优化函数的卡方统计

Question

如何记下卡方统计量作为R中的函数，然后如何在优化中使用它来找出概率分布的参数。 任何帮助将不胜感激，谢谢。

n<-28
prob<-function(K, M){
(choose(M+x-2, x-1)*choose(K-M+n-x,n-x+1))/choose(K+n-1,n)}
# prob schould be a vector of functions for x from 1 to 29
# something like that 
# prob<-c() 
# for(x in 1:(n+1)){prob[x]<-function(K, M){ 
# (choose(M+x-2, x-1)*choose(K-M+n-x,n-x+1))/choose(K+n-1,n)}}
# but this is not work.
N<-3754
chi<-function(K, M){sum((frequency[,2]-N*prob)^2/(N*prob))}
optim( c(-5.54, 0.37), chi, hessian=TRUE)