.TH REGRES 3M
.SH NAME
regres
.SH DESCRIPTION
subroutine regres.f

source
  Bevington, pages 172-175.

purpose
  make mulitple linear regression fit to data with specified
    function which is linear in coefficients

usage
  call regres (x, y, sigmay, npts, nterms, m, mode, yfit,
    a0, a, sigma0, sigmaa, r, rmul, chisqr, ftest)

description of parameters
  x      - array of points for independent variable
  y      - array of points for dependent variable
  sigmay - array of standard deviations for y data points
  npts   - number of pairs of data points
  nterms - number of coefficients
  m      - array of inclusion/rejection criteria for fctn
  mode   - determines method of weighting least-squares fit
           +1 (instrumental) weight(i) = 1./sigmay(i)**2
            0 (no weighting) weight(i) = 1.
           -1 (statistical)  weight(i) = 1./y(i)
  yfit   - array of calculated values of y
  a0     - constant term
  a      - array of coefficients
  sigma0 - standard deviation of a0
  sigmaa - array of standard deviations for coefficients
  r      - array of linear correlation coefficients
  rmul   - multiple linear correlation coefficient
  chisqr - reduced chi square for fit
  ftest  - value of f for test of fit

subroutines and function subprograms required
  fctn (x, i, j, m)
    evaluates function for the jth term and the ith data
      point using array m to specify terms in function
  matinv (array, nterms, det)
    inverts symmetric two-dimension matrix of degree nterms
      and calculates its determinant

comments
  valid for npts up to 100 and nterms up to 10
  one source line modified - sigmaa substituted for sigmaag