the solution goes as following
1. we know that Xi's have type 1 negative binomial distribution with parameter p
\(P(X\ge x)\\=P(X=x)+P(X=x+1) +P(X=x+2).........\\=pq^{x-1}+pq^{x} + pq^{x+1} ............\\=p(q^{x-1}+q^x +q^{x+1} ..............)\) this is an infinite geometric progression with a=\(q^{x-1}\) and r=\(q\)
, thus
\(=p\frac{q^{x-1}}{1-q}\\=p\frac{q^{x-1}}{p}\\=(1-p)^{x-1}\)
2.(a)\(Y=min(X_1,X_2,......,X_n)\\thusP(Y\ge y)\\=P(min(X_1,X_2,......,X_n \ge y)\)
so if minimum of Xi's is greater than y than all Xi's should be greater than y, therefore
\(P(min(X_1,X_2,.....,X_n) \ge y)\\=P(X_1 \ge y) \times P(X_2 \ge y).........P(X_n \ge y)\\=P(X_i \ge y)^n\\=(1-p)^{n(x-1)}\)
(b) comparing this with result in part 1 we can see that Y has type 1 negative binomial distribution with probability of failure \((1-p)^n\) and probability of success \(1-(1-P)^n\)
Last edited by a moderator: Apr 30, 2015