17.01.2015 Views

LibraryPirate

LibraryPirate

LibraryPirate

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

7.5 HYPOTHESIS TESTING: A SINGLE POPULATION PROPORTION 259<br />

sample sufficiently large for application of the central limit theorem as discussed in Section<br />

5.5 is available for analysis, the test statistic is<br />

z = pN - p 0<br />

p 0 q 0<br />

A n<br />

which, when H 0 is true, is distributed approximately as the standard normal.<br />

(7.5.1)<br />

EXAMPLE 7.5.1<br />

Wagenknecht et al. (A-20) collected data on a sample of 301 Hispanic women living in<br />

San Antonio, Texas. One variable of interest was the percentage of subjects with impaired<br />

fasting glucose (IFG). IFG refers to a metabolic stage intermediate between normal glucose<br />

homeostasis and diabetes. In the study, 24 women were classified in the IFG stage.<br />

The article cites population estimates for IFG among Hispanic women in Texas as 6.3<br />

percent. Is there sufficient evidence to indicate that the population of Hispanic women<br />

in San Antonio has a prevalence of IFG higher than 6.3 percent<br />

Solution:<br />

1. Data. The data are obtained from the responses of 301 individuals<br />

of which 24 possessed the characteristic of interest; that is, Np =<br />

24>301 = .080.<br />

2. Assumptions. The study subjects may be treated as a simple random<br />

sample from a population of similar subjects, and the sampling distribution<br />

of Np is approximately normally distributed in accordance with<br />

the central limit theorem.<br />

3. Hypotheses.<br />

H 0 : p … .063<br />

H A : p 7 .063<br />

We conduct the test at the point of equality. The conclusion we reach<br />

will be the same as we would reach if we conducted the test using any<br />

other hypothesized value of p greater than .063. If H 0 is true, p = .063<br />

and the standard error s pN = 11.06321.9372>301. Note that we use the<br />

hypothesized value of p in computing s pN . We do this because the<br />

entire test is based on the assumption that the null hypothesis is true.<br />

To use the sample proportion, pN , in computing s pN would not be consistent<br />

with this concept.<br />

4. Test statistic. The test statistic is given by Equation 7.5.1.<br />

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

is approximately normally distributed with a mean of zero.<br />

6. Decision rule. Let a = .05. The critical value of z is 1.645. Reject<br />

if the computed z is Ú1.645.<br />

H 0

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

Saved successfully!

Ooh no, something went wrong!