1) 6.2.1 - 6.2.3
6.2.1 An instructor collected data on prices (in dollars) paid by students for their most recent
haircut, also recording each student’s sex, to test whether females in the population paid more
on average for their most recent haircut than males. Which of the following are appropriate sets
of hypotheses?
A, B, C, D are all correct.
E is wrong because we need to use population mean symbol μ in hypothesis
F and G are wrong because they did not state that we hypothesize that female spend more on
haircuts.
6.2.2 Reconsider the previous exercise about haircut prices. The p-value for the appropriate test
turns out to be 0.0022. What would you conclude?
A, strong evidence that female pay more than male on haircuts
6.2.3 Reconsider the previous two exercises about haircut prices. The sample mean prices
were $21.85 for males and $54.05 for females, a difference of $32.20. Which are appropriate
interpretations of the p-value of 0.0022?
A) There’s a 0.22% chance that women in the population did not pay more on average than males for
their most recent haircut.
B) If there were no difference in the population between what females and males paid for their most
recent haircut, then there’s a 0.22% chance that the sample mean price for females would have been
at least $32.20 higher than the sample mean price for males.
C) If there were no difference in the population between what females and males paid for their most
recent haircut, then 0.22% of all random shuffles based on the sample data would produce the
shuffled mean price for females being at least $32.20 higher than the shuffled mean price for males.
B and C are correct
6.2.1 An instructor collected data on prices (in dollars) paid by students for their most recent
haircut, also recording each student’s sex, to test whether females in the population paid more
on average for their most recent haircut than males. Which of the following are appropriate sets
of hypotheses?
A, B, C, D are all correct.
E is wrong because we need to use population mean symbol μ in hypothesis
F and G are wrong because they did not state that we hypothesize that female spend more on
haircuts.
6.2.2 Reconsider the previous exercise about haircut prices. The p-value for the appropriate test
turns out to be 0.0022. What would you conclude?
A, strong evidence that female pay more than male on haircuts
6.2.3 Reconsider the previous two exercises about haircut prices. The sample mean prices
were $21.85 for males and $54.05 for females, a difference of $32.20. Which are appropriate
interpretations of the p-value of 0.0022?
A) There’s a 0.22% chance that women in the population did not pay more on average than males for
their most recent haircut.
B) If there were no difference in the population between what females and males paid for their most
recent haircut, then there’s a 0.22% chance that the sample mean price for females would have been
at least $32.20 higher than the sample mean price for males.
C) If there were no difference in the population between what females and males paid for their most
recent haircut, then 0.22% of all random shuffles based on the sample data would produce the
shuffled mean price for females being at least $32.20 higher than the shuffled mean price for males.
B and C are correct
