options nocenter ls=80 ;

PROC PRINTTO log="descript.out" print="descript.out" new;
run;


* just read in make price mpg rep78 foreign ;
DATA auto ;
  input MAKE $ PRICE MPG REP78 FOREIGN ;
DATALINES;
AMC    4099 22 3 0
AMC    4749 17 3 0
AMC    3799 22 3 0
Audi   9690 17 5 1
Audi   6295 23 3 1
BMW    9735 25 4 1
Buick  4816 20 3 0
Buick  7827 15 4 0
Buick  5788 18 3 0
Buick  4453 26 3 0
Buick  5189 20 3 0
Buick 10372 16 3 0
Buick  4082 19 3 0
Cad.  11385 14 3 0
Cad.  14500 14 2 0
Cad.  15906 21 3 0
Chev.  3299 29 3 0
Chev.  5705 16 4 0
Chev.  4504 22 3 0
Chev.  5104 22 2 0
Chev.  3667 24 2 0
Chev.  3955 19 3 0
Datsun 6229 23 4 1
Datsun 4589 35 5 1
Datsun 5079 24 4 1
Datsun 8129 21 4 1
;
RUN;

PROC PRINT DATA=auto(obs=10);
RUN;

* lets examine the variables rep78, mpg, price and foreign ;
* we can get frequency tables for them as shown below ;
PROC FREQ DATA=auto;
  TABLES make ;
RUN;

PROC FREQ DATA=auto;
  TABLES rep78 ;
RUN;

PROC FREQ DATA=auto;
  TABLES foreign ;
RUN;


* You can specify multiple variables on the TABLES statement, so we ;
* could have done this more easily like this ;
PROC FREQ DATA=auto;
  TABLES make price mpg rep78 foreign ;
RUN;

* Let's look at repair history for domestic and foreign cars. ;
PROC FREQ DATA=auto;
  TABLES rep78*foreign ;
RUN;

* we can show just the cell percentages to make the table easier to read;
PROC FREQ DATA=auto;
  TABLES rep78*foreign / NOROW NOCOL NOFREQ ;
RUN;

* notice that the order of the options does not matter as long as ;
* they appear after the / ;
PROC FREQ DATA=auto;
  TABLES rep78*foreign / NOFREQ NOROW NOCOL ;
RUN;

* for summary statistics, we can use PROC MEANS ;
PROC MEANS DATA=auto;
  VAR  mpg;
RUN:

PROC MEANS DATA=auto;
  CLASS foreign ;
  VAR  mpg;
RUN:

* for more detailed information, we can use PROC UNIVARIATE ;
PROC UNIVARIATE DATA=auto;
  VAR mpg;
RUN;

* we might want to get the univariate statistics separately for foreign ;
* and domestic cars.  to do this, you would be tempted to try ;
* PROC UNIVARIATE DATA=auto;
*    CLASS foreign;
*    VAR mpg;
* RUN;
* 
* Unfortunately, UNIVARIATE does not support the CLASS statement.  But ;
* we have another way we can do this using SORT and the BY statement ;
PROC SORT DATA=auto;
  BY foreign;
RUN;

PROC UNIVARIATE DATA=auto;
  BY foreign;
  VAR mpg;
RUN;