Reference no: EM131033832

The file 'assignment4data.txt' containing data for patients who screened on a tobacco screening day held at a local hospital has been uploaded to the EG SAS server.

Each column in the file is tab separated from the other. First column contains patient's Gender (1=male 2= female) Second column contains patient's Age Third column contains patient's Race (1=White, 2=Black, 3=Hispanic, and 4=Asian) Fourth column contains patient's Smoking status (1=yes and 2= no) Fifth column contains patient's Diastolic blood pressure Sixth column contains patient's Systolic blood pressure Seventh column contains patient's Education status (0= not high school educated and 1= high school educated) (Note: Assume that the patients were randomly selected and put into different Race categories and independent of each other.)

As a data analysis expert, you were asked to perform data analysis and to generate results to be included in the annual report for that tobacco screening program. You were asked to do the following:

Question 1: Read the data into SAS using appropriate variable names.

Question 2: Verify if there is any difference in Systolic blood pressure among the Race categories.

a. Which type of analysis is appropriate and why?

b. Is there is any difference (explain why or why not)? c. Identify the different group(s) (if any) with 95% confidence limits. Clearly identify your dependent variable and independent variables in your explanation.

Question 3: Verify the correlation of Systolic blood pressure, Diastolic blood pressure, and Education with respect to Smoking status. Which type of correlation is appropriate to report? Explain your result with appropriate values and statistics with their meaning.

Question 4: Can you predict Education level of a patient from Smoking status? How? Show the plot for prediction.