Posted by Morgan on .
90% of adults drink milk.
A sample of adults in an area was taken.
657 of 750 drink milk.
Do these responses provide strong evidence that the 90% figure is not accurate for this region?
I figured it out and got the P-value to be .028
How do I explain this?
With 750 persons and a 90% probability, the most probable result would be 0.9*750 = 675 and the standard deviation would be sqrt[0.9*0.1*750] = 8.2.
657 is 2.2 sigma less than the mean. That may be consistent with your P-value of 0.028, but I'm not certain what that means.
I do not consider that to be strong evidence that the 90% figure is not correct.
statistics (reconsidered) -
I checked a normal distribution table and found a probability of only 1.4% that the number of milk drinkers would be 657 or less. That does strongly suggest the fraction may be less than 90% for that region.