Poisson Approximation to Binomial

[Victor Frankenstein]

For a binomial distribution with n=10 and p=0.5 ,we should not use the poisson approximation because both of the conditions n>=100 and np<=10 are not satisfied. SUppose we go way out on a limb and use the Poisson aproximation anyway. Are the resulting probabilities unacceptable approximations? Why or why not ?

 

[Hurkyl]

Have you worked out the actual value and the approximation?

 

[Victor Frankenstein]

n=10, p=1/2, x=1, mean=n*p= 5

using the poisson formula i got 3.4%
using binomial formula I got 1%
using (mean)+/- 2(standard deviation) i got 8.4 - 1.8

I don't know If its right, confused because should'nt the binomial furmula give the answer within the maximum and minumum usual values ?