*NKNW096, diagnostics for simple linear regression;

options nocenter;
*This goption turns off the color in plots;
goptions colors=(none);

*reads in external file.  A new variable is created which
	represents the observation or sequence number; 
data a1;
infile 'C:\Ageorge\Purdue\Stat512\Textdata\CH01TA01.dat';
input lotsize workhrs;
seq=_n_;

proc print data=a1; 
run;

*generates summary statistics and a qqplot for both x and y.
 	The normal option in qqplot assesses fit to the normal 
 	distribution.  The other options draw the line the 
	observations should follow;
proc univariate data=a1 plot; 
var lotsize workhrs;
qqplot lotsize workhrs / normal (L=1 mu=est sigma=est); 
run;

*generates a plot of Y based on sequence order;
symbol1 v=circle i=sm70;
proc gplot data=a1; 
plot lotsize*seq/frame; 
run;