2. To test the null hypothesis pi = P2 with two independent samples of sizes nį and n2, we require that n1 < N1/20, that n2 < N2/20, that n1 * pi * (1 – p1) > 10, and that n2 * p2 * (1– p2) > 10. Our test statistic TS is pi – p2 Va•(1 – p) • (+ + +) where p is the pooled estimate p = (x1 + x2)/(n1 + n2). (a) For a two-tailed test, we may compute +za/2 = ±InvNorm(a/2,0, 1) and check that the test-statistic falls in a tail. Or we may instead compute P = 2 * normalcdf (|TS|, 0,0, 1) and check that P < a. Suppose our null hypothesis is pi p2, that our sample sizes are ni = 1500 and n2 = 1600, and that we find x1 = 506 and x2 = 692. Assume that N1 and N2 are very large. i. If we use a two-tailed test, what is our alternative hypothesis: pi + p2 ? pi < P2 ? or pi > P2 ? ii. What would we conclude if we rejected the null hypothesis with a two-tailed test? iii. Can we reject the null hypothesis at level of significance a = 0.05, using a two-tailed test? iv. Can we reject the null hypothesis at level of significance a = 0.01, using a two-tailed test?

Algebra & Trigonometry with Analytic Geometry
13th Edition
ISBN:9781133382119
Author:Swokowski
Publisher:Swokowski
Chapter10: Sequences, Series, And Probability
Section10.8: Probability
Problem 31E
icon
Related questions
Question
Solve questions 1 through 4 please
2. To test the null hypothesis p1 = P2 with two independent samples of sizes ni and n2, we require that ni < N1/20,
that n2 < N2/20, that n1 * p1 * (1 – p1) > 10, and that n2 p2 * (1 – p2) > 10. Our test statistic TS is
pi – p2
p• (1 – p) • (+ + )
where p is the pooled estimate p = (x1 + x2)/(n1 + n2).
(a) For a two-tailed test, we may compute ±z,/2 = ±InvNorm(a/2,0, 1) and check that the test-statistic falls
in a tail. Or we may instead compute P = 2 * normalcdf (|TS\, 0, 0, 1) and check that P < a. Suppose
our null hypothesis is pi = P2, that our sample sizes are ni = 1500 and n2 = 1600, and that we find
x1 = 506 and x2 = 692. Assume that N1 and N2 are very large.
i. If we use a two-tailed test, what is our alternative hypothesis: p1 # p2 ? p1 < p2 ? or pi > p2 ?
ii. What would we conclude if we rejected the null hypothesis with a two-tailed test?
iii. Can we reject the null hypothesis at level of significance a = 0.05, using a two-tailed test?
iv. Can we reject the null hypothesis at level of significance a = 0.01, using a two-tailed test?
Transcribed Image Text:2. To test the null hypothesis p1 = P2 with two independent samples of sizes ni and n2, we require that ni < N1/20, that n2 < N2/20, that n1 * p1 * (1 – p1) > 10, and that n2 p2 * (1 – p2) > 10. Our test statistic TS is pi – p2 p• (1 – p) • (+ + ) where p is the pooled estimate p = (x1 + x2)/(n1 + n2). (a) For a two-tailed test, we may compute ±z,/2 = ±InvNorm(a/2,0, 1) and check that the test-statistic falls in a tail. Or we may instead compute P = 2 * normalcdf (|TS\, 0, 0, 1) and check that P < a. Suppose our null hypothesis is pi = P2, that our sample sizes are ni = 1500 and n2 = 1600, and that we find x1 = 506 and x2 = 692. Assume that N1 and N2 are very large. i. If we use a two-tailed test, what is our alternative hypothesis: p1 # p2 ? p1 < p2 ? or pi > p2 ? ii. What would we conclude if we rejected the null hypothesis with a two-tailed test? iii. Can we reject the null hypothesis at level of significance a = 0.05, using a two-tailed test? iv. Can we reject the null hypothesis at level of significance a = 0.01, using a two-tailed test?
Expert Solution
steps

Step by step

Solved in 2 steps with 1 images

Blurred answer
Knowledge Booster
Truth Tables
Learn more about
Need a deep-dive on the concept behind this application? Look no further. Learn more about this topic, statistics and related others by exploring similar questions and additional content below.
Recommended textbooks for you
Algebra & Trigonometry with Analytic Geometry
Algebra & Trigonometry with Analytic Geometry
Algebra
ISBN:
9781133382119
Author:
Swokowski
Publisher:
Cengage