Can anyone check my answer about the following hypothesis test?

A company considers buying a machine to manufacture a certain item. When tested, 28 out of 600 items produced by the machine were found defective. Does the data support the hypothesis that the defect rate of the machine is smaller than 3% at the 5% significance level.

$H_0: p \ge 0.03$

$H_a: p < 0.03$

$\alpha = 0.05$

Critical value $z = -1.645$

Reject $H_0$ if $z < -1.645$

Test statistic

$\Rightarrow Z_0 = \frac{\overline{X} - \mu_o}{\sigma/\sqrt{n}} = > \frac{0.0467-0.03}{0.03*0.97/\sqrt{600}} = 14.057$

Therefore, we fail to reject $H_0$. There isn't enough evidence to say that defect rate of machine is smaller than 3%.


  • $\begingroup$ But you have not stated the value of $\sigma$, nor whether you know the population value, or if you obtained $\sigma$ from sample data, in which case your statistic would be a $t-$statistic. $\endgroup$
    – BFD
    Oct 30 '13 at 6:53
  • $\begingroup$ Sorry, I just mean that you did not mention $\sigma$ in the statement of the problem. $\endgroup$
    – BFD
    Oct 30 '13 at 7:13
  • $\begingroup$ BFD:Proportions hyposthesis testing, you don't need a sigma $\endgroup$ Oct 30 '13 at 9:34

H0: p=.03

H1: p<.03


p-hat = .0467 = 28/600

Test statistic => z = (0.0467 - 0.03)/sqrt(0.03*.97/600) = 2.398

z>-1.65 (One tailed test with alpha = .05)

Hence fail to reject H0 to conclude that there is not sufficient evidence that the defect

rate is smaller than 3%

Sorry, I changed the solution


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.