【无标题】

Plant breeders are attempting to develop a new strain of dogwood tree that is resistant to air pollution. In one study of their progress, a random sample of $n=45$ seedlings of the new strain was selected, and the seedlings were planted at random locations in a particular industrial region. Results indicate that 27 of those seedlings died within three years. Historical records show that 70% of an existing strain of dogwood tree planted in that region died within three years.

Use this information to answer Questions 1-4.

---

Choose the correct alternative hypothesis for the test of whether the new strain of dogwood tree has a lower death rate within three years than the existing strain when planted in the industrial region.

• $H_a:\pi =0.70$
• $H_a:\pi \ne 0.70$
• $H_a:\pi <0.70$
• $H_a:\pi >0.70$

---

Compute the test statistic for the hypothesis test of whether the new strain of dogwood tree has a lower death rate within three years than the existing strain when planted in the industrial region. (Round answer to two decimal places.)

---

What is the p-value for this test? (Round your p-value to 2 decimal places.)

---

Choose the correct conclusion for the hypothesis test using $\alpha =0.05$.

• Reject $H_0$. There is sufficient evidence to suggest that the new strain of dogwood tree has a lower death rate within three years than the existing strain.
• Fail to reject $H_0$. There is insufficient evidence to suggest that the new strain of dogwood tree has a lower death rate within three years than the existing strain.
• Fail to reject $H_0$. There is insufficient evidence to suggest that the new strain of dogwood tree has a higher death rate within three years than the existing strain.
• Reject $H_0$. There is sufficient evidence to suggest that the new strain of dogwood tree has a higher death rate within three years than the existing strain.
  Four quantities influencing the power of a hypothesis test are the significance level, the sample size, the variability, and the difference one wishes to detect. Answer Questions 5-8 by selecting either DECREASES or INCREASES to fill in the blank. For all statements, assume all other factors affecting power are held constant except the factor of interest in that particular statement.

---

When the significance level decreases from $\alpha =0.05$ to $\alpha =0.01$, the power of the hypothesis test

• ☐ INCREASES
• ☐ DECREASES

---

When the sample size increases, the power of the hypothesis test

• ☐ INCREASES
• ☐ DECREASES

---

When the variability in the study decreases, the power of the hypothesis test

• ☐ INCREASES
• ☐ DECREASES

---

When the size of the difference one wishes to test decreases, the power of the hypothesis test

• ☐ INCREASES
• ☐ DECREASES

Measurements were made on nine widgets. You know that the distribution of widget measurements has historically been close to normal, but suppose that you do not know $\sigma$. To test if the population mean differs from 5 you obtain a 90% confidence interval for the mean using the t-procedure. The software output is below.

---

One-Sample T: Values

Test of $H_0:\mu =5$ vs. $H_a:\mu \ne 5$

Variable	N	Mean	StDev	SE Mean	90% CI
Values	9	4.7889	?	0.0824	(4.6357, 4.9421)

Use this information to answer Questions 9 and 10.

---

What is the value for the standard deviation (StDev) that is left off this output? (Round to two decimal places.)

---

Based on the 90% confidence interval, what is your conclusion for this hypothesis test: $H_0:\mu =5$ vs. $H_a:\mu \ne 5$.

• ☐ The mean of the widget measurements is different from 5 because 5 does not fall in the 90% confidence interval.
• ☐ There is not enough evidence that the mean of the widget measurements is different from 5 because 5 does not fall in the 90% confidence interval.
• ☐ The mean of the widget measurements is different from 5 because 0 does not fall in the 90% confidence interval.
• ☐ There is not enough evidence that the mean of the widget measurements is different from 5 because 0 does not fall in the 90% confidence interval.

An article in the journal of Neurology (1998, Vol. 50, pp. 1246-1252) observed that monozygotic twins share numerous physical, psychological, and pathological traits. The investigators measured an intelligence score of 10 pairs of twins. Their objective is to test whether the test scores differ based on birth order. When completing this hypothesis test, be sure to take into account the natural pairing of the data.

