1 / 15

Module 22: Proportions: One Sample

This module explores hypothesis testing and confidence intervals for proportions using one random sample from a population. It includes examples and calculations for males keeping appointments and asthma prevalence.

ecrabtree
Download Presentation

Module 22: Proportions: One Sample

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Module 22: Proportions: One Sample This module presents confidence intervals and tests of hypotheses for proportions for the situation with one random sample from a population. Reviewed 06 June 05 /MODULE 22 22 - 1

  2. Proportions P = Population parameter, the proportion of population with characteristic x = Number in sample with the characteristic n = Total number in sample p = x/n, the sample estimate of the proportion with the characteristic 22 - 2

  3. Hypothesis tests and confidence intervals are based on the normal approximation to the binomial distribution. For the hypothesis: H0: P = P0 vs. H1: P  P0 The options for the test statistic are: where Q0 = 1- P0 22 - 3

  4. Example: AJPH, Nov. 1977;67:1033 - 1036 22 - 4

  5. 22 - 5

  6. One Sample Hypothesis test Table 1 on the previous page indicates that 85.39% of the 1,109 males kept their appointments. Suppose that you had worked in this area previously and the percent of appointments kept before had always been 90% or higher. A question this raises is whether this observed rate is sufficiently different from 90% for you to think your population was different. That is, you would like to test the hypothesis: H0: PM = 0.90 vs. H1: PM 0.90 22 - 6

  7. Hypothesis test for males keeping appointments • The hypothesis: H0: PM = 0.90 vs. H1: PM 0.90 • 2.The assumptions: Independence • 3.The  level:  = 0.05 • 4. The test statistic: • 5. The rejection region: Reject H0: PM = 0.90 if z is not between 1.96 22 - 7

  8. 6. The result: 7. The conclusion: Reject H0: PM = 0.90 since z is not between ± 1.96 22 - 8

  9. Confidence Interval for P Confidence Interval for P, with  = 0.05 22 - 9

  10. Appointment keeping behavior for males 22 - 10

  11. 22 - 11

  12. 22 - 12

  13. Social Class I, Asthma or Wheezy bronchitis n = 191 p = 0.047 or 4.7% 1. The hypothesis: H0: P = 0.10 vs. H1: P 0.10 2. The assumptions: Independence 3. The -level :  = 0.05 4. The test statistic: 5. The rejection region: Reject H0: P = 0.10, if z is not between ±1.96 22 - 13

  14. 6. The result: 7. The conclusion: Reject H0: P = 0.10, since z is not between ± 1.96 22 - 14

  15. Confidence Interval for P with  = 0.05 n = 191, p = 0.047, p(1-p) = 0.047(0.953) = 0.0448 22 - 15

More Related