私はRにちょっと慣れていません。家族の収入のデータも含むデータセットがあり、最尤推定値を使用して、このデータにガンマ分布を当てはめる必要があります。fitdistr ではなく、パッケージ optim を使用する必要があることが明確に示されています。これは私のコードです：
t1 <- sum(log(newdata$faminc))
t2 <- sum(newdata$faminc)
obs <- nrow(newdata)
lh.gamma <- function(par) {
-((par[1]-1)*t1 - par[2]*t2 - obs*par[1]*log(par[2]) - obs*lgamma(par[1]))
}
#initial guess for a = mean^2(x)/var(x) and b = mean(x) / var(x)
a1 <- (mean(newdata$faminc))^2/var(newdata$faminc)
b1 <- mean(newdata$faminc)/var(newdata$faminc)
init <- c(a1,b1)
q <- optim(init, lh.gamma, method = "BFGS")
q
また、初期化ベクトルに値だけを入力して、このコードを含めてみました。
dlh.gamma <- function(par){
cbind(obs*digamma(par[1])+obs*log(par[2])-t2,
obs*par[1]/par[2]-1/par[2]^2*t1)
}
最適化は次のようになります。
q <- optim(init, lh.gamma, dhl.gamma, method="BFGS")
どれも「機能しません」。まず、学校のコンピューターでコードを試してみたところ、形状とレートのパラメーターに非常に大きな数値が表示されましたが、これは不可能でした。今、自宅で試してみると、次のようになります。
> q <- optim(init, lh.gamma, method = "BFGS")
Error in optim(init, lh.gamma, method = "BFGS") :
non-finite finite-difference value [2]
In addition: There were 50 or more warnings (use warnings() to see the first 50)
> q
function (save = "default", status = 0, runLast = TRUE)
.Internal(quit(save, status, runLast))
<bytecode: 0x000000000eaac960>
<environment: namespace:base>
q は「作成」すらされていません。上記の dlh.gamma 部分を含めた場合を除きますが、再び膨大な数が得られ、収束しません。
何がうまくいかないか/何をすべきか知っている人はいますか?
編集：
> dput(sample(newdata$faminc, 500))
c(42.5, 87.5, 22.5, 17.5, 12.5, 30, 30, 17.5, 42.5, 62.5, 62.5,
30, 30, 150, 22.5, 30, 42.5, 30, 17.5, 8.75, 42.5, 42.5, 42.5,
62.5, 42.5, 30, 17.5, 87.5, 62.5, 150, 42.5, 150, 42.5, 42.5,
42.5, 6.25, 62.5, 87.5, 6.25, 87.5, 30, 150, 22.5, 62.5, 42.5,
150, 17.5, 42.5, 42.5, 42.5, 62.5, 22.5, 42.5, 42.5, 30, 62.5,
30, 62.5, 87.5, 87.5, 42.5, 22.5, 62.5, 22.5, 8.75, 30, 30, 17.5,
87.5, 8.75, 62.5, 30, 17.5, 22.5, 62.5, 42.5, 30, 17.5, 62.5,
8.75, 62.5, 42.5, 150, 30, 62.5, 87.5, 17.5, 62.5, 30, 62.5,
87.5, 42.5, 62.5, 30, 62.5, 42.5, 87.5, 150, 12.5, 42.5, 62.5,
42.5, 62.5, 62.5, 150, 30, 87.5, 12.5, 17.5, 42.5, 62.5, 30,
6.25, 62.5, 42.5, 12.5, 62.5, 8.75, 17.5, 42.5, 62.5, 87.5, 8.75,
62.5, 30, 62.5, 87.5, 42.5, 62.5, 62.5, 12.5, 150, 42.5, 62.5,
12.5, 62.5, 42.5, 62.5, 62.5, 87.5, 42.5, 62.5, 30, 42.5, 150,
