[英]Finding the roots of equation system
I would like to use multiroot
command in the rootSolve
package to find b and m. 我想用multiroot
命令在rootSolve
包装,拿出B和M。 The code is given below. 代码如下。 I tried different starting values but the result was either NaN
or NaNs produced
. 我尝试了不同的起始值,但结果是生成了NaN
或NaNs produced
。
n <- 23
model <- function(theta){
b <- theta[1]
m <- theta[2]
power <- exp(-(x-m)*b)
a <- -n/sum(log(1-power))
betat <- apply(x,1,function(x) (x-m)*power/(1-power))
mut <- apply(x,1, function(x) power/(1-power))
F1 <- n/b-sum(x)+n*m+(a-1)*sum(betat)
F2 <- n*b-b*(a-1)*sum(mut)
c(F1=F1,F2=F2)
}
multiroot(f = model, start = c(.5, .5))
So can someone explain me where the mistake is, please? 那么有人可以向我解释错误在哪里吗?
library(rootSolve)
x<- c(17.88,28.92,33,41.52,42.12,45.6,48.40,51.84,51.96,54.12,55.56,67.80,
68.64,68.64,68.88,84.12,93.12, 98.64,105.12,105.84,127.92,128.04,173.4)
n <- length(x)
model <- function(theta){
b <- theta[1]
m <- theta[2]
power <- exp(-(x-m)*b)
a <- -n/sum(log(1-power))
F1 <- n/b-sum(x-m) + (a-1)*sum((x-m)*power/(1-power))
F2 <- n*b - b*(a-1)*sum(power/(1-power))
c(F1=F1,F2=F2)
}
# model(c(b = 0.031, m = 4.748))
multiroot(f = model, start = c(.03, 5))
so the result is: 所以结果是:
> multiroot(f = model, start = c(.03, 5))
$root
[1] 0.03140027 4.55976021
$f.root
F1 F2
-2.046363e-12 -6.217249e-15
$iter
[1] 5
$estim.precis
[1] 1.02629e-12
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.