Project 3
The primary objective of the Study on the Efficacy of Nosocomial Infection Control (SENIC Project) was to determine whether infection surveillance and control programs have reduced the rates of nosocomial (hospital-acquired) infection in United States hospitals. This data set consists of a random sample of 113 hospitals from a study done between 1975-1976. Each line of the data set has an identification number and provides information on 11 other variables for a single hospital.

Use this data set to answer questions 1,2,3, and 4. The data can be found on the course website in SPSS and Excel formats.

1. The effect of average age on mean infection risk is to be studied. For this study average age is to be classified into four categories: under 50.0,50.0-54.9,55.0-59.9,60. and over. Assume a one-way ANOVA model is appropriate. Test whether or not the mean infection risk differs among the four age groups. State the null hypothesis, alternative, and conclusion.
2. Obtain confidence intervals for all pairwise comparisons between the four regions maintaining an experimental error rate of $\alpha=0.1$. Identify and use the method (out of the ones discussed in the course) which produces the narrowest set of confidence intervals.
3. Certain hospitals are to be considered in a study of the effects of region (factor A) and average age of patients (factor B) on the mean length of hospital stay. The ID numbers of the hospitals are as follows,

For this study age is to be classified into two categories: less than or equal to 53.9 years, 54.0 years or older. Assume a two-way ANOVA model with interaction is appropriate.

1. Prepare an estimated treatment means plot. Interpret the results.
2. Obtain the ANOVA table. Does any one source account for most of the total variability? Explain.
3. Test whether or not interaction is significant at \(\alpha=0.05\). State the null hypothesis, alternative, and conclusion. Compute the \(p\) -value of the test.
4. Test whether or not region and age main effects are significant. In each case use \(\alpha=0.05\). State the null hypothesis, alternative, and conclusion. Compute the \(p\) -value for each test. Is it meaningful to test for main factor effects here? Explain.

4. Consider testing

where \(\mu\) is the mean percent of infection risk.

1. Use the first 13 observations to obtain an estimate of the standard deviation \(\sigma\). Conduct the test at \(\alpha=0.05\) using the remaining 100 observations.
2. Compute the power of the test from part (a) when \(\mu=3.5,3.8,4.1,4.4,4.7\), by simulating at least 1000 variables from a snoncentral \(t\) distribution for each $\mu$. The previously estimated standard deviation may be used again.

Price: $20.24

Solution: The downloadable solution consists of 12 pages, 824 words and 15 charts.
Deliverable: Word Document