The data provided include 25 patients discharged from a selected Pennsylvania hospital as part of a retrospective chart review of antibiotic usage in hospitals. You may assume these data are a SRS from a larger population of interest. The data set (n=25 observations and 9 variables) is available with this test as an Excel file. Variables and corresponding units provided for each observation include: ? P_Id: patient ID number (1-25) ? Dur_stay: duration of hospital stay (days) ? Age: age (years) at the time discharged from the hospital ? Sex: 1=Male, 2=Female ? Temp: first temperature following admission (degree Fahrenheit) ? WBC: first white blood cell count (per 1000) following admission ? Antibio: antibiotic status, received antibiotic (1=yes, 2=no) ? Bact_cul: received bacterial culture (1=yes, 2=no) ? Service: 1=med, 2=surg

1a) Suppose investigators are interested in testing if the mean temperature is different from 98.6 degrees.

• Include all steps for hypothesis testing:
• State the null and alternative hypothesis in words (that apply to this scenario) and symbols.
• Check any assumptions including addressing whether normality is needed or if It is met. Explain briefly and proceed with hypothesis testing even if this assumption is not met.
• Display any plot that you used to check assumptions.
• Calculate the test statistic. Show a few interim steps as practical.
• Calculate the p-value. ? State the degrees of freedom if appropriate.
• If you use software, state the command you used and/or include a portion of the output. If you used a table, state that.
• Interpret the p-value for a non-statistician in the context of the problem. [The p-value is a probability .... What is it the probability in THIS problem? Do NOT use the words "null hypothesis."] Do NOT simply state whether or not the result is statistically significant.

1b) Compute and interpret a 90% confidence interval for the mean temperature. Include your STATA output and command OR your calculation by hand including the formula used.

1c) Investigators are interested in comparing the temperature of males vs. females. Construct two side-by-side boxplots to help the investigator compare the temperature of males and females.

Comments: Your graphs should be descriptive, organized, and clear. Think carefully about labeling, clarity and communication. Graphing is more than the mechanics of the software; you must communicate a story accurately and succinctly to address the interests of the investigators.