Taylor W. answered 04/29/19
Statistical Programmer - Masters of Applied Statistics
The null hypothesis is the opposite of the 'claim' in the question. The 'claim' is the alternative hypothesis.
Null Hypothesis: mean >= 21.1
Alternative Hypothesis: mean < 21.1
Define the things you know:
n = 25
degrees of freedom = 25 - 1 = 24
mean = 19.4
SD = 3.77
SE = 3.77/sqrt(25) = 3.77/5 = 0.754
Compute your test statistic using the formula:
t = (sample mean - hypothesized mean)/SE = (19.4 - 21.1)/0.754 = -2.2546
Look up the critical t-statistic for 24 degrees of freedom for a 1-tailed test at a significance level of 0.05. This is -1.711.
Compare your obtained statistic with the critical statistic and get the p-value from a table or statistical program.
p-value for a left tailed test is: 0.01678
Since 0.01678 < 0.05, we can reject the null hypothesis in favor of the alternative that the mean is less than 21.1, suggesting that the filters are effective.