A mobile computer network consists of a number of computers (called nodes) that communicate with each other while moving throughout a region. A node that is out of transmission range of the other nodes, so that it is unable to communicate, is said to be partitioned. In studies carried out at the Colorado School of Mines, S. Kurkowski found that in a network containing 185 nodes in which destinations were chosen at random from a uniform distribution, 19 nodes were partitioned. J. Norman found that in a network containing 164 nodes whose movements mimicked those on a college campus, 30 nodes were partitioned. Find a 99% confidence interval for the difference between the proportions of partitioned nodes in the two networks.

5.

The enrolled student population at Indiana University-Bloomington, both undergraduate and graduate, is 64.9% White, 7.76% Asian, 7.32% Hispanic or Latino, 4.52% Two or More Races, 4.26% Black or African American, 0.0463% American Indian or Alaska Native, and 0.0287% Native Hawaiian or Other Pacific Islanders. Suppose that in a random sample of 250 students, 40 of them are Asian. Suppose we sample another 250 students from this population, what is the expected proportion of Asian students? b. a. C. Suppose we sample another 250 students from this population, what is the standard deviation of the proportion of Asian students? For a sample of 250 students out of this population, what is the probabilty that the proportion of Asian students is between 6% and 8%?

3) The following two sets of Excel output use are from the same data set as described above, but the first set of output is for the set of 35 CEO’s that earn the lowest total compensation and the second set of output is for a set of 40 CEO’s that earn the highest total compensation. a) What is heteroscedasticity? b) Why is heteroscedasticity a problem? c) Based on a comparison of the two sets of output, does it appear that there is heteroscedasticity in the data set? Explain.