What to hand in: Entire SAS program and all relevant output and plots generated. Be sure to answer all questions.
A SAS dataset called tomhscv on the class website contains risk factor and cardiovascular outcome data on all 902 participants in the TOMHS study. The following variables are on the dataset.
Variable Name
Description
group treatment group assigned (1-5 active drug, 6=placebo)age of participant at entry (baseline)
sex gender, 1=men, 2=women
eversmk question of whether the participant ever smoke cigarettes (1=yes, 2=no)
nowsmk question of whether the participant now smokes cigarettes (1=yes, 2=no). This question is asked only if the the variable eversmk = 1. These questions were asked at baseline.
sbpbl systolic BP at baseline
sbp12 systolic BP at 12-months
cholbl blood serum cholesterol at baseline
chol12 blood serum cholesterol at 12-months
hdlbl blood HDL cholesterol at baseline
hdl12 blood HDL cholesterol at 12-months
glucosbl blood glucose at baseline
glucos12 blood glucose at 12-months
cvd CVD event status during the study (1=yes,2=no) Do the following:
In a data-step read in the dataset tomhscv creating a work dataset called tomhs and adding the following
Define a variable called smoke = 1 if the participant is a current smoker at baseline and 0 if not a current smoker at baseline, i.e. an ex-smoker or never-smoker (use variables eversmk and nowsmk).
Define a variable called dm = 1 if the participant’s glucose at baseline is above 126 mg/dl and 0 if 126 mg/dl or below at
Define a variable called active = 1 if on active BP medication and 0 for
Define a variable called rxold = 1 if group is equal to 1 or 3, and = 2 if group is equal to 2,4, or The placebo group (group = 6) should be missing.
When creating new variables be sure to account for missing data. For example, the variable smoke should only be defined for those that completed the item eversmk.
Write SAS code to perform the following analysis and to answer the following questions. You may need to add additional variables to your dataset.
How many and what percentage of participants were current smokers at baseline? How many participants had missing data for smoking?
How many and what percentage of participants experienced a CVD event during the study?
Did being on active treatment lower the risk of CVD during the trial? Give the odds ratio of CVD for active treatment versus placebo. (Hint: Use either proc freq or prog logist).
Using proc logist which of the following baseline variables are significantly related to CVD?
1) age, 2) gender (women versus men), 3) systolic BP, 4) serum cholesterol, 5) smoking, and
6) diabetes (variable dm). Include all these variables in one model. What is the adjusted odds ratio of CVD for smokers versus non-smokers?
Did the older or newer drugs reduce systolic BP more at 12-months compared to baseline? Was the difference in SBP change between the two groups significant? (Hint: Use proc ttest or proc glm).
DescriptionIn this final assignment, the students will demonstrate their ability to apply two ma
Path finding involves finding a path from A to B. Typically we want the path to have certain properties,such as being the shortest or to avoid going t
Develop a program to emulate a purchase transaction at a retail store. Thisprogram will have two classes, a LineItem class and a Transaction class. Th
1 Project 1 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of
1 Project 2 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of