options ls=78;
title "Profile Plot - Spouse Data";

 /* %let allows the p variable to be used throughout the code below
  * After reading in the spouse data, where each variable is
  * originally in its own column, the next statements define difference
  * variables between husbands and wives, and they stack the data
  * so that all group labels (1 through 4) are in one column called 'variable',
  * and all differences are in another column called 'diff'.
  * This format is used for the calculations that follow.
  */

%let p=4;
data spouse;
  infile "D:\Statistics\STAT 505\data\spouse.csv" firstobs=2 delimiter=',';
  input h1 h2 h3 h4 w1 w2 w3 w4;
  variable=1; diff=h1-w1; output;
  variable=2; diff=h2-w2; output;
  variable=3; diff=h3-w3; output;
  variable=4; diff=h4-w4; output;
  drop h1 h2 h3 h4 w1 w2 w3 w4;
  run;

proc sort;
  by variable;
  run;

 /* The means procedure calculates and saves the sample size,
  * mean, and variance for each variable. It then saves these results 
  * in a new data set 'a' for use in the final step below.
  * /

proc means data=spouse;
  by variable;
  var diff;
  output out=a n=n mean=xbar var=s2;
  run;

 /* The data step here is used to calculate the simultaneous
  * confidence intervals based on the F-multiplier
  * from the statistics calculated in the data set 'a'.
  * /

data b;
  set a;
  f=finv(0.95,&p,n-&p);
  diff=xbar; output;
  diff=xbar-sqrt(&p*(n-1)*f*s2/(n-&p)/n); output;
  diff=xbar+sqrt(&p*(n-1)*f*s2/(n-&p)/n); output;
  run;

 /* The axis commands define the size of the plotting window.
  * The horizontal axis is of the variables, and the vertical
  * axis is used for the confidence limits.
  * The reference line of 0 corresponds to the null value of the 
  * difference for each variable.
  * /

proc gplot data=b;
  axis1 length=4 in;
  axis2 length=6 in;
  plot diff*variable / vaxis=axis1 haxis=axis2 vref=0 lvref=21;
  symbol v=none i=hilot color=black;
  run;