00:01
It's stated in this question that drinking water is safe when the preclarate levels are 24 .5 parts per billion or less.
00:10
And so we want to test if this level is exceeded in some water.
00:15
We are asked to test at a significant level of 5 percent.
00:19
And to do so, we sampled 28 water sources and found that among these 28, there was a sample mean of 25 .3 parts per billion, and a sample standard deviation of four and a half parts per billion.
00:35
For part a, we are asked to state the hypotheses.
00:39
Now, the null hypothesis here would be that there is no problem, that the mean concentration is 24 .5 parts per billion.
00:50
And the alternative hypothesis is that the mean exceeds the safe level.
00:58
For b, we're asked to calculate the test statistic.
01:01
Now, since we do not know the population standard deviation, we are relying on on using the sample standard deviation.
01:08
And in this case, the test statistic is based on the t distribution with n minus 1 or 27 degrees of freedom.
01:16
Test statistic is calculated as the sample mean minus the null hypothesized mean divided by the sample standard deviation over the square root of the sample size.
01:43
And this comes out to approximately 0 .9407 for c - where it has to calculate a p -value from the test statistic.
01:58
So since this is a right -tailed test, we know that by looking at the alternative hypothesis, it's a greater than hypothesis.
02:06
The p -value is equal to the probability of having gotten a test statistic, at least as great as the one that we got.
02:16
And keep in mind that this is the t distribution based on 27 degrees of freedom...