SAS 3: Inputting data manually for Odds Ratios and Relative Risk
Last week, you learned how to read an excel file into SAS. There are other ways to get data into SAS. For instance, if you already have your 2x2 table ready and you just want SAS to calculate either your Odds Ratio or your Relative Risk, you can input the data directly into SAS using a function called datelines. Here is an example of how data lines works. Note in the code below the data is called GORDIS, and the input are delineated by the $ telling the data what each column represents
DATA gordis ;
INPUT exposed $ disease $ patients ;
DATALINES ;
exposed disease 50
exposed none 50
not_exp disease 25
not_exp none 75
;
PROC FREQ DATA = gordis ;
TABLES exposed*disease / RELRISK RISKDIFF;
WEIGHT patients ;
RUN ;
1. Run the above program and screenshot the results. You will now put that into a word document as part of your submission.
2. Now look up your own example of a 2x2 table. Create your own code and screenshot the code as well as the result. You want to change the labels of the graph to reflect your own data yet. You also should change the name of the data file.
SAS 4: Graphing Prevalence
We are going to work on how to graph annual prevalence rates for the purposes of evaluating and comparing different countries trends. We are going to use the datelines function to input some data from a variety of different sources. This data is fictitious, but at the end of this assignment, you will be asked to collect and aggregate your own data on a disease of your choosing.
DATA HIVDATA ;
INPUT Country $ Year $ HIVPrev ;
DATALINES ;
USA XXXXXXXXXX
USA XXXXXXXXXX
USA XXXXXXXXXX
USA XXXXXXXXXX
Nigeria XXXXXXXXXX
Nigeria XXXXXXXXXX
Nigeria XXXXXXXXXX
Nigeria XXXXXXXXXX
RUN ;
Then we are going to craft a line graph to look at all the trends across the different years between these two countries.
PROC SORT
DATA=WORK.HIVDATA(KEEP=Year HIVPrev Country)
OUT=WORK.SORTTempTableSorted
;
BY Year;
RUN;
SYMBOL1
INTERPOL=JOIN
HEIGHT=10pt
VALUE=NONE
LINE=1
WIDTH=2
CV = _STYLE_
;
SYMBOL2
INTERPOL=JOIN
HEIGHT=10pt
VALUE=NONE
LINE=1
WIDTH=2
CV = _STYLE_
;
Legend1
FRAME
;
Axis1
STYLE=1
WIDTH=1
MINOR=NONE
;
Axis2
STYLE=1
WIDTH=1
MINOR=NONE
;
TITLE;
TITLE1 "HIV Prevalence per 100,000 Population as reported by WHO, XXXXXXXXXX";
FOOTNOTE;
FOOTNOTE1 "APA Reference Should go Here";
PROC GPLOT DATA = WORK.SORTTempTableSorted
;
PLOT HIVPrev * Year =Country
VAXIS=AXIS1
HAXIS=AXIS2
FRAME LEGEND=LEGEND1
;
RUN;
1. Screen shot your results and input them into a word document.
2. You are going to select a disease. Using the data lines you are going to input some type of geographic variable (Country, Zip code, or State). You are going to have three columns of information Geography, Year, Incidence or Prevalence rate.
Your title should accurately reflect what your graph represents. In footnote1 you will need to include in APA all the references that you used to make the table.