我正在尝试使用R中的speedglm来估计模型.数据集很大(约6988万行和38列).乘以行数和列数导致约27亿,超出整数限制.我无法提供数据,但以下示例重新创建了该问题.
library(speedglm)
# large example that works
require(biglm)
n <- 500000
k <- 500
y <- rgamma(n, 1.5, 1)
x <- round(matrix(rnorm(n*k), n, k), digits = 3)
colnames(x) <- paste("s", 1:k, sep = "")
da <- data.frame(y, x)
fo <- as.formula(paste("y~", paste(paste("s", 1:k, sep = ""), collapse = "+")))
working.example <- speedglm(fo, data = da, family = Gamma(log))
# repeat with large enough size to break
k <- 5000 # 10 times larger than above
x <- round(matrix(rnorm(n*k), …