Intutively and By Moment generating function technique, I can prove that independent bernoulli random variable's sum follows binomial distribution. But how can I prove that not by MGF technique?
$\begingroup$
$\endgroup$
$\begingroup$
$\endgroup$
If you start from $$X_1,\ldots,X_n\stackrel{\text{i.i.d.}}{\sim}\mathcal{B}(p)$$ and define $$Y=X_1+\cdots+X_n$$ you can compute directly$$\mathbb{P}(Y=y)={n \choose y} p^y (1-p)^{n-y}\qquad y=0,1,\ldots,n$$ by a combinatoric argument.
self-studytag in that it is connected with a book, exercise or homework assignment? In which case you would need to add the tag. $\endgroup$ – Xi'an Sep 18 '16 at 10:32