NAG Library Manual, Mark 28.4
Interfaces:  FL   CL   CPP   AD 

NAG CL Interface Introduction
Example description
/* nag_correg_robustm_corr_huber (g02hkc) Example Program.
 *
 * Copyright 2022 Numerical Algorithms Group.
 *
 * Mark 28.4, 2022.
 *
 */

#include <nag.h>
#include <stdio.h>

#define X(I, J) x[(I - 1) * tdx + J - 1]
int main(void) {
  Integer exit_status = 0, i, iter, j, k, l1, l2, m, max_iter, n, print_iter;
  Integer tdx;
  NagError fail;
  double *cov = 0, eps, *theta = 0, tol, *x = 0;

  INIT_FAIL(fail);

  printf("nag_correg_robustm_corr_huber (g02hkc) Example Program Results\n");

  /* Skip heading in data file */
  scanf("%*[^\n]\n");

  /* Read in the dimensions of X */
  scanf("%" NAG_IFMT " %" NAG_IFMT " %*[^\n]\n", &n, &m);

  if (n > 1 && (m >= 1 && m <= n)) {
    if (!(x = NAG_ALLOC((n) * (m), double)) ||
        !(theta = NAG_ALLOC(m, double)) ||
        !(cov = NAG_ALLOC(m * (m + 1) / 2, double))) {
      printf("Allocation failure\n");
      exit_status = -1;
      goto END;
    }
    tdx = m;
  } else {
    printf("Invalid n or m.\n");
    exit_status = 1;
    return exit_status;
  }
  /* Read in the x matrix */
  for (i = 1; i <= n; ++i) {
    for (j = 1; j <= m; ++j)
      scanf("%lf", &X(i, j));
    scanf("%*[^\n]\n");
  }

  /* Read in value of eps */
  scanf("%lf%*[^\n]\n", &eps);

  /* Set up remaining parameters */
  max_iter = 100;
  tol = 5e-5;

  /* Set print_iter to a positive value for iteration monitoring */
  print_iter = 0;
  /* nag_correg_robustm_corr_huber (g02hkc).
   * Robust estimation of a correlation matrix, Huber's weight
   * function
   */
  fflush(stdout);
  nag_correg_robustm_corr_huber(n, m, x, tdx, eps, cov, theta, max_iter,
                                print_iter, 0, tol, &iter, &fail);
  if (fail.code != NE_NOERROR) {
    printf("Error from nag_correg_robustm_corr_huber (g02hkc).\n%s\n",
           fail.message);
    exit_status = 1;
    goto END;
  }

  printf("\nnag_correg_robustm_corr_huber (g02hkc) required %" NAG_IFMT
         " iterations "
         "to converge\n\n",
         iter);
  printf("Covariance matrix\n");
  l2 = 0;
  for (j = 1; j <= m; ++j) {
    l1 = l2 + 1;
    l2 += j;
    for (k = l1; k <= l2; ++k)
      printf("%10.3f", cov[k - 1]);
    printf("\n");
  }
  printf("\ntheta\n");
  for (j = 1; j <= m; ++j)
    printf("%10.3f\n", theta[j - 1]);

END:
  NAG_FREE(x);
  NAG_FREE(theta);
  NAG_FREE(cov);
  return exit_status;
}