1 / 27

Chapter 13: Chi-Square Procedures

Chapter 13: Chi-Square Procedures. 13.1 Test for Goodness of Fit 13.2 Inference for Two-Way Tables. M&Ms Example. Sometimes we want to examine the distribution of proportions in a single population. As opposed to comparing distributions from two populations, as in Chapter 12.

yvon
Télécharger la présentation

Chapter 13: Chi-Square Procedures

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. Chapter 13: Chi-Square Procedures 13.1 Test for Goodness of Fit 13.2 Inference for Two-Way Tables

  2. M&Ms Example • Sometimes we want to examine the distribution of proportions in a single population. • As opposed to comparing distributions from two populations, as in Chapter 12. • Does the distribution of colors in your bags match up with expected values? • We can use a chi-square goodness of fit test. • Χ2 • We would not want to do multiple one-proportion z-tests. • Why?

  3. Performing a X2 Test 1. H0: the color distribution of our M&Ms is as advertised: Pbrown=0.30, Pyellow=Pred=0.20, and Porange=Pgreen=Pblue=0.10 Ha: the color distribution of our M&Ms is not as advertised. • Conditions: • All individual expected counts are at least 1. • No more than 20% of expected counts are less than 5. • Chi-square statistic:

  4. X2 Family of Distribution Curves • Used to assess the evidence against H0 represented in the value of X2. • The member of the family we choose is determined only by the degrees of freedom. • P-value is the probability of observing a value X2 at least as extreme as the one actually observed.

  5. X2 Family of Distribution Curves (Figure 13.2, p. 732)

  6. Performing a test with our calculators • Enter data: • L1: observed values (not percentages) • L2: expected values • L3: (L1-L2)2/L2 • LIST/MATH Sum (L3) • X2cdf(ans,1099, df)

  7. Practice • Exercise 13.10, p. 743

  8. More Practice • Exercise 13.4, p. 737

  9. 13.4 summary

  10. 13.4 Follow-Up • So we reject the null, but so what? • What does this mean in the context of the problem? • Where did the differences occur?

  11. Graph for Problem 13.4

  12. Section 13.2: Inference for Two-Way Tables

  13. Example 13.4, pp. 744-748 • Is there a difference between proportion of successes? • At left is a two-way table for use in studying this question. • Explanatory Variable: • Type of Treatment • Response Variable: • Proportion of no relapses

  14. Example 13.4, pp. 744-748 • H0: p1=p2=p3 • Ha: at least one proportion is not equal to the others.

  15. Example 13.4, pp. 744-748 • We need expected counts for each cell: • For our example, 2/3 relapsed (48/72). So, if Ho is true, then 24(2/3) of those taking Desipramine would relapse. • Write expected counts for each cell in your table at the bottom of page 747.

  16. Chi-Square Test forHomogeneity of Populations • In this example, we are comparing the proportion of relapses in three populations: addicts who take desipramine, addicts who take lithium, and addicts who take a placebo. • Our question is this: Are the populations homogeneous in terms of the proportion of relapsed addicts? • We use a chi-square test for homogeneity of populations.

  17. Conditions • All individual expected counts are at least one, and • No more than 20% of expected counts are less than 5.

  18. Calculations for Example 13.4 Note: df=(#r-1)(#c-1)=(3-1)(2-1)=2

  19. Full Analysis of Example 13.4 • See Example 13.7, p. 752

  20. Practice • 13.14, pp. 748-749

  21. Let’s begin with a practice problem … • 13.15, p. 749 + 13.17, p. 756

  22. Two Settings for Chi-Square Testsfor Two-Way Tables • Yesterday we studied the problem of treatments for cocaine addicts. The cocaine addicts study is an experiment that assigned 24 addicts to each of three groups. Each group is a sample from a separate population corresponding to a separate treatment. • We used a chi-square test for homogeneity of populations. (H0: p1=p2=p3 vs. Ha: at least one not the same) • Today, we look at problems where subjects from a single sample are classified with respect to a categorical variable. • We will use a chi-square test of association/independence. • Notes: • See bottom paragraph, p. 763. • The analysis for today’s problem will be essentially identical to the analysis from yesterday.

  23. Example • 13.9, 13.10, and 13.11, pp. 758-761 • Hypotheses: • H0: there is no relationship between smoking status and SES (two categorical variables). • Ha: there is a relationship between smoking status and SES.

  24. Expected Counts and Conditions • All expected counts are at least 1, no more than 20% less than 5.

  25. Practice Problem • 13.20, p. 762 • Make a bar graph to show the data graphically before beginning your calculations for the chi-square test.

  26. Graph for 13.20

  27. Practice • 13.32, p. 770 • Chapter 13 Test on Tuesday.

More Related