options ls=78;
title "Confidence Intervals - 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 noprint;
  by variable;
  var diff;
  output out=a n=n mean=xbar var=s2;
  run;

 /* The data step here is used to calculate the confidence interval
  * limits from the statistics calculated in the data set 'a'.
  * The values 't' and'f' are the critical values used in the 
  * Bonferroni and F intervals, respectively.
  * /

data b;
  set a;
  f=finv(0.95,&p,n-&p);
  t=tinv(1-0.025/&p,n-1);
  losim=xbar-sqrt(&p*(n-1)*f*s2/(n-&p)/n); 
  upsim=xbar+sqrt(&p*(n-1)*f*s2/(n-&p)/n); 
  lobon=xbar-t*sqrt(s2/n);
  upbon=xbar+t*sqrt(s2/n);
  run;

proc print data=b;
  run;