17.01.2015 Views

LibraryPirate

LibraryPirate

LibraryPirate

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

244 CHAPTER 7 HYPOTHESIS TESTING<br />

We wish to know if we may conclude, on the basis of these results, that, in general,<br />

persons with thrombosis have, on the average, higher IgG levels than persons without<br />

thrombosis.<br />

Solution:<br />

1. Data. See statement of example.<br />

2. Assumptions. The statistics were computed from two independent samples<br />

that behave as simple random samples from a population of persons<br />

with thrombosis and a population of persons who do not have<br />

thrombosis. Since the population variances are unknown, we will use the<br />

sample variances in the calculation of the test statistic.<br />

3. Hypotheses.<br />

or, alternatively,<br />

H 0 : m T - m NT … 0<br />

H A : m T - m NT 7 0<br />

H 0 : m T … m NT<br />

H A : m T 7 m NT<br />

4. Test statistic. Since we have large samples, the central limit theorem<br />

allows us to use Equation 7.3.5 as the test statistic.<br />

5. Distribution of test statistic. When the null hypothesis is true, the test<br />

statistic is distributed approximately as the standard normal.<br />

6. Decision rule. Let a = .01. This is a one-sided test with a critical<br />

value of z equal to 2.33. Reject if z computed Ú 2.33.<br />

7. Calculation of test statistic.<br />

H 0<br />

z =<br />

59.01 - 46.61<br />

44.89 2<br />

A 53<br />

+ 34.852<br />

54<br />

= 1.59<br />

8. Statistical decision. Fail to reject H 0 , since z = 1.59 is in the nonrejection<br />

region.<br />

9. Conclusion. These data indicate that on the average, persons with<br />

thrombosis and persons without thrombosis may not have differing IgG<br />

levels.<br />

10. p value. For this test, p = .0559. When testing a hypothesis about the<br />

difference between two populations means, we may use Figure 6.4.1 to<br />

decide quickly whether the test statistic should be z or t.<br />

■<br />

We may use MINITAB to perform two-sample t tests. To illustrate, let us<br />

refer to the data in Table 7.3.1. We put the data for control subjects and spinal cord

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!