/* Example of finding summary statistics and graphs using SAS */

/* The data are the gas mileage data from p. 30 on the textbook */

/* The following commands name the data set and variables and list the data */
/* Please read the "Introduction to SAS" on the course web page first */


OPTIONS pagesize=50 linesize=64;

DATA gasdata;

INPUT mileage;

CARDS;

     36.3
       41
     36.9
     37.1
     44.9
     36.8
       30
     37.2
     42.1
     36.7
     32.7
     37.3
     41.2
     36.6
     32.9
     36.5
     33.2
     37.4
     37.5
     33.6
     40.5
     36.5
     37.6
     33.9
     40.2
     36.4
     37.7
     37.7
       40
     34.2
     36.2
     37.9
       36
     37.9
     35.9
     38.2
     38.3
     35.7
     35.6
     35.1
     38.5
       39
     35.5
     34.8
     38.6
     39.4
     35.3
     34.4
     38.8
     39.7
     36.3
     36.8
     32.5
     36.4
     40.5
     36.6
     36.1
     38.2
     38.4
     39.3
       41
     31.8
     37.3
     33.1
       37
     37.6
       37
     38.7
       39
     35.8
       37
     37.2
     40.7
     37.4
     37.1
     37.8
     35.9
     35.6
     36.7
     34.5
     37.1
     40.3
     36.7
       37
     33.9
     40.1
       38
     35.2
     34.8
     39.5
     39.9
     36.9
     32.9
     33.8
     39.8
       34
     36.8
       35
     38.1
     36.9
;

/* The following procedure produces several summary statistics and graphs */

/* DATA= tells SAS which data set to use */
/* VAR tells SAS which variable to compute the statistics and graphs for */

/* If there are several variables in the data set */
/* you could specify more than one variable with VAR */


PROC UNIVARIATE DATA=gasdata PLOT FREQ;

VAR mileage;

TITLE 'Summary of the Gas Mileages for the 100 Cars';

RUN;

/* PROC UNIVARIATE gives summary statistics about the variable "mileage" */
/* Look for the mean, median, variance, standard deviation, etc. */

/* The PLOT FREQ command produces a stem-and-leaf display and boxplot */
/* Notice the UNIVARIATE procedure produces rather rudimentary graphs */

/* The INSIGHT procedure will give us the same thing as UNIVARIATE */
/* but with more and nicer-looking graphs. */

/* The syntax is slightly different in INSIGHT: */

PROC INSIGHT;

OPEN gasdata;

DIST mileage;

RUN;

/* The graphs INSIGHT produces are a box plot and a histogram.*/

/* To change the class intervals, */
/* click on the arrow at the bottom left of the histogram. Choose "Ticks". */
/* First Tick is the start of the first interval, */
/* Last Tick is the end of the last interval, */
/* and Tick Increment is the interval width.  */

/* Note how changing the class intervals changes the look of the histogram. */

/* Note that the histogram shown is a relative frequency histogram. */
/* To get a frequency histogram, while still in PROC INSIGHT, */
/* choose the "Analyze" menu, and choose "Histogram/Bar Chart". */
/* Click on the name of the variable (here, MILEAGE) and then click "Y". */
/* Click "OK" and a frquency histogram should appear. */

/* You can copy and paste the graphs from PROC INSIGHT into Microsoft Word */
/* Click on the border of the box you want, and copy and paste as normal */

/* To quit PROC INSIGHT or remove the INSIGHT graphs, */
/* click the X in the upper right box of the graph(s) */