4
6/18/09 1 1 §9.2 Testing the Difference of Two Means (with large independent samples) Assumptions for the z-test of two means: The samples from each population must be independent of one another. The populations from which the samples are taken must be normally distributed and the population standard deviations must be know, or the sample sizes must be large (i.e. n 1 30 and n 2 30. 2

Assumptions for the z-test of two meansweb02.gonzaga.edu/faculty/rayr/ma121/Section9.2.pdf · Assumptions for the z-test of two means: • The samples from each population must be

  • Upload
    others

  • View
    9

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Assumptions for the z-test of two meansweb02.gonzaga.edu/faculty/rayr/ma121/Section9.2.pdf · Assumptions for the z-test of two means: • The samples from each population must be

6/18/09

1

1

§9.2 Testing the Difference of Two Means

(with large independent samples)

Assumptions for the z-test of two means: •  The samples from each population must be independent of

one another. •  The populations from which the samples are taken must be

normally distributed and the population standard deviations must be know, or the sample sizes must be large (i.e. n1≥30 and n2≥30.

2

Page 2: Assumptions for the z-test of two meansweb02.gonzaga.edu/faculty/rayr/ma121/Section9.2.pdf · Assumptions for the z-test of two means: • The samples from each population must be

6/18/09

2

3

The test statistic:

4

Example:

A medical researcher wishes to see whether the pulse rates of smokers are higher than the pulse rates of non-smokers. Samples of 100 smokers and 100 nonsmokers are selected. The results are shown below. Can the researcher conclude at α = .05, that smokers have higher pulse rates than nonsmokers?

H0: µ1 - µ2 = 0 H1: µ1 - µ2 > 0

Nonsmokers Smokers

Page 3: Assumptions for the z-test of two meansweb02.gonzaga.edu/faculty/rayr/ma121/Section9.2.pdf · Assumptions for the z-test of two means: • The samples from each population must be

6/18/09

3

5

6

Example

A researcher claims that students in a private school have exam scores that are at most 8 points higher than those of students in public schools. Random samples of 45 and 60 students from each type of school are selected and given an exam. At α = 0.05 test the hypothesis H0: µ1 - µ2 = 8 against H1: µ1 - µ2 > 8

n1 = 45

s1 = 12

Public schools Private Schools

Page 4: Assumptions for the z-test of two meansweb02.gonzaga.edu/faculty/rayr/ma121/Section9.2.pdf · Assumptions for the z-test of two means: • The samples from each population must be

6/18/09

4

7

Confidence intervals for the difference of two means.

8

Example (construction of a confidence interval)

Two groups of students are given a problem-solving test, and the results are compared. Find the 90% confidence interval of the true difference in means.

Computer Science Majors

Mathematics Majors