TABLE 10-14
a Problem with a Telephone Line $$\text { t-Test: Two- Sample Assuming Unequal Variances }$$

TABLE 10-14
A problem with a telephone line that prevents a customer from receiving or making calls is disconcerting to both the customer and the telephone company. The data on samples of 20 problems reported to twodifferent offices of a telephone company and the time toclear these problems (in minutes) from the customers'lines are collected. Belowis the Excel output to see whether there is evidence of a difference in the mean waitingtime between the two offices assuming that the population variances in the two offices are not equal.
$$\text { t-Test: Two- Sample Assuming Unequal Variances }$$
$$\begin{array} { l r r } & \text { Office 1 } & \text { Office 2 } \\\hline \text { Mean } & 2214 & 2.0115 \\\text { Variance } & 2.951657 & 3.57855 \\\text { Observations } & 20 & 20 \\\text { Hypothesized Mean Difference } & 0 & \\\mathrm { df } & 38 & \\\mathrm { t } \text { Stat } & 0.354386 & \\\mathrm { P } ( \mathrm { T } < = \mathrm { t } ) \text { one- tail } & 0.362504 & \\\mathrm { t } \text { Critical one- tail } & 1.685953 & \\\mathrm { P } ( \mathrm { T } < = \mathrm { t } ) \text { two- tail } & 0.725009 & \\\mathrm { t } \text { Critical two-tail } & 2.024394 & \\\hline\end{array}$$
-Referring to Table 10-14, what is the largest level of significance at which a test on a difference in the variability of the waiting time between the two offices will not be rejected?