使用fitdist拟合Nikitin分布参数时遇MLE报错求助

我们在项目工作中使用极大似然法（MLE）拟合自定义Nikitin分布的参数时遇到问题，恳请协助解决。

相关代码 #

dNikitin <- function(x,xm,k){ifelse(x<=xm,k*x,k*((xm)^(k+1))/(x^(k+1)))}
pNikitin <- function(q,xm,k){ifelse(q<=xm,k*(q^2)/2,1-((xm/q)^k))}
qNikitin <- function(p,xm,k){ifelse(p<=xm,sqrt(2*p/k),((1-p)^(1/k))/xm)}
normalize <- function(x){
return((x-min(x, na.rm = TRUE))/(max(x, na.rm = TRUE)-min(x, na.rm = TRUE)))
}
normWeibull<-normalize(meanWeibull)
fitdist(normWeibull,dNikitin,method="mle",start=list(xm=0.3,k=2))

输入数据 #

c(110.748686129801, 98.2776959086357, 107.896205308347, 92.2915138464519, 
87.7617193395103, 90.1622792140005, 91.8033807629933, 94.568405422293, 
92.5874058165138, 88.0884443786551, 96.5309067199432, 91.0261197676354, 
94.2679775694526, 90.5093551193029, 88.9174199439019, 91.8514293903992, 
90.9955076177624, 91.1814276091258, 91.7929514693243, 93.3873263237287, 
92.6780609953716, 94.1147227956929, 90.6022332236083, 91.3516389064167, 
93.3044623928651, 92.6844973173802, 92.1094717946254, 92.3325385449018, 
92.5078077279718, 91.7228807632554, 91.2199417181825, 92.5131361104952, 
91.1129952612204, 92.7588384693641, 90.8665206849997, 90.779883682863, 
91.0429550901112, 93.5118794242166, 90.9171366944406, 92.9923347664536, 
91.2320675536598, 92.5010420516451, 92.2063219496921, 90.7726417196627, 
91.0286532971901, 92.1203260272004, 91.9261263838444, 92.3717505797982, 
91.9426032838848, 93.4844753515267, 92.4941315850104, 91.617671404993, 
91.9104672687007, 91.8751700888031, 91.8492961510924, 90.6914716378463, 
91.8338048738146, 91.955641871349, 92.3667886405851, 91.9173795403439, 
91.5429025873175, 91.5123507018074, 92.5311555262706, 91.7890357660746, 
91.842671638066, 91.6771883587705, 93.1362779612421, 92.124381384808, 
91.8557174119997, 91.5201622975485, 92.0565738905183, 92.1950908699028, 
91.8527357900513, 92.2933530428259, 91.6476806115201, 91.8410850771431, 
91.3042061948952, 91.8876820473797, 91.3635638985579, 91.7575551978857, 
91.8951555314514, 91.8591302699135, 91.9771331048671, 92.0229325271029, 
92.2772778806803, 91.9120631092919, 92.049009551631, 92.3230796792234, 
91.901438300024, 91.9086185375799, 91.6037245872085, 91.4819628420924, 
91.749716533664, 91.6475919457206, 91.8099939281075, 91.9324739291272, 
91.4278296918048, 92.3146169121117, 91.3771664156326)

错误信息 #

<simpleError in optim(par = vstart, fn = fnobj, fix.arg = fix.arg, obs = data,     gr = gradient, ddistnam = ddistname, hessian = TRUE, method = meth,     lower = lower, upper = upper, ...): function cannot be evaluated at initial parameters>
Error in fitdist(normWeibull, dNikitin, method = "mle", start = list(xm = 0.3,  : 
  the function mle failed to estimate the parameters, 
                with the error code 100

感谢各位提供解决思路，顺颂时祺。

内容的提问来源于stack exchange，提问作者n_nikitin