ST590G -- FALL 2012 
     
  Class Exercise #8 -- Thursday, 08 November 2012

  Our Group ___________________________________________________

    In the 'fiba' directory are the results from the preliminary rounds
    of the basketball competition at the 2012 Olympics.  These were
    round robins (each team play every other team) for two groups of
    six teams.  So each team plays 5 games; 15 games in a group.

    There are two sources of the data.  You can read the data directly
    from the website (see nov07.ex5) or use one of files in the 'fiba' 
    directory: menoly12A, menoly12B, woly12A, woly12B. 


    1) Read the results of the fifteen games for your group and create
    a dataset with 15 observations, and variables with two team names
    and scores.

    2) Create a SAS dataset with the team (country) names.

    3) Create two formats from that SAS dataset, one to go from a code
    number (1 to 6) to a team, another (character format) to go from
    a team name to a (character) number.  

    4) Construct a dataset with explanatory variables X1 up to X6.
    For a given game between home team h and away team a, Xh is 1 and 
    Xa is -1, and all of the other Xj are 0 (these teams are not involved).  
    Also construct a response variable Y whose value is the difference 
    between the scores: home - away. (Since some of the games are
    blow-outs, you can also log-transform the scores:
       y = log(home) - log(away) ;   
    and interpret the ratings on a log scale.)
  
    5) Do the statistical analysis by running the following code:
      proc glm data=whatever ;
        model y = x1-x6 ;
    run ;
   
    and report the ranking of the teams in the group.