使用模擬混合模型中的新數據產生的錯誤

Question

我試圖在lme4中使用glmer模型中的simulate。我試圖通過newdata，但獲得各種格式的不同錯誤。可能只是不理解函數需要什麼格式，但包示例也會產生錯誤。從包數據

實施例：

# Mixed model 
gm1 <- glmer(cbind(incidence, size - incidence) ~ period + (1 | herd), 
       data = cbpp, family = binomial) 

# Generate new data as per example 
newdata <- with(cbpp, expand.grid(period=unique(period), herd=unique(herd))) 

# Predict works as expected 
predict(gm1, newdata=newdata)    # works 
predict(gm1, newdata=newdata[1,])   # works 

# Simulate generates different errors 
simulate(gm1, newdata=newdata)    # works with error, but probably fine. 
# Warning message: 
# In wts - Y : 
# longer object length is not a multiple of shorter object length 


simulate(gm1, newdata=newdata[1,])   # doesn't work 
# Error in data.frame(sim_1 = c(" 4", "10"), check.names = FALSE, row.names = "1") : 
# 'row.names' should specify one of the variables 
# In addition: Warning message: 
# In format.data.frame(x, digits = digits, na.encode = FALSE) : 
# corrupt data frame: columns will be truncated or padded with NAs 

newdata2 = data.frame(
    herd=c("1"), 
    period=c("1") 
) 
simulate(gm1, newdata=newdata2)    # same error 

simulate(gm1, newdata=newdata[1:2,])   # works but with error 
# Warning message: 
# In format.data.frame(x, digits = digits, na.encode = FALSE) : 
# corrupt data frame: columns will be truncated or padded with NAs 

---

R version 3.2.1 (2015-06-18) 
Platform: x86_64-pc-linux-gnu (64-bit) 
Running under: Ubuntu 14.04.1 LTS 

other attached packages: 
[1] ggplot2_1.0.0 Zelig_3.5.4  boot_1.3-9  MASS_7.3-29  Hmisc_3.14-5 
[6] Formula_1.1-2 survival_2.37-7 lattice_0.20-29 plyr_1.8.1  RCurl_1.95-4.3 
[11] bitops_1.0-6 lme4_1.1-10  Matrix_1.1-2 

loaded via a namespace (and not attached): 
[1] Rcpp_0.12.1   cluster_1.14.4  munsell_0.4.2  colorspace_1.2-4 
[5] minqa_1.2.4   stringr_0.6.2  tools_3.2.1   nnet_7.3-7   
[9] MatchIt_2.4-21  gtable_0.1.2  nlme_3.1-113  latticeExtra_0.6-26 
[13] digest_0.6.4  reshape2_1.4  RColorBrewer_1.0-5 nloptr_1.0.4  
[17] acepack_1.3-3.3  rpart_4.1-5   labeling_0.3  scales_0.2.4  
[21] foreign_0.8-59  proto_0.3-10  

Answer 1

這現在fixed是在開發版本lme4。非常感謝Ben Bolker。

devtools::install_github("lme4/lme4")