Answer :
Answer:
We reject the null hypothesis that the population means are equal and accept the alternative hypothesis that the population means are different.
Step-by-step explanation:
We have large sample sizes [tex]n_{1} = 49[/tex] and [tex]n_{2} = 64[/tex], the unbiased point estimate for [tex]\mu_{1}-\mu_{2}[/tex] is [tex]\bar{x}_{1} - \bar{x}_{2}[/tex], i.e., 12-14 = -2.
The standard error is given by [tex]\sqrt{\frac{\sigma^{2}_{1}}{n_{1}}+\frac{\sigma^{2}_{2}}{n_{2}}}[/tex], i.e.,
[tex]\sqrt{\frac{(3)^{2}}{49}+\frac{(4)^{2}}{64}}[/tex] = 0.6585.
We want to test [tex]H_{0}: \mu_{1}-\mu_{2} = 0[/tex] vs [tex]H_{1}: \mu_{1}-\mu_{2} \neq 0[/tex] (two-tailed alternative). The rejection region is given by RR = {z | z < -2.5758 or z > 2.5758} where -2.5758 and 2.5758 are the 0.5th and 99.5th quantiles of the standard normal distribution respectively. The test statistic is [tex]Z = \frac{\bar{x}_{1} - \bar{x}_{2}-0}{\sqrt{\frac{\sigma^{2}_{1}}{n_{1}}+\frac{\sigma^{2}_{2}}{n_{2}}}}[/tex] and the observed value is [tex]z_{0} = \frac{-2}{0.6585} = -3.0372[/tex]. Because -3.0372 fall inside RR, we reject the null hypothesis.
The test statistic follow a standard normal distribution because we are dealing with large sample sizes.