Question

我正在尝试使用二项式响应在R中执行glmer。这是代码：

    hg1<-glmer(Used~ size*daytime + (1|Bird), family=binomial(link=logit), data=hg.model).

使用的是1或0，大小是Hectares中的区域，白天是以米为单位的距离，Bird是我的随机效果变量。当我运行它时，我得到以下内容，

    Error: (maxstephalfit) PIRLS step-halvings failed to reduce deviance in pwrssUpdate
    In addition: Warning message:
    Some predictor variables are on very different scales: consider rescaling

模型无法运行。当我使用附加术语运行模型时：

    hg1<-glmer(Used~ size + daytime + (1|Bird), family=binomial(link=logit), data=hg.model)

我收到以下消息，但模型确实运行了：

    Warning messages:
    1: Some predictor variables are on very different scales: consider rescaling 
    2: In checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv,  :
      Model failed to converge with max|grad| = 0.555943 (tol = 0.001, component 2)
    3: In checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv,  :
      Model is nearly unidentifiable: very large eigenvalue
     - Rescale variables?;Model is nearly unidentifiable: large eigenvalue   ratio
     - Rescale variables?

当我交叉变量（任意组合）时，模型不会运行的任何原因以及如何修复它？感谢

错误：（maxstephalfit）在R中执行二项式glmer时，PIRLS步长减半无法减少pwrssUpdate中的偏差

0 个答案: