HW 13 220

ECO220Y: Homework 13
Required Exercises: Chapter 12: 5, 9, 11, 13, 15, 49, 51, 53, 55, 58, 69, 71, 75 (Note: There is a correction in the solution
for exercise 69.)
Required Problems:
(1) Practice your understanding of the P‐value.
(a) Why does the P‐value depend on whether the research hypothesis (H1) specifies >, <, or ≠? Give an example.
(b) For the first babies of Indian‐born moms the sample proportion (P‐hat) of males is 0.510 for the 14,789
babies. What does a P‐value of 0.665 mean when testing H0: p = 0.512 and H1: p > 0.512? How can it be so big?
(c) Give an example where the P‐value for a two‐tailed test is NOT double the P‐value for a one‐tailed test.
(2) Doing a two‐ vs. one‐tailed test affects what: the rejection region, the test statistic, neither or both?
(3) Recall Karlan and List (2007): “Does Price Matter in Charitable Giving? Evidence from a Large‐Scale Natural Field
Experiment.”
(a) Suppose a researcher wants to prove that offering a match increased the response rate compared to no
match. Write the associated hypotheses using formal notation.
(b) Suppose a researcher wants to prove that offering a match decreased the response rate compared to no
(c) Suppose a researcher wants to prove that offering a match affected the response rate compared to no
(d) For the hypothesis test in Part (a), what does it mean if the P‐value is greater than 0.5?
(e) What is the standardized rejection region for the hypothesis test in Part (a) for a 5% significance level?
(f) What is the standardized rejection region for the hypothesis test in Part (b) for a 10% significance level?
(g) What is the standardized rejection region for the hypothesis test in Part (c) for a 1% significance level?
(4) For each scenario, are the results: (1) statistically significant, (2) economically significant, or (3) significant?
(a) A sample of 𝑛 3,000,000 coupons to test H0: 𝑝 = 0.15 v. H1: 𝑝 > 0.15 where 𝑃 = 0.151 and the P‐value ≈ 0.
(b) A sample of births to test H0: 𝑝 = 0.512 v. H1: 𝑝 > 0.512 where 𝑃 0.636 and the P‐value = 0.20.
(c) A sample of births to test H0: 𝑝 = 0.512 v. H1: 𝑝 > 0.512 where 𝑃 0.533 and the P‐value = 0.0002.
(d) Using two samples to compare the unemployment rates between two groups to test 𝐻 : 𝑝 𝑝 0 v.
𝐻:𝑝 𝑝 0 where 𝑃 0.0541, 𝑃 0.0780 and the P‐value ≈ 0.
(e) Using two samples to compare calories of a control group (regular menu) and a treatment group (menu gives
calories) to test 𝐻 : 𝜇 𝜇 0 v. 𝐻 : 𝜇 𝜇 0 where 𝑋 1,501, 𝑋 1,523 and the P‐value is 0.0359.
Page 1 of 2
(5) True or False and Explain: In hypothesis testing, a smaller P‐value means a larger Type II error.
(6) This question expands on exercise 58 (“Radio ads”) in Chapter 12. [Note: You complete that exercise first.] The
opening states “A company is willing to renew its advertising contract with a local radio station only if the station can
prove that more than 20% of the residents of the city have heard the ad and recognize the company’s product. The radio
station conducts a random phone survey of 400 people.”
(a) If the significance level is 0.05, what is the power of the hypothesis test if in truth 24% of residents have
heard the ad? Find the answer numerically and illustrate it graphically. Interpret the numerical value for the
power of the test that you find.
(b) If the significance level is 0.05, what is the power of the hypothesis test if in truth 26% of residents have
heard the ad? Find the answer numerically and illustrate it graphically.
(c) If the significance level is 0.05, what is the power of the hypothesis test if in truth 28% of residents have
(d) Explain in words why power changes in the way that it does from (a) to (c).
(e) Without doing further calculations (but reviewing your work thus far), explain what the power would be if in
truth 50% of residents have heard the ad? Verify your thinking by doing the actual calculation.
(f) Without doing calculations further calculations (but reviewing your work thus far), explain what the power
would be if in truth 20.5% of residents have heard the ad? Verify your thinking by doing the actual calculation.
(g) If the significance level is 0.10, what is the power of the hypothesis test if in truth 26% of residents have
(h) If the significance level is 0.05, what is the power of the hypothesis test if in truth 26% of residents have
heard the ad and the random sample size is 600? Find the answer numerically and illustrate it graphically.
(7) To test these hypotheses about the population proportion – H0: p = 0.60; H1: p > 0.60 – you plan to collect a random
sample of 100 individuals and use a 5% significance level. Compute the Type II error if the true population proportion is
0.58, 0.60, 0.62, 0.64, 0.66, 0.70, 0.72, 0.74, 0.76. Next, graph your results with a line graph where the horizontal axis is
the population proportion, and the vertical axis is the probability of making a Type II error. This is called a power curve.
Page 2 of 2

HW 13 220

Uploaded by

Copyright:

Available Formats

HW 13 220

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

HW 13 220

Uploaded by

Copyright:

Available Formats

ECO220Y: Homework 13

(1) Practice your understanding of the P‐value.

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.