options FORMDLIM="#";

/* This is a "Comment" in SAS */
/***************************************************************
         Columns     Description
         -------      -----------
          1- 2       Serial No. (1-25) within each group of 25
                     (the order in which data points were
                     abstracted)

          4          Number of companions (0, 1, or 8)

          6          Type of companion
                         0: newly pregnant female
                         1: virgin female
                         9: not applicable (when PARTNERS=0)

          8- 9       Lifespan, in days

         11-14       Length of thorax, in mm (x.xx)

         16-17       Percentage of each day spent sleeping
**************************************************************/

/* Read in data from local drive */
data fruitfly;
  infile "My Documents\stat230\fruitfly3.txt";
  input fly companions type lifespan thorax sleeppercent group $;
run;

/* OR */
/* Read in data from webpage (url) */
data fruitfly;
  infile "http://tofu.byu.edu/stat230/fruitfly3.txt" url;  
     /* NOTE: if there was a header row on fruitfly3.txt, we could tell
          SAS to ignore the first line and find the first observation
          on row 2 by changing the infile statement to:
             infile "http://tofu.byu.edu/stat230/fruitfly3.txt" url firstobs=2;
          There is no header row here on fruitfly3.txt so the firstobs option
          is unnecessary, but there will be a header row on the cancer.txt file 
          on your homework.
     */
  input fly companions type lifespan thorax sleeppercent group $;
run;

proc print; run;

proc glm data=fruitfly;
  class group;
  model lifespan = group;
  means group;  /* This gives means for the levels of 'group'.  
                   If you wanted to get t tests for comparing each 
                   possible pair of group means, you could use:
                      means group / t;
                */
run;