What is convergence of binomial to and to notmal distribution?
Let "X" be a Binomial random variable given as,
"f(x)=\\binom{n}{x}p^xq^{n-x},\\space x=0,1,2,.....n"
"0,\\space elsewhere"
For small values of "n" the probability that "X"assumes a specified value can be obtained from the Binomial tables. When "n" is sufficiently large, and the probability of success "(p)" is close to 0.5, the distribution of "X" tends to the normal distribution with mean and standard deviation given by,
"\\mu=E(x)=np" and "\\sigma=\\sqrt{var (x)}=\\sqrt{np(1-p)}=\\sqrt{npq}"
We write,
"f(x)\\sim N(np,(npq))"
To find "p(X=a)=p(a-0.5\\lt X\\lt a+0.5)"
"=p({a-0.5-np\\over\\sqrt{npq}}\\lt Z\\lt{a+0.5-np\\over\\sqrt{npq}})" where 0.5 is a correction factor for continuity.
A possible guide to determine when the normal approximation may be used is provided by calculating "np" and "n(1-p)". If both of these quantities exceed 5, the approximation will yield good results.
Comments
Leave a comment