实,本站将立刻删除。
发表评论