00:01
A software company is interested in improving customer satisfaction from the current claimed rate.
00:06
So the current claim is that the rate, p, the proportion of all customers who are satisfied is 56%, 0 .56.
00:16
We want to know if it's higher than that now.
00:18
Perhaps it's gone above that.
00:20
This would be our null hypothesis.
00:22
This would be our alternative.
00:24
I know which is which because the null hypothesis always gets an equal sign of some kind.
00:28
And to test this, we have a sample.
00:31
Sample size, 121.
00:33
Out of these, 75 were satisfied.
00:36
We want to find the z statistic.
00:43
Now, this is basically the z score of the sample proportion.
00:48
And z tells you how many standard deviations away from a mean a value is.
00:53
But what would that mean here? mean standard deviation of what distribution? well, that would be of the sampling distribution.
01:00
What we do is we assume that the null hypothesis is true, and we plot out what possible sample proportions we might get.
01:10
According to the central limit theorem, this distribution will be approximately normal, and its parameters, so p hat follows an approximately normal distribution, the mean is p, the standard deviation is root p1 minus p over n...