Quote Originally Posted by gabe
i have a bunch of work due in my probability class due tomorrow. i havent been to class all week. also, ive never had a probability class before.

the assignment is mostly related to the normal distribution. the first question is something like: 'flip a coin 400 times, if H is the number of heads, find the normal approximation to P(190 < H < 200)'

help me get started.
Ok. I dont know what a normal approximation means, and its been a long time since ive done this but id do this ===>


First you gotta standardise the thing. You give each of your numbers a Z score.

Z score is the number of standard deviations from the mean your number is.

Tossing a coin 400 times you expect the mean number of heads to be 200 so from each value you take 200.

you now have

between -10 and 0.

Now you divide by the standard deviation.

The standard deviation in a binomial problem is given by

sqrt(N*p*(1-p))

where N is the number of trials
p is the probability of a success (50%)

so in this case the varience (standard deviation squared) is

N*p*(1-p) = 400*0.5*0.5 = 100

so the standard deviation is 10

so your standardised results should be between

-1 and 0 standard deviations of the mean.


Somewhere or other you should have a table that tells you the percentage of area of a normal distribution curve that lies between 0 and z.
If not then this one will do (http://www.statsoft.com/textbook/sttable.html).

It says that 0.0398 of the area lies between 0 and 1 (or 0 and -1). In other words the probability P(190 < H < 200) = 0.0398.


As I said before its been a while since ive done this so if it turns out to be bollocks then...well.... meh.
I think its right though. If you need anymore explaining ill be awake a little while yet.
Goodluck