Use this information to answer Questions 11-19.

The data for this question is linked below:

Pair	Birth Order 1	Birth Order 2
1	6.08	5.73
2	6.22	5.80
3	7.99	8.42
4	7.44	6.84
5	6.48	6.43
6	7.99	8.76
7	6.32	6.32
8	7.60	7.62
9	6.03	6.59
10	7.52	7.67

---

Choose the correct alternative hypothesis for the hypothesis test of whether the test scores differ based on birth order.

• ☐ $H_a:{\mu }_2<{\mu }_1$
• ☐ $H_a:{\mu }_2>{\mu }_1$
• ☐ $H_a:{\mu }_2\ne {\mu }_1$
• ☐ $H_a:{\mu }_2={\mu }_1$

---

Calculate the test statistic either using software or by hand (round to two decimal places).

---

Select the appropriate p-value for the hypothesis test that tests if the two mean test scores differ.

• ☐ $0.7230$
• ☐ $<0.0001$
• ☐ $0.9047$
• ☐ $0.3615$

---

Based on the p-value chosen in Question 13, select the appropriate conclusion for the hypothesis test. $\alpha =0.05$.

• ☐ Fail to reject $H_0$. There is sufficient evidence to conclude that the test scores are significantly different based on birth order.
• ☐ Fail to reject $H_0$. There is insufficient evidence to conclude that the test scores are significantly different based on birth order.
• ☐ Reject $H_0$. There is sufficient evidence to conclude that the test scores are significantly different based on birth order.
• ☐ Reject $H_0$. There is insufficient evidence to conclude that the test scores are significantly different based on birth order.

---

What is the upper bound for the 95% confidence interval for the difference in mean test scores based on birth order? (Round answer to 3 decimal places.)

---

What is the lower bound for the 95% confidence interval for the difference in mean test scores based on birth order? (Round answer to 3 decimal places.)

---

Suppose instead of the 95% confidence interval you computed in Questions 15 and 16, you were computed a 99% confidence interval. Would this 99% confidence interval be wider or narrower than the 95% confidence interval?

• ☐ Wider
• ☐ Narrower

---

If instead of a 95% confidence interval, you calculated a 90% confidence interval. Would the 90% interval be wider or narrower than the 95% confidence interval you constructed in Questions 15-17?

• ☐ Narrower

• ☐ Wider
  True or False: You are performing a hypothesis test to determine if the true mean test scores differ based on birth order. A TYPE II error would be concluding that there is not enough evidence to suggest a difference in test scores when a difference in test scores truly exists.

• ☐ True

• ☐ False

---

Question 20-24 are all standalone. No question builds on information from a previous question.

---

True or False: You are performing a hypothesis test to determine if the true mean breaking strength of a certain fiber is more than 400 pounds. This hypothesis test is a two-sided hypothesis test.

• ☐ True
• ☐ False

---

True or False: A study about the change in weight on a new diet reports a p-value = 0.043 for testing $H_0:\mu =0$ vs. $H_a:\mu \ne 0$. If the authors had instead reported a 95% confidence interval for $\mu$, then the interval would have contained 0.

• ☐ True
• ☐ False

---

True or False: The p-value is the probability the null hypothesis is true.

• ☐ True
• ☐ False

---

You perform a two-sample t-test for the hypotheses $H_0:{\mu }_1-{\mu }_2\le 0$ vs. $H_a:{\mu }_1-{\mu }_2>0$ and obtain $t_{obs}=0.37$ and a p-value of 0.358. What would be the p-value if the hypothesis test was instead $H_0:{\mu }_1-{\mu }_2=0$ vs. $H_a:{\mu }_1-{\mu }_2\ne 0$? Round to 3 decimal places.

---

True or False: You perform a one-sample t-test for $H_0:\mu \ge 16$ vs. $H_a:\mu <16$ and obtain the test statistic $t_{obs}=-1.32$. The value $t_{obs}=1.32$ is also a valid test statistic for this hypothesis test because it does not matter how you subtract to obtain the test statistic.

• ☐ True
• ☐ False