42.5, 30, 62.5, 62.5, 87.5, 42.5, 30, 62.5, 62.5, 42.5, 42.5,
30, 62.5, 42.5, 42.5, 62.5, 62.5, 150, 42.5, 30, 42.5, 62.5,
17.5, 62.5, 17.5, 150, 8.75, 62.5, 30, 62.5, 42.5, 42.5, 22.5,
150, 62.5, 42.5, 62.5, 62.5, 22.5, 30, 62.5, 30, 150, 42.5, 42.5,
42.5, 62.5, 30, 12.5, 30, 150, 12.5, 8.75, 22.5, 30, 22.5, 30,
42.5, 42.5, 42.5, 30, 12.5, 62.5, 42.5, 30, 22.5, 42.5, 87.5,
22.5, 12.5, 42.5, 62.5, 62.5, 62.5, 30, 42.5, 30, 62.5, 30, 62.5,
12.5, 22.5, 42.5, 22.5, 87.5, 30, 22.5, 17.5, 42.5, 62.5, 17.5,
250, 150, 42.5, 30, 42.5, 30, 62.5, 17.5, 87.5, 22.5, 150, 62.5,
42.5, 6.25, 87.5, 62.5, 42.5, 30, 42.5, 62.5, 42.5, 87.5, 62.5,
150, 42.5, 30, 6.25, 22.5, 30, 42.5, 42.5, 62.5, 250, 8.75, 150,
42.5, 30, 42.5, 30, 42.5, 42.5, 30, 30, 150, 22.5, 62.5, 30,
8.75, 150, 62.5, 87.5, 150, 42.5, 30, 42.5, 42.5, 42.5, 30, 8.75,
42.5, 42.5, 30, 22.5, 62.5, 17.5, 62.5, 62.5, 42.5, 8.75, 42.5,
12.5, 12.5, 150, 42.5, 42.5, 17.5, 42.5, 62.5, 62.5, 42.5, 42.5,
30, 42.5, 62.5, 30, 62.5, 42.5, 42.5, 42.5, 22.5, 62.5, 62.5,
62.5, 22.5, 150, 62.5, 42.5, 62.5, 42.5, 30, 30, 62.5, 22.5,
62.5, 87.5, 62.5, 42.5, 42.5, 22.5, 62.5, 62.5, 30, 42.5, 42.5,
8.75, 87.5, 42.5, 42.5, 87.5, 30, 62.5, 17.5, 62.5, 42.5, 17.5,
22.5, 62.5, 8.75, 62.5, 22.5, 22.5, 22.5, 42.5, 17.5, 22.5, 62.5,
42.5, 42.5, 42.5, 42.5, 42.5, 30, 30, 8.75, 30, 42.5, 62.5, 22.5,
6.25, 30, 42.5, 62.5, 17.5, 62.5, 42.5, 8.75, 22.5, 30, 17.5,
22.5, 62.5, 42.5, 150, 87.5, 22.5, 12.5, 62.5, 62.5, 62.5, 30,
42.5, 22.5, 62.5, 87.5, 30, 42.5, 62.5, 22.5, 87.5, 30, 30, 22.5,
87.5, 87.5, 250, 30, 62.5, 250, 62.5, 42.5, 42.5, 62.5, 62.5,
42.5, 6.25, 62.5, 62.5, 62.5, 42.5, 42.5, 150, 62.5, 62.5, 30,
150, 22.5, 87.5, 30, 150, 17.5, 8.75, 62.5, 42.5, 62.5, 150,
42.5, 22.5, 42.5, 42.5, 17.5, 62.5, 17.5, 62.5, 42.5, 150, 250,
22.5, 42.5, 30, 62.5, 62.5, 42.5, 42.5, 30, 150, 150, 42.5, 17.5,
17.5, 42.5, 8.75, 62.5, 42.5, 42.5, 22.5, 150, 62.5, 30, 250,
62.5, 87.5, 62.5, 8.75, 62.5, 30, 30, 8.75, 17.5, 17.5, 150,
22.5, 62.5, 62.5, 42.5)
faminc 変数の単位は 1000 です
編集2:
さて、コードは良いですが、次を使用してヒストグラムに分布を当てはめようとします:
x <- rgamma(500,shape=q$par[1],scale=q$par[2])
hist(newdata$faminc, prob = TRUE)
curve(dgamma(x, shape=q$par[1], scale=q$par[2]), add=TRUE, col='blue')
x軸に平らな青い線を生成するだけです..